Nothing Special   »   [go: up one dir, main page]

WO2020258936A1 - 一种基于共享地图的定位方法及装置、电子设备和存储介质 - Google Patents

一种基于共享地图的定位方法及装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2020258936A1
WO2020258936A1 PCT/CN2020/080465 CN2020080465W WO2020258936A1 WO 2020258936 A1 WO2020258936 A1 WO 2020258936A1 CN 2020080465 W CN2020080465 W CN 2020080465W WO 2020258936 A1 WO2020258936 A1 WO 2020258936A1
Authority
WO
WIPO (PCT)
Prior art keywords
current frame
map data
feature
matching
feature points
Prior art date
Application number
PCT/CN2020/080465
Other languages
English (en)
French (fr)
Inventor
谢卫健
王楠
钱权浩
章国锋
Original Assignee
浙江商汤科技开发有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 浙江商汤科技开发有限公司 filed Critical 浙江商汤科技开发有限公司
Priority to SG11202108199YA priority Critical patent/SG11202108199YA/en
Priority to JP2021543389A priority patent/JP7261889B2/ja
Publication of WO2020258936A1 publication Critical patent/WO2020258936A1/zh
Priority to US17/383,663 priority patent/US20210350170A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/757—Matching configurations of points or features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes

Definitions

  • the present disclosure relates to the field of positioning technology, and in particular to a positioning method and device based on a shared map, electronic equipment and storage medium.
  • simultaneous localization and mapping is a robot moving from an unknown location in an unknown environment. Start to move, and perform self-positioning according to the position estimation and map during the movement, so as to realize the autonomous positioning and map sharing of the robot.
  • the present disclosure proposes a positioning technical solution based on a shared map.
  • a positioning method based on a shared map including:
  • the local map data associated with the key frame can be extracted from the global map data containing at least one key frame.
  • the local map data associated with the key frame contains candidate frames composed of multiple key frames that are most similar to the current frame, so that the amount of key frame data for feature matching with the current frame increases. Therefore, the feature matching The accuracy is improved accordingly, and after the positioning result of the current frame is obtained according to the matching result, the multiple terminals are moved and positioned on the shared map according to the positioning result, so that precise positioning between each other can be achieved.
  • the method before the obtaining the current frame in the image collected by the second terminal, the method further includes: determining whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and If it is less than the expected threshold, triggering the processing of supplementing the feature points of the current frame.
  • the current frame collected by the second terminal includes the current frame obtained after performing the process of supplementing the characteristic points of the current frame.
  • the current frame collected by the second terminal can be the current frame obtained by directly using the feature points extracted in the current frame, or the current frame obtained after performing the process of supplementing the feature points of the current frame, so as to adopt according to actual needs Different feature point extraction methods.
  • performing the processing of supplementing the feature points of the current frame includes:
  • the first screening threshold is adaptively adjusted according to the reference information to obtain a second screening threshold, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the feature points obtained by actual collection Quantity.
  • the screening threshold can be adaptively adjusted, and feature points can be added to the current frame according to the adjusted screening threshold, so that the number of feature points is greater than the actual The number of feature points acquired by the collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • any external information or information of the current frame itself will affect the adaptive adjustment of the screening threshold.
  • the feature points are subsequently added to the current frame according to the adjusted screening threshold.
  • the number of feature points is greater than the number of feature points obtained by actual collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • the feature matching the current frame with the local map data, and obtaining the positioning result of the current frame according to the matching result includes:
  • the current frame and the at least one key frame in the local map data are matched with feature points from 2D to 2D, that is, the position in the two-dimensional space is determined. Since the pose includes orientation and displacement, the displacement can be described by the position in the two-dimensional space. This form of orientation can be determined, and 3D information is also required. Therefore, it is necessary to filter out those containing 3D information from the 2D feature matching results. 2D feature matching results and extract the 3D information, so as to obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as the positioning result, so that multiple terminals are evaluated according to the positioning result Movement and positioning in the shared map can achieve precise positioning between each other.
  • a positioning method based on a shared map including:
  • the first terminal performs image collection to obtain global map data including at least one key frame
  • the first terminal extracts the local map data associated with the key frame from the global map data
  • the first terminal receives the current frame collected by the second terminal, performs feature matching between the current frame and the local map data, obtains the positioning result of the current frame according to the matching result, and sends the positioning result.
  • global map data including at least one key frame is collected through the first terminal, and positioning is performed on the first terminal side, specifically, from the global map data, a local map associated with the key frame is extracted Data, perform feature matching between the current frame obtained from the second terminal and the local map data, obtain the positioning result of the current frame according to the matching result, and send the positioning result to the second terminal. Because the local map data associated with the key frame can be extracted from the global map data containing at least one key frame. According to the positioning result, the multiple terminals are moved and positioned on the shared map, so that precise positioning can be achieved with each other.
  • the first terminal extracting the local map data associated with the key frame from the global map data includes:
  • the data of the predetermined range extracted with the key frame as the reference center must be the local map data associated with the key frame, and the key frame and its associated local map data are collectively regarded as matching the current frame
  • the information which increases the amount of data for feature point matching, so that a more accurate matching effect can be obtained.
  • the feature matching the current frame with the local map data, and obtaining the positioning result of the current frame according to the matching result includes:
  • the current frame and the at least one key frame in the local map data are matched with feature points from 2D to 2D, that is, the position in the two-dimensional space is determined. Since the pose includes orientation and displacement, the displacement can be described by the position in the two-dimensional space. This form of orientation can be determined, and 3D information is also required. Therefore, it is necessary to filter out those containing 3D information from the 2D feature matching results. 2D feature matching results and extract the 3D information, so as to obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as the positioning result, so that multiple terminals are evaluated according to the positioning result Movement and positioning in the shared map can achieve precise positioning between each other.
  • a positioning method based on a shared map including:
  • the second terminal performs image collection, obtains the current frame in the collected image, and sends the current frame
  • the positioning result is a result obtained by the first terminal according to the matching result by performing feature matching on the local map data associated with the current frame and the key frame;
  • the global map data is map data containing at least one key frame in the image collected by the first terminal, and the amount of data is greater than the local map data.
  • positioning is performed on the side of the first terminal, and multiple terminals are moved and positioned on a shared map according to the positioning result, and precise positioning between each other can be achieved. Further, the supplementary processing of the feature points of the current frame is performed on the second terminal. By supplementing the feature points of the current frame, the feature point data for feature matching is improved, and the accuracy of the feature matching is improved accordingly.
  • the method before the second terminal performs image collection to obtain the current frame in the collected image, the method further includes: judging whether the number of feature points extracted from the current frame is less than that used for feature matching The expected threshold value, when less than the expected threshold value, triggers the process of supplementing the feature points of the current frame.
  • the current frame collected by the second terminal includes the current frame obtained after performing the process of supplementing the characteristic points of the current frame.
  • the current frame collected by the second terminal can be the current frame obtained by directly using the feature points extracted in the current frame, or the current frame obtained after performing the process of supplementing the feature points of the current frame, so as to adopt according to actual needs Different feature point extraction methods.
  • performing the processing of supplementing the feature points of the current frame includes:
  • the first screening threshold is adaptively adjusted according to the reference information to obtain a second screening threshold, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the feature points obtained by actual collection Quantity.
  • the screening threshold can be adaptively adjusted, and feature points can be added to the current frame according to the adjusted screening threshold, so that the number of feature points is greater than the actual The number of feature points acquired by the collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • any external information or information of the current frame itself will affect the adaptive adjustment of the screening threshold.
  • the feature points are subsequently added to the current frame according to the adjusted screening threshold.
  • the number of feature points is greater than the number of feature points obtained by actual collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • a positioning method based on a shared map including:
  • the second terminal receives global map data including at least one key frame, and extracts local map data associated with the key frame from the global map data;
  • the second terminal performs image collection to obtain the current frame in the collected image
  • the second terminal performs feature matching between the current frame and the local map data, and obtains the positioning result of the current frame according to the matching result.
  • positioning is performed on the second terminal side, specifically by extracting the local map data associated with the key frame from the global map data, and the current frame obtained from the second terminal and the local map The data is matched with features, and the positioning result of the current frame is obtained according to the matching result. Because the local map data associated with the key frame can be extracted from the global map data containing at least one key frame. According to the positioning result, the multiple terminals are moved and positioned on the shared map, so that precise positioning can be achieved with each other.
  • the method before the second terminal performs image collection to obtain the current frame in the collected image, the method further includes: judging whether the number of feature points extracted from the current frame is less than that used for feature matching The expected threshold value, when less than the expected threshold value, triggers the process of supplementing the feature points of the current frame.
  • the current frame includes a current frame obtained after performing a process of supplementing feature points on the current frame.
  • the current frame collected by the second terminal can be the current frame obtained by directly using the feature points extracted in the current frame, or the current frame obtained after performing the process of supplementing the feature points of the current frame, so as to adopt according to actual needs Different feature point extraction methods.
  • performing the processing of supplementing the feature points of the current frame includes:
  • the first screening threshold is adaptively adjusted according to the reference information to obtain a second screening threshold, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the feature points obtained by actual collection Quantity.
  • the screening threshold can be adaptively adjusted, and feature points can be added to the current frame according to the adjusted screening threshold, so that the number of feature points is greater than the actual The number of feature points acquired by the collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • any external information or information of the current frame itself will affect the adaptive adjustment of the screening threshold.
  • the feature points are subsequently added to the current frame according to the adjusted screening threshold.
  • the number of feature points is greater than the number of feature points obtained by actual collection. Therefore, more feature points are used for feature matching, and the matching effect will be more accurate.
  • the feature matching the current frame with the local map data, and obtaining the positioning result of the current frame according to the matching result includes:
  • the current frame and the at least one key frame in the local map data are matched with feature points from 2D to 2D, that is, the position in the two-dimensional space is determined. Since the pose includes orientation and displacement, the displacement can be described by the position in the two-dimensional space. This form of orientation can be determined, and 3D information is also required. Therefore, it is necessary to filter out those containing 3D information from the 2D feature matching results. 2D feature matching results and extract the 3D information, so as to obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as the positioning result, so that multiple terminals are evaluated according to the positioning result Movement and positioning in the shared map can achieve precise positioning between each other.
  • a positioning method based on a shared map including:
  • positioning is performed in the cloud, and the positioning result is sent to the second terminal. Because the local map data associated with the key frame can be extracted from the global map data containing at least one key frame. According to the positioning result, the multiple terminals are moved and positioned on the shared map, so that precise positioning can be achieved with each other.
  • a positioning device based on a shared map including:
  • the first extraction unit is configured to extract the local map data associated with the key frame from the global map data including at least one key frame of the image collected by the first terminal;
  • the first obtaining unit is configured to obtain the current frame in the image collected by the second terminal;
  • the first matching unit is configured to perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result.
  • the device further includes: a trigger unit, configured to:
  • the device further includes: a feature point supplement unit, configured to:
  • the first screening threshold is adaptively adjusted according to the reference information to obtain a second screening threshold, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the feature points obtained by actual collection Quantity.
  • a positioning device based on a shared map including:
  • the first acquisition unit is used for image acquisition to obtain global map data including at least one key frame;
  • the first extraction unit is configured to extract the local map data associated with the key frame from the global map data
  • the first matching unit is configured to receive the current frame collected by the second terminal, perform feature matching between the current frame and the local map data, obtain the positioning result of the current frame according to the matching result, and send the positioning result.
  • the first matching unit is further configured to:
  • a positioning device based on a shared map including:
  • the second acquisition unit is configured to perform image acquisition, obtain the current frame in the acquired image, and send the current frame;
  • the second matching unit is configured to receive a positioning result, where the positioning result is a result obtained by the first terminal according to the matching result by performing feature matching on the local map data associated with the current frame and the key frame;
  • the global map data is map data containing at least one key frame in the image collected by the first terminal, and the amount of data is greater than the local map data.
  • the device further includes: a feature point supplement unit, configured to:
  • the first screening threshold is adaptively adjusted according to the reference information to obtain a second screening threshold, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the feature points obtained by actual collection Quantity.
  • a positioning device based on a shared map including:
  • the second extraction unit is configured to receive global map data including at least one key frame, and extract local map data associated with the key frame from the global map data;
  • the second acquisition unit is used for image acquisition to obtain the current frame in the acquired image
  • the second matching unit is configured to perform feature matching between the current frame and the local map data, and obtain the positioning result of the current frame according to the matching result.
  • a positioning device based on a shared map including:
  • the first receiving unit is configured to receive global map data including at least one key frame of the image collected by the first terminal, and extract local map data associated with the key frame from the global map data;
  • the second receiving unit is configured to receive the current frame in the image collected by the second terminal;
  • the third matching unit is configured to perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result;
  • the third positioning unit is used to send the positioning result.
  • an electronic device including:
  • a memory for storing processor executable instructions
  • the processor is configured to execute the aforementioned positioning method based on a shared map.
  • a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the foregoing positioning method based on a shared map is realized.
  • a computer program wherein the computer program includes computer-readable code, and when the computer-readable code runs in an electronic device, a processor in the electronic device executes To realize the above-mentioned positioning method based on shared map.
  • the local map data associated with the key frame is extracted from the global map data containing at least one key frame of the image collected by the first terminal; the current image in the image collected by the second terminal is obtained Frame; feature matching of the current frame and the local map data, and obtain the positioning result of the current frame according to the matching result.
  • the local map data associated with the key frame can be extracted from the global map data including at least one key frame.
  • the local map data associated with the key frame contains candidate frames composed of multiple key frames that are most similar to the current frame, so that the amount of key frame data for feature matching with the current frame increases.
  • the feature matching The accuracy is improved, and the positioning result of the current frame is obtained according to the matching result, which can move and locate multiple terminals (the first terminal and the second terminal are not limited to one terminal, but only serve as a reference) in the shared map. Can achieve precise positioning between each other.
  • Fig. 1 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Fig. 2 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Fig. 3 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Fig. 4 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Fig. 5 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Fig. 6 shows a schematic diagram of a process of supplementing feature points of a current frame according to an embodiment of the present disclosure.
  • FIG. 7 shows a schematic diagram of the process of locating the pose of the current frame according to an embodiment of the present disclosure.
  • Fig. 8 shows a block diagram of a positioning device based on a shared map according to an embodiment of the present disclosure.
  • FIG. 9 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 10 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
  • the SLAM problem can be described as: the robot starts to move from an unknown position in an unknown environment, and locates itself according to the position estimation and the map during the movement, and at the same time Build incremental maps on the basis of self-positioning to realize autonomous positioning and navigation of robots.
  • the robots need to share each other's position in a scene, they need to share each other's position through map sharing, and use positioning technology to determine each other's position on the shared map, so as to determine their position relationship in the real world.
  • augmented reality AR, Augmented Reality
  • VR Virtual Reality
  • the map constructed by the SLAM system based on lidar is a dense point cloud.
  • the point cloud is a massive collection of points that express the spatial distribution and surface characteristics of the target under the same spatial reference system.
  • the positioning is mainly based on the matching of two point clouds, that is, the feature matching of the corresponding feature points of the two point cloud data images.
  • the equipment cost of lidar is relatively high, and based on the positioning technology of point cloud alignment, the calculation amount will be relatively large.
  • the cost of a camera is much lower than that of lidar.
  • the problems of using the above positioning technology are: First, in many cases, due to the limitations of computing performance or the SLAM framework, the number of feature points extracted in each frame of image is limited, otherwise it may be time-consuming to extract feature points. The performance of the SLAM algorithm is dragged down for a long time, which may cause positioning failures in scenes with changing perspectives or weak textures. Second, in the case that each frame of image carries a small number of feature points, positioning based on the matching between two frames of images is likely to cause positioning failure due to too few feature points in the image itself. With the present disclosure, any of the following strategies can be adopted, or the two strategies can be used in combination, with the aim of increasing the amount of data used for feature matching, thereby improving the positioning ability under weak texture conditions, and making full use of map information, Improve the positioning success rate.
  • the positioning unit can be used for positioning (the positioning unit can be on the first terminal side, the second terminal side or the cloud).
  • the positioning unit can be on the first terminal side, the second terminal side or the cloud.
  • Strategy 2 When using the current frame to locate on the shared map, adaptively add feature points according to the environment, so that the number of feature points extracted on the current frame is always at a higher number, for example, the feature points extracted on the current frame The number is greater than the actual number of feature points obtained in the current frame when the SLAM system itself is used for tracking. Obviously, the amount of data used for feature matching has increased, and consequently, the positioning success rate has also increased.
  • FIG. 1 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • the positioning method based on a shared map is applied to a positioning device based on a shared map.
  • a positioning device based on a shared map may be used by a terminal device or a server.
  • the terminal equipment can be a user equipment (UE, User Equipment), a mobile device, a cellular phone, a cordless phone, a personal digital processing (PDA, Personal Digital Assistant), a handheld device, a computing device, a vehicle-mounted device, Wearable devices, etc.
  • the positioning method based on a shared map may be implemented by a processor invoking computer-readable instructions stored in a memory. As shown in Figure 1, the process includes:
  • Step S101 Extract local map data associated with the key frame from the global map data including at least one key frame of the image collected by the first terminal.
  • the local map data associated with the key frame may be local point cloud data associated with the key frame, and the local point cloud data may select the key frame as the center.
  • Key frame refers to the candidate frame most similar to the current frame.
  • Step S102 Obtain the current frame in the image collected by the second terminal.
  • the current frame is directly feature-matched with the local map data. If the number of feature points in the current frame is less than the expected threshold, the process of supplementing feature points in the current frame is triggered.
  • Step S103 Perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result.
  • step S103 it may further include: obtaining, according to the positioning result, the positional relationship between the first terminal and the second terminal in the case that the first terminal and the second terminal share the global map data.
  • Using the present disclosure different from the feature matching of the current frame and the key frame to achieve positioning, it uses more feature points for feature matching, for example, feature the current frame and the local point cloud data formed by the key frame as the center match.
  • Using local point cloud data is to use more feature points, or to use a local map to supplement the matching relationship between the current frame and the key frame, so as to achieve more accurate processing effects and accurate positioning.
  • FIG. 2 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • the positioning method based on a shared map is applied to a positioning device based on a shared map.
  • a positioning device based on a shared map may be used by a terminal device or a server.
  • the terminal equipment can be a user equipment (UE, User Equipment), a mobile device, a cellular phone, a cordless phone, a personal digital processing (PDA, Personal Digital Assistant), a handheld device, a computing device, a vehicle-mounted device, Wearable devices, etc.
  • the positioning method based on a shared map can be implemented by a processor calling a computer-readable instruction stored in a memory. As shown in Figure 2, the process includes:
  • Step S201 Extract local map data associated with the key frame from the global map data including at least one key frame in the image collected by the first terminal.
  • the local map data associated with the key frame may be local point cloud data associated with the key frame, and the local point cloud data may select the key frame as the center.
  • Key frame refers to the candidate frame most similar to the current frame.
  • Step S202 It is determined whether the number of feature points extracted from the current frame is less than the expected threshold for feature matching, and if it is less than the expected threshold, step S203 is executed; otherwise, step S204 is executed.
  • the above-mentioned expected threshold may not be reached.
  • Step S203 Trigger the process of supplementing the feature points of the current frame, and execute the process of supplementing the feature points of the current frame.
  • a feature point addition unit that supplements the feature points of the current frame may be used, and the feature point addition unit is located on the side of the second terminal for collecting the current frame.
  • Step S204 Obtain the current frame in the image collected by the second terminal.
  • the current frame is the current frame obtained by acquiring images; if the number of feature points in the current frame is less than the expected threshold, the current frame is the execution The current frame obtained after the process of supplementing the feature points of the current frame.
  • Step S205 Perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result.
  • Step S206 Obtain, according to the positioning result, the positional relationship between the first terminal and the second terminal when the global map data is shared.
  • the present disclosure is different from the comparison between the current frame and the key frame to achieve alignment, and the feature points of the current frame can be supplemented, that is, more feature point comparisons are used to achieve more accurate processing effects and accurate positioning.
  • the amount of feature point data in the current frame is consistent with the actual number of feature points obtained when the SLAM system itself is used for tracking.
  • the number of feature points that can be extracted under weak texture conditions may drop sharply.
  • when extracting the current frame The number of feature points extracted will be more than the number of feature points actually obtained during SLAM tracking (it can be twice or more than the number of feature points actually obtained during LAM tracking), and it will Additional points are added, which increases the number of feature points extracted in the current frame and improves the positioning success rate. And by adaptively modifying the threshold of the points, the feature point extraction ability in weak texture scenes is enhanced.
  • two terminals are positioned based on a shared map as an example.
  • Two users hold a mobile phone and play an AR game at the same table.
  • two mobile phones can observe and interact with the same AR effect, which requires the two terminals to be in the same coordinate system and know each other's poses, and sharing each other's poses needs to be based on the shared map.
  • Positioning Specifically, the first terminal (mobile phone 1) performs image collection to obtain global map data including at least one key frame.
  • the local map data (such as local point cloud data) associated with the key frame is extracted from the global map data, and the local point cloud data can select the key frame (the candidate frame most similar to the current frame) as the center.
  • the current frame (or the current frame obtained after adding feature points) is feature-matched with the local point cloud data, and the local map is used to supplement the matching relationship between the current frame and the key frame to improve the positioning success rate.
  • the positioning result of the current frame is obtained according to the matching result, and the positional relationship between the first terminal (mobile phone 1) and the second terminal (mobile phone 2) when the global map data is shared by the positioning result.
  • the meaning of sharing means that the first terminal (mobile phone 1) and the second terminal (mobile phone 2) are located in the same coordinate system where the map is located, and can locate each other's position or pose and other information in the same coordinate system.
  • performing the processing of supplementing the feature points of the current frame includes: obtaining a first screening threshold for feature point extraction of the current frame, and adaptively adjusting the first screening threshold according to reference information To obtain a second screening threshold, and add feature points to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • the reference information includes: at least one of environmental information for image acquisition, parameter information in the image acquisition device, and image information of the current frame itself.
  • the environmental information is one of the external factors that may lead to an insufficient number of extracted feature points: at least one type of information such as lighting conditions, surrounding occlusion, etc., is not limited to at least one that will lead to a small or reduced number of feature points. Impact information in this situation.
  • the parameter information in the image acquisition device may be sensor parameter information, which is the second external influence factor that may cause insufficient number of extracted feature points, such as the sensitivity, sharpness, exposure, contrast, etc. of the camera's sensor acquisition.
  • the image information of the current frame itself is one of the influencing factors that may cause insufficient number of feature points to be extracted. For example, some images have less texture and simple images. Correspondingly, the feature points available for extraction may not be available. many.
  • performing feature matching on the current frame and local map data, and obtaining the positioning result of the current frame according to the matching result includes: performing feature point 2D on at least one key frame in the current frame and the local map data Feature matching, and get a 2D feature matching result. From the 2D feature matching results, the 2D feature matching results containing 3D information are filtered out and the 3D information is extracted. Obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as the positioning result. Specifically, after performing feature matching from 2D to 2D feature points, 2D feature matching results containing 3D information (referred to as screening results) can be obtained by screening, and the pose of the current frame can be obtained according to the screening results.
  • screening results 2D feature matching results containing 3D information
  • FIG. 3 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • the positioning method based on a shared map is applied to a positioning device based on a shared map.
  • a positioning device based on a shared map can be used by a terminal device or a server.
  • the terminal equipment can be a user equipment (UE, User Equipment), a mobile device, a cellular phone, a cordless phone, a personal digital processing (PDA, Personal Digital Assistant), a handheld device, a computing device, a vehicle-mounted device, Wearable devices, etc.
  • UE user equipment
  • PDA Personal Digital Assistant
  • the positioning method based on a shared map may be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the positioning unit may be located on the side of the first terminal, as shown in FIG. 3, the process includes:
  • Step S301 The first terminal performs image collection to obtain global map data including at least one key frame.
  • Step S302 The second terminal performs image collection, obtains the current frame in the collected image, and sends the current frame to the second terminal.
  • Step S303 The first terminal extracts local map data associated with the key frame from the global map data.
  • the global map data is map data containing at least one key frame in the image collected by the first terminal, and the amount of data is larger than the local map data.
  • Step S304 The first terminal receives the current frame collected by the second terminal, performs feature matching between the current frame and the local map data, obtains the positioning result of the current frame according to the matching result, and sends the positioning result to the second terminal.
  • Step S305 The second terminal obtains the positional relationship between the first terminal and the second terminal when the global map data is shared by the first terminal and the second terminal according to the positioning result.
  • the first terminal extracts the local map data associated with the key frame from the global map data, which includes: taking the key frame as a reference center, and extracting the local map data according to the key frame And the map data obtained from the preset extraction range is used as the local map data.
  • performing feature matching of the current frame with the local map data, and obtaining a positioning result of the current frame according to the matching result includes: comparing the current frame with at least one of the local map data
  • the key frame performs 2D feature matching of feature points to obtain 2D feature matching results; from the 2D feature matching results, the 2D feature matching results containing 3D information are filtered out and the 3D information is extracted; and the 3D information is obtained according to the 3D information.
  • the pose of the current frame, and the pose of the current frame as the positioning result.
  • 2D feature matching results containing 3D information can be obtained by screening, and the pose of the current frame can be obtained according to the screening results.
  • the method further includes: the second terminal performs image collection, and before obtaining the current frame in the collected image, judging whether the number of feature points extracted from the current frame is less than that used for features The matched expected threshold, if less than the expected threshold, triggers the processing of supplementing the feature points of the current frame.
  • the current frame collected by the second terminal includes the current frame obtained after performing the process of supplementing the characteristic points of the current frame.
  • a first screening threshold for feature point extraction of the current frame is obtained; the first screening threshold is adaptively adjusted according to reference information to obtain a second screening threshold, and features are supplemented according to the second screening threshold Point to the current frame, when the number of feature points is greater than the number of feature points obtained by actual collection, the process of supplementing feature points for the current frame can be ended.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • FIG. 4 shows a flowchart of a positioning method based on a shared map according to an embodiment of the present disclosure.
  • the positioning method based on a shared map is applied to a positioning device based on a shared map.
  • a positioning device based on a shared map may be used by a terminal device or a server.
  • the terminal equipment can be a user equipment (UE, User Equipment), a mobile device, a cellular phone, a cordless phone, a personal digital processing (PDA, Personal Digital Assistant), a handheld device, a computing device, a vehicle-mounted device, Wearable devices, etc.
  • UE user equipment
  • PDA Personal Digital Assistant
  • the positioning method based on a shared map may be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the positioning unit may be located on the side of the second terminal, as shown in FIG. 4, the process includes:
  • Step S401 The second terminal receives global map data including at least one key frame, and extracts local map data associated with the key frame from the global map data.
  • Step S402 The second terminal performs image collection to obtain the current frame in the collected image.
  • Step S403 The second terminal performs feature matching between the current frame and the local map data, and obtains the positioning result of the current frame according to the matching result.
  • Step S404 The second terminal obtains the position relationship between the first terminal and the second terminal when the global map data is shared by the first terminal and the second terminal according to the positioning result.
  • the method further includes: the second terminal performs image collection, and before obtaining the current frame in the collected image, judging whether the number of feature points extracted from the current frame is less than that used for features The matched expected threshold, if less than the expected threshold, triggers the processing of supplementing the feature points of the current frame.
  • the current frame includes the current frame obtained after performing the process of supplementing the characteristic points of the current frame.
  • performing the process of supplementing the feature points of the current frame includes: obtaining a first screening threshold for extracting feature points of the current frame; and performing self-processing on the first screening threshold according to reference information
  • the second screening threshold is obtained by adaptive adjustment, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • the performing feature matching of the current frame with the local map data, and obtaining the positioning result of the current frame according to the matching result includes: comparing the current frame with the local map data Perform 2D feature matching of feature points on at least one key frame to obtain 2D feature matching results; from the 2D feature matching results, filter out 2D feature matching results containing 3D information and extract the 3D information; according to the 3D information Obtain the pose of the current frame, and use the pose of the current frame as the positioning result.
  • 2D feature matching results containing 3D information (referred to as screening results) can be obtained by screening, and the pose of the current frame can be obtained according to the screening results.
  • the positioning method based on a shared map can be applied to a positioning device based on a shared map.
  • a positioning device based on a shared map may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user Equipment (UE, User Equipment), mobile devices, cellular phones, cordless phones, personal digital processing (PDA, Personal Digital Assistant), handheld devices, computing devices, in-vehicle devices, wearable devices, etc.
  • the positioning method based on a shared map may be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the positioning unit may be located in the cloud, and the process includes: receiving global map data including at least one key frame of the image collected by the first terminal, and extracting local map data associated with the key frame from the global map data . Receive the current frame in the image collected by the second terminal. Perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result. Sending the positioning result to obtain, according to the positioning result, the positional relationship between the first terminal and the second terminal when the global map data is shared.
  • FIG. 5 shows a positioning method based on a shared map according to an embodiment of the present disclosure.
  • Take two terminal devices device one and device two
  • the positioning process includes: generating a map consisting of at least one key frame by scanning the scene through the device, and defining this map as a shared map.
  • This shared map can be saved locally on the device or uploaded to other terminal devices. (Such as device two), you can also store the shared map in the cloud.
  • One or more devices abbreviated as device two in the figure
  • that have a demand for shared maps can send the current frame data collected by the device to the positioning unit.
  • the positioning unit can run on any device or on the cloud.
  • the positioning unit can also obtain shared map data.
  • the positioning unit can obtain the positioning result of the current frame according to the current frame image and the shared map data, and transmit the positioning result back to the second device. In this way, the second device can obtain its relative pose with respect to the coordinate system of the shared map.
  • Fig. 6 shows a schematic diagram of a process of supplementing feature points of a current frame according to an embodiment of the present disclosure.
  • the second device can adaptively adjust the current frame image according to the feature point supplement unit to supplement and generate more feature points.
  • the process of adding feature points in the current frame includes the following:
  • Feature points and descriptors (or called feature descriptors).
  • the descriptor is a data structure that describes features, and the dimension of a descriptor can be multi-dimensional;
  • step 2 Check the number of feature points extracted in step 1. If the number of feature points is less than a specific expected threshold, skip to step 3, otherwise skip to step 4.
  • FIG. 7 shows a schematic diagram of the process of locating the pose of the current frame according to an embodiment of the present disclosure, and the positioning process can be realized by a positioning unit. As shown in Figure 7, the positioning process includes the following:
  • Input current frame data, shared map
  • the pose of the current frame can be optimized.
  • step 4 Determine whether the pose obtained in step 3 has enough interior points. If the number of interior points is less than a certain threshold, proceed to step 5; otherwise, skip to step 7.
  • the 2D feature matching results containing 3D information can be filtered (referred to as the screening results), and the current can be obtained according to the screening results.
  • the quality is based on feature matching. According to the quality, the feature points can be divided into internal points and external points. Among them, the inner point refers to the feature point with good quality; the outer point refers to the feature point with insufficient quality.
  • Multi-view geometry refers to the use of geometric methods to recover three-dimensional objects through several two-dimensional images.
  • Research three-dimensional reconstruction mainly used in computer vision.
  • Through multi-view geometry technology not only can the computer perceive the geometric information in the three-dimensional environment, including its shape, position, posture, movement, etc., but also describe, store, recognize and understand them.
  • computer vision it is necessary to find the feature matching points of two frames of images. For example, in one frame of two frames of image, 1000 feature points (two-dimensional) can be extracted according to the image quality and texture information; In another frame of the image, 1000 feature points (two-dimensional) can also be extracted based on the image quality and texture information.
  • not all 2D feature points contain 3D information , Or it contains applicable 3D information.
  • 3D information For example, only 300 2D feature points of these 600 feature points contain 3D information. Therefore, it is necessary to filter to obtain 2D feature matching results containing 3D information (referred to as screening results) and then filter according to the As a result, the pose of the current frame is obtained, which will be more accurate.
  • step 5 Based on the candidate frame obtained in step 1, select at least one frame that has a common view relationship with the candidate frame and use it as a key frame, and use the point cloud set contained in these key frames as local map data (or local point cloud) Data), use the pose obtained in step 3 as the initial pose for supplementary matching.
  • step 5 According to the matching result obtained in step 5, the pose of the current frame is optimized and the positioning result is returned.
  • the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possibility.
  • the inner logic is determined.
  • the present disclosure also provides a positioning device, electronic equipment, computer-readable storage medium, and a program based on a shared map, all of which can be used to implement any of the shared map-based positioning methods provided in the present disclosure, and the corresponding technical solutions and descriptions Please refer to the corresponding records in the method section, and will not repeat them.
  • FIG. 8 shows a block diagram of a positioning device based on a shared map according to an embodiment of the present disclosure.
  • the positioning device based on a shared map according to an embodiment of the present disclosure includes: a first extracting unit 31, configured to obtain data from the first Extract the local map data associated with the key frame from the global map data of the image collected by the terminal including at least one key frame; the first obtaining unit 32 is configured to obtain the current frame in the image collected by the second terminal; The first matching unit 33 is configured to perform feature matching between the current frame and the local map data, and obtain a positioning result of the current frame according to the matching result.
  • the device further includes: a first positioning unit, configured to obtain, according to the positioning result, the positional relationship between the first terminal and the second terminal when the global map data is shared.
  • the device further includes: a triggering unit, configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and if it is less than the expected threshold Next trigger the processing of supplementing the feature points of the current frame.
  • a triggering unit configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and if it is less than the expected threshold Next trigger the processing of supplementing the feature points of the current frame.
  • the current frame collected by the second terminal includes the current frame obtained after performing the processing of supplementing the characteristic points of the current frame.
  • the device further includes: a feature point supplement unit, configured to: obtain a first screening threshold for feature point extraction of the current frame; and perform self-checking on the first screening threshold according to reference information
  • the second screening threshold is obtained by adaptive adjustment, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • the first matching unit is further configured to: perform feature point 2D feature matching between the current frame and at least one key frame in the local map data to obtain a 2D feature matching result; From the 2D feature matching results, filter out the 2D feature matching results containing 3D information and extract the 3D information; obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as The positioning result.
  • the device includes: a first collection unit configured to perform image collection to obtain global map data including at least one key frame; From the global map data, extract the local map data associated with the key frame; the first matching unit is configured to receive the current frame collected by the second terminal, and perform feature matching between the current frame and the local map data, Obtain the positioning result of the current frame according to the matching result, and send the positioning result.
  • the first extraction unit is further configured to: take the key frame as a reference center, and use map data obtained according to the key frame and a preset extraction range as the local map data.
  • the first matching unit is further configured to: perform feature point 2D feature matching between the current frame and at least one key frame in the local map data to obtain a 2D feature matching result; From the 2D feature matching results, filter out the 2D feature matching results containing 3D information and extract the 3D information; obtain the pose of the current frame according to the 3D information, and use the pose of the current frame as The positioning result.
  • the device includes: a second acquisition unit configured to perform image acquisition to obtain the current frame in the acquired image, and send the current frame; and the second matching unit uses When receiving the positioning result, the positioning result is that the first terminal performs feature matching on the local map data associated with the current frame and the key frame, and the result is obtained according to the matching result; the second positioning unit is configured to perform feature matching according to the The positioning result obtains the positional relationship between the first terminal and the second terminal when the global map data is shared with each other; wherein, the global map data is the map data of at least one key frame included in the image collected by the first terminal and the amount of data is greater than The local map data.
  • the device further includes: a triggering unit, configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and if it is less than the expected threshold Next trigger the processing of supplementing the feature points of the current frame.
  • a triggering unit configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and if it is less than the expected threshold Next trigger the processing of supplementing the feature points of the current frame.
  • the current frame collected by the second terminal includes the current frame obtained after performing the processing of supplementing the characteristic points of the current frame.
  • the device further includes: a feature point supplement unit, configured to: obtain a first screening threshold for feature point extraction of the current frame; and perform self-checking on the first screening threshold according to reference information
  • the second screening threshold is obtained by adaptive adjustment, and feature points are added to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • the reference information includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • the device includes: a second extraction unit, configured to receive global map data including at least one key frame, and extract the key frame from the global map data.
  • the associated local map data the second collection unit is used for image collection to obtain the current frame in the collected image;
  • the second matching unit is used for feature matching the current frame with the local map data, according to The matching result obtains the positioning result of the current frame;
  • the second positioning unit is configured to obtain, according to the positioning result, the positional relationship between the first terminal and the second terminal when the global map data is shared.
  • the device further includes: a triggering unit, configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and trigger when the number is less than the expected threshold The processing of supplementing feature points for the current frame.
  • a triggering unit configured to determine whether the number of feature points extracted from the current frame is less than an expected threshold for feature matching, and trigger when the number is less than the expected threshold The processing of supplementing feature points for the current frame.
  • the current frame according to the embodiment of the present disclosure includes the current frame obtained after performing the process of supplementing feature points to the current frame.
  • the device further includes: a feature point addition unit, configured to: obtain a first screening threshold for feature point extraction of the current frame; and adaptively adjust the first screening threshold according to reference information To obtain a second screening threshold, and add feature points to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • a feature point addition unit configured to: obtain a first screening threshold for feature point extraction of the current frame; and adaptively adjust the first screening threshold according to reference information To obtain a second screening threshold, and add feature points to the current frame according to the second screening threshold, so that the number of feature points is greater than the number of feature points obtained by actual collection.
  • the reference information according to the embodiment of the present disclosure includes at least one of environmental information for image collection, parameter information in the image collection device, and image information of the current frame itself.
  • the second positioning unit is further configured to: perform feature point 2D feature matching between the current frame and at least one key frame in the local map data to obtain a 2D feature matching result; In the 2D feature matching results, the 2D feature matching results containing 3D information are filtered out and the 3D information is extracted; the pose of the current frame is obtained according to the 3D information, and the pose of the current frame is taken as the Positioning results.
  • the device includes: a first receiving unit configured to receive global map data including at least one key frame of an image collected by the first terminal, from the global map data The local map data associated with the key frame is extracted; the second receiving unit is used to receive the current frame in the image collected by the second terminal; the third matching unit is used to compare the current frame with the local map The data is feature-matched, and the positioning result of the current frame is obtained according to the matching result; the third positioning unit is configured to send the positioning result, so as to obtain according to the positioning result that the first terminal and the second terminal share the global The positional relationship between each other in the case of map data.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the embodiment of the present disclosure also proposes a computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing positioning method based on a shared map is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium.
  • the embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured as the above-mentioned positioning method based on a shared map.
  • the electronic device can be provided as a terminal, server or other form of device.
  • An embodiment of the present disclosure also provides a computer program, wherein the computer program includes computer-readable code, and when the computer-readable code runs in an electronic device, the processor in the electronic device executes the above Location method based on shared map.
  • Fig. 9 is a block diagram showing an electronic device 800 according to an exemplary embodiment.
  • the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.
  • the positioning unit is located at any terminal side.
  • the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.
  • the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components.
  • the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
  • the memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operated on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 804 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic Disk Magnetic Disk or Optical Disk.
  • the power supply component 806 provides power for various components of the electronic device 800.
  • the power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.
  • the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input audio signals.
  • the audio component 810 includes a microphone (MIC).
  • the microphone is configured to receive external audio signals.
  • the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
  • the audio component 810 further includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation.
  • the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components.
  • the component is the display and the keypad of the electronic device 800.
  • the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
  • the position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
  • the sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
  • the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the electronic device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • ASIC application specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field A programmable gate array
  • controller microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.
  • a non-volatile computer-readable storage medium such as a memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the foregoing method.
  • Fig. 10 is a block diagram showing an electronic device 900 according to an exemplary embodiment.
  • the electronic device 900 may be provided as a server.
  • the electronic device 900 includes a processing component 922, which further includes one or more processors, and a memory resource represented by a memory 932, for storing instructions that can be executed by the processing component 922, such as application programs.
  • the application program stored in the memory 932 may include one or more modules each corresponding to a set of instructions.
  • the processing component 922 is configured to execute instructions to perform the aforementioned methods. At this time, the positioning unit is located in the cloud.
  • the electronic device 900 may also include a power supply component 926 configured to perform power management of the electronic device 900, a wired or wireless network interface 950 configured to connect the electronic device 900 to a network, and an input output (I/O) interface 958 .
  • the electronic device 900 can operate based on an operating system stored in the memory 932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium such as the memory 932 including computer program instructions, which can be executed by the processing component 922 of the electronic device 900 to complete the foregoing method.
  • the present disclosure may be a system, method, and/or computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding device such as a printer with instructions stored thereon
  • the computer-readable storage medium used herein is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
  • the computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server carried out.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to access connection).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more functions for implementing the specified logical function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Navigation (AREA)
  • Image Analysis (AREA)

Abstract

本公开涉及一种基于共享地图的定位方法及装置、电子设备和存储介质，其中，所述方法包括：从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；获得第二终端所采集图像中的当前帧；将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。采用本公开，能准确地在共享地图中对处于运动的多个终端，实现彼此间精准的定位。

Description

一种基于共享地图的定位方法及装置、电子设备和存储介质
本公开要求在2019年06月27日提交中国专利局、申请号为201910569120.6、申请名称为“一种基于共享地图的定位方法及装置、电子设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及定位技术领域，尤其涉及一种基于共享地图的定位方法及装置、电子设备和存储介质。
背景技术
多个终端可以在各自的坐标体系中运动及进行自身定位。随着定位技术的发展，基于共享地图的定位技术有广阔的应用场景，比如，一个应用场景中，即时定位与地图构建(SLAM，simultaneous localization and mapping)，是机器人在未知环境中从一个未知位置开始移动，在移动过程中根据位置估计和地图进行自身定位，以实现机器人的自主定位和地图共享。
如果多个终端共享同一个地图，即多个终端在共享地图中运动及定位，如何实现多个终端间彼此精准的定位是要解决的技术问题。然而，相关技术中未存在有效的解决方案。
发明内容
本公开提出了一种基于共享地图的定位技术方案。
根据本公开的一方面，提供了一种基于共享地图的定位方法，所述方法包括：
从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
获得第二终端所采集图像中的当前帧；
将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
采用本公开，由于可以从包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。而与所述关键帧相关联的局部地图数据中，包含与当前帧最相似的多个关键帧构成的候选帧，从而与当前帧进行特征匹配的关键帧数据量变多了，因此，特征匹配的精确度随之提高，则根据该匹配结果得到当前帧的定位结果后，根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
可能的实现方式中，所述获得第二终端所采集图像中的当前帧之前，所述方法还包括：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
采用本公开，可以判断当前帧中提取特征点的数量是否符合用于特征匹配的期望阈值，符合就直 接使用当前帧中提取的特征点，不符合再触发对所述当前帧补充特征点的处理。
可能的实现方式中，所述第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
采用本公开，第二终端采集的当前帧，可以是直接使用当前帧中提取的特征点，也可以是执行对所述当前帧补充特征点的处理后得到的当前帧，从而根据实际需求来采用不同的特征点提取方式。
可能的实现方式中，执行对所述当前帧补充特征点的处理，包括：
获得用于对当前帧进行特征点提取的第一筛选阈值；
根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
采用本公开，触发对所述当前帧补充特征点的处理后，可以对筛选阈值进行自适应调整，并根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
可能的实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
采用本公开，任何外部信息或当前帧自身的信息都会影响到筛选阈值的自适应调整，将至少一种情况都考虑在内，则后续根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
可能的实现方式中，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：
将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
采用本公开，将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D到2D的特征匹配，也就是说，确定在二维空间中的位置。由于位姿包括朝向和位移，位移可以通过二维空间中的位置来描述，可确定朝向这种形态，还需要3D信息，因此，需要从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息，以便根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果，从而根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
根据本公开的一方面，提供了一种基于共享地图的定位方法，所述方法包括：
第一终端进行图像采集，得到包含至少一个关键帧的全局地图数据；
所述第一终端从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
所述第一终端接收第二终端采集的当前帧，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送所述定位结果。
采用本公开，通过第一终端采集得到包含至少一个关键帧的全局地图数据，在第一终端侧进行定位，具体是从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据，将从第二终端获得的当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送定位结果给第二终端。由于可以从包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
可能的实现方式中，所述第一终端从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据，包括：
以所述关键帧为参考中心，将根据所述关键帧和预设提取范围得到的地图数据作为所述局部地图数据。
采用本公开，以所述关键帧为参考中心所提取预定范围的数据，必然是与所述关键帧相关联的局部地图数据，将关键帧和其相关联局部地图数据共同作为与当前帧所匹配的信息，则提高了特征点匹配的数据量，从而可以得到更精确的匹配效果。
可能的实现方式中，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：
将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
采用本公开，将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D到2D的特征匹配，也就是说，确定在二维空间中的位置。由于位姿包括朝向和位移，位移可以通过二维空间中的位置来描述，可确定朝向这种形态，还需要3D信息，因此，需要从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息，以便根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果，从而根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
根据本公开的一方面，提供了一种基于共享地图的定位方法，所述方法包括：
第二终端进行图像采集，得到所采集图像中的当前帧，发送所述当前帧；
所述第二终端接收定位结果，所述定位结果为第一终端将所述当前帧与所述关键帧相关联的局部地图数据进行特征匹配，根据匹配结果得到的结果；
其中，全局地图数据为第一终端所采集图像中包含至少一个关键帧的地图数据且数据量大于所述局部地图数据。
采用本公开，在第一终端侧进行定位，据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。进一步的，在第二终端进行当前帧特征点的增补处理，通过对当前帧特征点的增补处理，提高进行特征匹配的特征点数据，特征匹配的精确度随之提高。
可能的实现方式中，所述第二终端进行图像采集，得到所采集图像中的当前帧之前，所述方法还包括：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
采用本公开，可以判断当前帧中提取特征点的数量是否符合用于特征匹配的期望阈值，符合就直接使用当前帧中提取的特征点，不符合再触发对所述当前帧补充特征点的处理。
可能的实现方式中，所述第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
采用本公开，第二终端采集的当前帧，可以是直接使用当前帧中提取的特征点，也可以是执行对所述当前帧补充特征点的处理后得到的当前帧，从而根据实际需求来采用不同的特征点提取方式。
可能的实现方式中，执行对所述当前帧补充特征点的处理，包括：
获得用于对当前帧进行特征点提取的第一筛选阈值；
根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
采用本公开，触发对所述当前帧补充特征点的处理后，可以对筛选阈值进行自适应调整，并根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
可能的实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
采用本公开，任何外部信息或当前帧自身的信息都会影响到筛选阈值的自适应调整，将至少一种情况都考虑在内，则后续根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
根据本公开的一方面，提供了一种基于共享地图的定位方法，所述方法包括：
第二终端接收包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；
所述第二终端进行图像采集，得到所采集图像中的当前帧；
所述第二终端将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
采用本公开，在第二终端侧进行定位，具体是从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据，将从第二终端获得的当前帧与所述局部地图数据进行特征匹配，根据匹配结果得 到当前帧的定位结果。由于可以从包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
可能的实现方式中，所述第二终端进行图像采集，得到所采集图像中的当前帧之前，所述方法还包括：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
采用本公开，可以判断当前帧中提取特征点的数量是否符合用于特征匹配的期望阈值，符合就直接使用当前帧中提取的特征点，不符合再触发对所述当前帧补充特征点的处理。
可能的实现方式中，所述当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
采用本公开，第二终端采集的当前帧，可以是直接使用当前帧中提取的特征点，也可以是执行对所述当前帧补充特征点的处理后得到的当前帧，从而根据实际需求来采用不同的特征点提取方式。
可能的实现方式中，执行对所述当前帧补充特征点的处理，包括：
获得用于对当前帧进行特征点提取的第一筛选阈值；
根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
采用本公开，触发对所述当前帧补充特征点的处理后，可以对筛选阈值进行自适应调整，并根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
可能的实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
采用本公开，任何外部信息或当前帧自身的信息都会影响到筛选阈值的自适应调整，将至少一种情况都考虑在内，则后续根据调整后的筛选阈值来增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。从而用更多的特征点进行特征匹配，匹配效果会更加精确。
可能的实现方式中，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：
将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
采用本公开，将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D到2D的特征匹配，也就是说，确定在二维空间中的位置。由于位姿包括朝向和位移，位移可以通过二维空间中的位置来描述，可确定朝向这种形态，还需要3D信息，因此，需要从所述2D特征匹配结果中，筛选出 含有3D信息的2D特征匹配结果并提取出所述3D信息，以便根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果，从而根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
根据本公开的一方面，提供了一种基于共享地图的定位方法，所述方法包括：
接收第一终端所采集图像的包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；
接收第二终端所采集图像中的当前帧；
将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果；
发送所述定位结果。
采用本公开，在云端进行定位，发送定位结果给第二终端。由于可以从包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。根据该定位结果对多个终端在共享地图中运动及定位，可以实现彼此间精准的定位。
根据本公开的一方面，提供了一种基于共享地图的定位装置，所述装置包括：
第一提取单元，用于从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
第一获得单元，用于获得第二终端所采集图像中的当前帧；
第一匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
可能的实现方式中，所述装置还包括：触发单元，用于：
判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
可能的实现方式中，所述装置还包括：特征点增补单元，用于：
获得用于对当前帧进行特征点提取的第一筛选阈值；
根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
根据本公开的一方面，提供了一种基于共享地图的定位装置，所述装置包括：
第一采集单元，用于进行图像采集，得到包含至少一个关键帧的全局地图数据；
第一提取单元，用于从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
第一匹配单元，用于接收第二终端采集的当前帧，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送所述定位结果。
可能的实现方式中，所述第一匹配单元，进一步用于：
将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征 匹配结果；
从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
根据本公开的一方面，提供了一种基于共享地图的定位装置，所述装置包括：
第二采集单元，用于进行图像采集，得到所采集图像中的当前帧，发送所述当前帧；
第二匹配单元，用于接收定位结果，所述定位结果为第一终端将所述当前帧与所述关键帧相关联的局部地图数据进行特征匹配，根据匹配结果得到的结果；
其中，全局地图数据为第一终端所采集图像中包含至少一个关键帧的地图数据且数据量大于所述局部地图数据。
可能的实现方式中，所述装置还包括：特征点增补单元，用于：
获得用于对当前帧进行特征点提取的第一筛选阈值；
根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
根据本公开的一方面，提供了一种基于共享地图的定位装置，所述装置包括：
第二提取单元，用于接收包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；
第二采集单元，用于进行图像采集，得到所采集图像中的当前帧；
第二匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
根据本公开的一方面，提供了一种基于共享地图的定位装置，所述装置包括：
第一接收单元，用于接收第一终端所采集图像的包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；
第二接收单元，用于接收第二终端所采集图像中的当前帧；
第三匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果；
第三定位单元，用于发送所述定位结果。
根据本公开的一方面，提供了一种电子设备，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：执行上述基于共享地图的定位方法。
根据本公开的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述基于共享地图的定位方法。
根据本公开的一方面，提供了一种计算机程序，其中，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述基于共享地图的定位方法。
在本公开实施例中，从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；获得第二终端所采集图像中的当前帧；将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。采用本公开，在当前帧与关键帧进行特征匹配的过程中，由于可以从包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。而与所述关键帧相关联的局部地图数据中，包含与当前帧最相似的多个关键帧构成的候选帧，从而与当前帧进行特征匹配的关键帧数据量变多了，因此，特征匹配的精确度随之提高，则根据该匹配结果得到当前帧的定位结果，可以对多个终端(第一终端和第二终端不限于一个终端，仅起指代作用)在共享地图中运动及定位，可以实现彼此间精准的定位。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的基于共享地图的定位方法的流程图。
图2示出根据本公开实施例的基于共享地图的定位方法的流程图。
图3示出根据本公开实施例的基于共享地图的定位方法的流程图。
图4示出根据本公开实施例的基于共享地图的定位方法的流程图。
图5示出根据本公开实施例的基于共享地图的定位方法的流程图。
图6示出根据本公开实施例的增补当前帧特征点过程的示意图。
图7示出根据本公开实施例的定位当前帧位姿过程的示意图。
图8示出根据本公开实施例的基于共享地图的定位装置的框图。
图9示出根据本公开实施例的电子设备的框图。
图10示出根据本公开实施例的电子设备的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好的说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
以即时定位与地图构建(SLAM，simultaneous localization and mapping)为例，SLAM问题可以描述为：机器人在未知环境中从一个未知位置开始移动，在移动过程中根据位置估计和地图进行自身定位，同时在自身定位的基础上建造增量式地图，实现机器人的自主定位和导航。当不同的机器人需要共享一个场景中彼此的位置时，则需要通过地图共享，通过定位技术确定彼此在共享地图中的位置，从而确定彼此在真实世界中的位置关系。在机器人、增强现实(AR，Augmented Reality)、虚拟现实(VR，Virtual Reality)中，基于共享地图的定位技术都有广阔的应用场景。
构建地图的方法不同，所得到的地图也具有不同的特性，相应的定位技术也有较大的变化。例如基于激光雷达的SLAM系统构建的地图是一个稠密的点云。其中，点云是在同一空间参考系下表达目标空间分布和目标表面特性的海量点集合。定位上主要基于两个点云的匹配，即两张点云数据图像的对应特征点的特征匹配。但是激光雷达的设备成本较高，并且基于点云对齐的定位技术，计算量会比较大。就硬件设备而言，相机的成本要比激光雷达低廉很多，采用相机并基于视觉的定位方法，可以是首先进行图像检索，找出最相似的关键帧，然后将当前帧与关键帧进行特征匹配，并根据匹配结果估算当前帧位姿。
然而，采用上述定位技术存在的问题是：其一、很多情况下由于计算性能或者SLAM框架的限制，每一帧图像上提取特征点的数量是有限定的，否则可能因为特征点提取耗时过久拖累SLAM算法性能，这就有可能导致在视角变化或者弱纹理场景下容易出现定位失败的情况。其二、在每帧图像携带特征点数量较少的情况下，基于两帧图像之间的匹配来进行定位很容易因为自身图像特征点过少而导致定位失败。采用本公开，可以采用如下任一方面的策略，或者是将两方面的策略结合使用，宗旨是提高用于特征匹配的数据量，从而提升弱纹理情况下的定位能力，及充分利用地图信息，提高定位成功率。
策略一：第一终端、第二终端和云端所构成的定位框架中，可以在用于定位的定位单元(定位单元可以在第一终端侧，第二终端侧或者云端)中，在第一终端发送的包括至少一个关键帧的共享地图中检索出与第二终端所发送的当前帧最相似的至少一个关键帧图像后，得到与至少一个关键帧相关联的局部点云信息来进行特征匹配，而不是采用全部的点云信息来进行特征匹配，从而可以充分利用共 享地图的视觉信息，也就是说，区别于当前帧与关键帧的特征匹配，是将当前帧与该关键帧相关联的局部点云信息进行特征匹配。显然用于特征匹配的数据量增多了，随之，定位成功率也就提高了。
策略二：使用当前帧在共享地图上进行定位时，根据环境自适应的增补特征点，使当前帧上提取到的特征点数量始终处于一个较高数量，比如，当前帧上提取到的特征点数量大于采用SLAM系统自身跟踪时得到当前帧的实际特征点数量。显然用于特征匹配的数据量增多了，随之，定位成功率也就提高了。
图1示出根据本公开实施例的基于共享地图的定位方法的流程图，该基于共享地图的定位方法应用于基于共享地图的定位装置，例如，基于共享地图的定位装置可以由终端设备或服务器或其它处理设备执行，其中，终端设备可以为用户设备(UE，User Equipment)、移动设备、蜂窝电话、无绳电话、个人数字处理(PDA，Personal Digital Assistant)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该基于共享地图的定位方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。如图1所示，该流程包括：
步骤S101、从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。
一示例中，该与所述关键帧相关联的局部地图数据，可以为与关键帧关联的局部点云数据，所述局部点云数据可以选取所述关键帧为中心。关键帧指：与当前帧最相似的候选帧。
步骤S102、获得第二终端所采集图像中的当前帧。
如果当前帧中特征点的数量大于等于用于特征匹配的期望阈值，则直接将当前帧与局部地图数据进行特征匹配。如果当前帧中特征点的数量小于该期望阈值的情况下触发对当前帧补充特征点的处理。
步骤S103、将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
步骤S103后，还可以包括：根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
采用本公开，区别于将当前帧与关键帧进行特征匹配来实现定位，是用更多的特征点进行特征匹配，如，将当前帧与以关键帧为中心所形成的局部点云数据进行特征匹配。采用局部点云数据，是用更多的特征点，或者说是用局部地图来补充当前帧与关键帧二者的匹配关系，从而达到更精确的处理效果，实现精准的定位。
图2示出根据本公开实施例的基于共享地图的定位方法的流程图，该基于共享地图的定位方法应用于基于共享地图的定位装置，例如，基于共享地图的定位装置可以由终端设备或服务器或其它处理设备执行，其中，终端设备可以为用户设备(UE，User Equipment)、移动设备、蜂窝电话、无绳电话、个人数字处理(PDA，Personal Digital Assistant)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该基于共享地图的定位方法可以通过处理器调用存储器中存储的计算 机可读指令的方式来实现。如图2所示，该流程包括：
步骤S201、从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据。
一示例中，该与所述关键帧相关联的局部地图数据，可以为与关键帧关联的局部点云数据，所述局部点云数据可以选取所述关键帧为中心。关键帧指：与当前帧最相似的候选帧。
步骤S202、判断从当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，如果小于所述期望阈值，则执行步骤S203；否则，执行步骤S204。
在采集的图像为弱纹理情况，或者每帧图像携带特征点数量较少的情况下，会导致达不到上述期望阈值。
步骤S203、触发对所述当前帧补充特征点的处理，执行对当前帧补充特征点的处理。
一示例中，执行对当前帧补充特征点的处理，可以采用增补当前帧特征点的特征点增补单元，特征点增补单元位于用于采集当前帧的第二终端侧。
步骤S204、获得第二终端所采集图像中的当前帧。
如果当前帧中特征点的数量大于等于用于特征匹配的期望阈值，则当前帧为通过采集图像得到的当前帧；如果当前帧中特征点的数量小于该期望阈值，则当前帧为执行对所述当前帧补充特征点的处理后得到的当前帧。
步骤S205、将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
步骤S206、根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
采用本公开，区别于当前帧与关键帧比对来实现对位，可以对当前帧进行特征点的补充，即用更多的特征点比对从而达到更精确的处理效果，实现精准的定位。相关技术中，当前帧中特征点数据量与采用SLAM系统自身跟踪时实际得到的特征点数量一致，在弱纹理情况下能提取到的特征点数可能会急剧下降，本公开中，在提取当前帧特征点的时候提取的点的数量会多于SLAM自身跟踪时实际得到的特征点数量(可以是LAM自身跟踪时实际得到的特征点数量两倍或两倍以上)，并且在弱纹理情况下会补充提点，从而增加了当前帧的特征点提取数量，提高了定位成功率。且通过自适应的修改提点的阈值，增强在弱纹理场景下的特征点提取能力。
一个示例中，以两个终端(手机)基于共享地图定位为例，两个用户分别手持一个手机，对着同一张桌子共同进行AR游戏。其中，两个手机能够对同一个AR效果进行观察以及互动，这就需要两个终端处在一个坐标系下，彼此知道对方的位姿，而共享彼此的位姿就需要基于共享地图实现彼此的定位。具体的，通过第一终端(手机1)进行图像采集，得到包含至少一个关键帧的全局地图数据。从全局地图数据中提取出与关键帧相关联的局部地图数据(如局部点云数据)，该局部点云数据可以选 取该关键帧(与当前帧最相似的候选帧)为中心。通过第二终端(手机2)采集图像，得到当前帧，如果当前帧中特征点的数量大于等于用于特征匹配的期望阈值，则直接将当前帧与局部地图数据进行特征匹配；如果当前帧中特征点的数量小于该期望阈值的情况下触发对当前帧补充特征点的处理，也就是说，可以对当前帧进行补充提点(或称增补特征点)。进一步还可以自适应调整提点的阈值以获得更多的特征点。将当前帧(或者增补特征点后得到的当前帧)与局部点云数据进行特征匹配，使用局部地图来补充当前帧与关键帧的匹配关系以达到提高定位成功率。根据匹配结果得到当前帧的定位结果，根据定位结果得到第一终端(手机1)和第二终端(手机2)共享全局地图数据情况下彼此的位置关系。其中，共享的含义是指：第一终端(手机1)和第二终端(手机2)位于该地图所在的同一坐标系下，可以在该同一坐标系下定位彼此的位置或者位姿等信息。
本公开一可能实现方式中，执行对当前帧补充特征点的处理，包括：获得用于对当前帧进行特征点提取的第一筛选阈值，根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。其中，参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。具体来说，1)该环境信息是外部可能导致提取特征点数量不足的影响因素之一：如光照情况，周边遮挡等至少一种信息，不限于会导致特征点数量较少或降低的至少一种情况下的影响信息。2)该图像采集设备中参数信息可以是传感器参数信息，是外部可能导致提取特征点数量不足的影响因素之二，如相机的传感器采集的灵敏度、清晰度、曝光、对比度等等。3)该当前帧本身的图像信息，是其自身可能导致提取特征点数量不足的影响因素之一，比如有的图像本身纹理少，图像简单，相应的，可供提取的特征点本身可能就不多。
本公开一可能实现方式中，将当前帧与局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：将当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果。从2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出3D信息。根据3D信息得到当前帧的位姿，将当前帧的位姿作为所述定位结果。具体来说，进行特征点2D到2D的特征匹配后，可以筛选得到含有3D信息的2D特征匹配结果(简称筛选结果)，根据该筛选结果可以求得当前帧的位姿。
图3示出根据本公开实施例的基于共享地图的定位方法的流程图，该基于共享地图的定位方法应用于基于共享地图的定位装置，例如，基于共享地图的定位装置可以由终端设备或服务器或其它处理设备执行，其中，终端设备可以为用户设备(UE，User Equipment)、移动设备、蜂窝电话、无绳电话、个人数字处理(PDA，Personal Digital Assistant)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该基于共享地图的定位方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。其中，定位单元可以位于第一终端侧，如图3所示，该流程包括：
步骤S301、第一终端进行图像采集，得到包含至少一个关键帧的全局地图数据。
步骤S302、第二终端进行图像采集，得到所采集图像中的当前帧，发送当前帧给第二终端。
步骤S303、第一终端从全局地图数据中，提取出与关键帧相关联的局部地图数据。
一示例中，全局地图数据为第一终端所采集图像中包含至少一个关键帧的地图数据且数据量大于局部地图数据。
步骤S304、第一终端接收第二终端采集的当前帧，将当前帧与局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送定位结果给第二终端。
步骤S305、第二终端根据定位结果得到第一终端和第二终端共享全局地图数据情况下彼此的位置关系。
本公开一可能实现方式中，第一终端从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据，包括：以所述关键帧为参考中心，将根据所述关键帧和预设提取范围得到的地图数据作为所述局部地图数据。
本公开一可能实现方式中，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。具体来说，进行特征点2D到2D的特征匹配后，可以筛选得到含有3D信息的2D特征匹配结果(简称筛选结果)，根据该筛选结果可以求得当前帧的位姿。
本公开一可能实现方式中，所述方法还包括：所述第二终端进行图像采集，得到所采集图像中的当前帧之前，判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。其中，第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。一示例中，获得用于对当前帧进行特征点提取的第一筛选阈值；根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，当特征点数量大于实际采集所获取的特征点数量时，可以结束对当前帧补充特征点的处理。
本公开一可能实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
图4示出根据本公开实施例的基于共享地图的定位方法的流程图，该基于共享地图的定位方法应用于基于共享地图的定位装置，例如，基于共享地图的定位装置可以由终端设备或服务器或其它处理设备执行，其中，终端设备可以为用户设备(UE，User Equipment)、移动设备、蜂窝电话、无绳电话、个人数字处理(PDA，Personal Digital Assistant)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该基于共享地图的定位方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。其中，定位单元可以位于第二终端侧，如图4所示，该流程包括：
步骤S401、第二终端接收包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据。
步骤S402、第二终端进行图像采集，得到所采集图像中的当前帧。
步骤S403、第二终端将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
步骤S404、所述第二终端根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
本公开一可能实现方式中，所述方法还包括：所述第二终端进行图像采集，得到所采集图像中的当前帧之前，判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。其中，所述当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
本公开一可能实现方式中，执行对所述当前帧补充特征点的处理，包括：获得用于对当前帧进行特征点提取的第一筛选阈值；根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。其中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
本公开一可能实现方式中，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。具体来说，进行特征点2D到2D的特征匹配后，可以筛选得到含有3D信息的2D特征匹配结果(简称筛选结果)，根据该筛选结果可以求得当前帧的位姿。
根据本公开实施例的基于共享地图的定位方法，可以应用于基于共享地图的定位装置，例如，基于共享地图的定位装置可以由终端设备或服务器或其它处理设备执行，其中，终端设备可以为用户设备(UE，User Equipment)、移动设备、蜂窝电话、无绳电话、个人数字处理(PDA，Personal Digital Assistant)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该基于共享地图的定位方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。其中，定位单元可以位于云端，该流程包括：接收第一终端所采集图像的包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据。接收第二终端所采集图像中的当前帧。将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。发送所述定位结果，以根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
应用示例：
图5示出根据本公开实施例的基于共享地图的定位方法，以两个终端设备(设备一和设备二)为例，不限于所示例的两个终端设备，在多个终端设备间也可以通过共享地图来进行定位。如图5所示，定位过程包括：通过设备一通过扫描场景，生成至少包含一个关键帧构成的地图，将这个地图定义为共享地图，这个共享地图可以保存于设备一本地或者上传到其他终端设备(如设备二)上，还可以将该共享地图存放于云端。对共享地图有需求的一个或多个设备(图中简略的标记为设备二)可以将本设备采集到的当前帧数据给到定位单元。定位单元可以运行在任意一个设备或位于云端上，除了设备二传送过来的当前帧数据，定位单元还可以获取到共享地图数据。定位单元根据当前帧图像以及共享地图数据，可以得到当前帧的定位结果，并将定位结果传送回设备二，通过这种方式，设备二可以得到自己相对于共享地图的坐标系的相对位姿。
图6示出根据本公开实施例的增补当前帧特征点过程的示意图。设备二可以根据特征点增补单元，对当前帧图像进行自适应调整以增补生成更多特征点。如图6所示，增补当前帧特征点过程包括如下内容：
输入：当前帧图像；
输出：特征点及描述子(或称为特征描述子)，特征描述子(Descriptor)是刻画特征的一个数据结构，一个描述子的维数可以是多维的；
1、以默认参数对设备二获取到的当前帧图像进行特征点提取，提取的特征点数量，可以是SLAM系统自身实际获取到特征点数量的两倍。
2、检查步骤1中提取出来的特征点数量，如果特征点数量少于特定的期望阈值，则跳转至步骤3，否则跳转至步骤4。
3、降低特征点的筛选阈值，补充提点(或称增补当前帧中的特征点数量)。
4、对提取到的特征点进行特征描述子的提取，返回提取结果。
图7示出根据本公开实施例的定位当前帧位姿过程的示意图，可以通过定位单元实现定位过程。如图7所示，定位过程包括如下内容：
输入：当前帧数据，共享地图；
输出：定位结果；
1、使用当前帧特征信息在共享地图上进行图像检索，找到与当前帧图像最相似的关键帧，称之为候选帧。
2、当前帧与候选帧进行特征匹配，候选帧上的特征点带有3D信息，因此可以得到一系列2D到3D的匹配结果。
3、根据步骤2得到的2D特征点与3D点的匹配结果，可以优化求解出当前帧的位姿。
4、判断步骤3得到的位姿是否有足够多的内点，如果内点数量小于一定阈值，则继续步骤5，否 则跳转至步骤7。
将当前帧与局部点云数据中的至少一个关键帧进行特征点2D到2D的特征匹配后，可以筛选得到含有3D信息的2D特征匹配结果(简称筛选结果)，根据该筛选结果可以求得当前帧的位姿。需要指出的是，该筛选结果并不都是质量好的特征点，质量的好坏以用于特征匹配为依据，根据质量的好坏可以将特征点分为内点和外点。其中，内点是指：质量的好的特征点；而外点是指：质量不够好的特征点。
需要指出的是，上述特征匹配会涉及到多视图几何(Multiple View Geometry)的概念，多视图几何，是指：用几何的方法，通过若干幅二维图像，来恢复三维物体，简言之就是研究三维重构，主要应用与计算机视觉中。通过多视图几何技术，不仅使计算机能感知三维环境中的几何信息，包括它的形状、位置、姿态、运动等，而且能对它们进行描述、存储、识别与理解。在计算机视觉中，需要找出两帧图像的特征匹配点，比如，在两帧图像中的一帧图像，根据图像质量和纹理信息可以提取出1000个特征点(二维的)；在两帧图像中的另一帧图像，也可以根据图像质量和纹理信息提取出1000个特征点(二维的)，需要找到这两幅图像如何相关，需要进行特征点匹配，比如，两帧图像进行特征点匹配得到600个特征点是相关的，因为，特征点的最大特点就是它具有唯一可识别图像信息的能力。由于物体是运动的，会产生位移，那么这两帧图像中的特征点所描述的信息(如2D特征点所包含的3D信息)可能不同，或者说利用多视图几何概念进行多视角观测，换个视角看，角度不同，特征点所描述的信息(如2D特征点所包含的3D信息)可能不同，甚至可能出现对图像遮挡或失真等极端情况，导致，并不是所有2D特征点都包含3D信息，或者说包含可应用的3D信息，比如这600个特征点中只有300个2D特征点包含3D信息，因此，需要筛选得到含有3D信息的2D特征匹配结果(简称筛选结果)后再根据该筛选结果求得当前帧的位姿，这样才会更准确。
5、以步骤1得到的候选帧为基础，选出与该候选帧有共视关系的至少一帧并作为关键帧，将这些关键帧包含的点云集合作为局部地图数据(或称局部点云数据)，使用步骤3得到位姿作为初始位姿，进行补充匹配。
6、根据步骤5得到的匹配结果，优化求解出当前帧的位姿，返回定位结果。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。
此外，本公开还提供了基于共享地图的定位装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种基于共享地图的定位方法，相应技术方案和描述和参见方法部分的相应记载，不再赘述。
图8示出根据本公开实施例的基于共享地图的定位装置的框图，如图8所示，本公开实施例的基于 共享地图的定位装置，包括：第一提取单元31，用于从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；第一获得单元32，用于获得第二终端所采集图像中的当前帧；第一匹配单元33，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。该装置还包括：第一定位单元，用于根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
本公开可能的实现方式中，所述装置还包括：触发单元，用于：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
本公开可能的实现方式中，所述第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
本公开可能的实现方式中，所述装置还包括：特征点增补单元，用于：获得用于对当前帧进行特征点提取的第一筛选阈值；根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
本公开可能的实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
本公开可能的实现方式中，所述第一匹配单元，进一步用于：将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
根据本公开实施例的基于共享地图的定位装置，所述装置包括：第一采集单元，用于进行图像采集，得到包含至少一个关键帧的全局地图数据；第一提取单元，用于从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据；第一匹配单元，用于接收第二终端采集的当前帧，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送所述定位结果。
本公开可能的实现方式中，所述第一提取单元，进一步用于：以所述关键帧为参考中心，将根据所述关键帧和预设提取范围得到的地图数据作为所述局部地图数据。
本公开可能的实现方式中，所述第一匹配单元，进一步用于：将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
根据本公开实施例的基于共享地图的定位装置，所述装置包括：第二采集单元，用于进行图像采集，得到所采集图像中的当前帧，发送所述当前帧；第二匹配单元，用于接收定位结果，所述定位结果为第一终端将所述当前帧与所述关键帧相关联的局部地图数据进行特征匹配，根据匹配结果得到的 结果；第二定位单元，用于根据所述定位结果得到所述第一终端和所述第二终端共享全局地图数据情况下彼此的位置关系；其中，全局地图数据为第一终端所采集图像中包含至少一个关键帧的地图数据且数据量大于所述局部地图数据。
本公开可能的实现方式中，所述装置还包括：触发单元，用于：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
本公开可能的实现方式中，所述第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
本公开可能的实现方式中，所述装置还包括：特征点增补单元，用于：获得用于对当前帧进行特征点提取的第一筛选阈值；根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
本公开可能的实现方式中，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
根据本公开实施例的基于共享地图的定位装置，所述装置包括：第二提取单元，用于接收包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；第二采集单元，用于进行图像采集，得到所采集图像中的当前帧；第二匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果；第二定位单元，用于根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
根据本公开实施例的所述装置还包括：触发单元，用于：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
根据本公开实施例的所述当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
根据本公开实施例的所述装置还包括：特征点增补单元，用于：获得用于对当前帧进行特征点提取的第一筛选阈值；根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
根据本公开实施例的所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
根据本公开实施例的所述第二定位单元，进一步用于：将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
根据本公开实施例的基于共享地图的定位装置，所述装置包括：第一接收单元，用于接收第一终 端所采集图像的包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；第二接收单元，用于接收第二终端所采集图像中的当前帧；第三匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果；第三定位单元，用于发送所述定位结果，以根据所述定位结果得到所述第一终端和所述第二终端共享所述全局地图数据情况下彼此的位置关系。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述基于共享地图的定位方法。计算机可读存储介质可以是非易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为上述基于共享地图的定位方法。
电子设备可以被提供为终端、服务器或其它形态的设备。
本公开实施例还提出一种计算机程序，其中，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述基于共享地图的定位方法。
图9是根据一示例性实施例示出的一种电子设备800的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。此时，定位单元位于任一终端侧。
参照图9，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存 储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图10是根据一示例性实施例示出的一种电子设备900的框图。例如，电子设备900可以被提供为一服务器。参照图10，电子设备900包括处理组件922，其进一步包括一个或多个处理器，以及由存储器932所代表的存储器资源，用于存储可由处理组件922的执行的指令，例如应用程序。存储器932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件922被配置为执行指令，以执行上述方法。此时，定位单元位于云端。
电子设备900还可以包括一个电源组件926被配置为执行电子设备900的电源管理，一个有线或无线网络接口950被配置为将电子设备900连接到网络，和一个输入输出(I/O)接口958。电子设备900可以操作基于存储在存储器932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器932，上述计算机程序指令可由电子设备900的处理组件922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执 行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中技术的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (23)

  1. 一种基于共享地图的定位方法，其特征在于，所述方法包括：
    从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
    获得第二终端所采集图像中的当前帧；
    将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
  2. 根据权利要求1所述的方法，其特征在于，所述获得第二终端所采集图像中的当前帧之前，所述方法还包括：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
  3. 根据权利要求2所述的方法，其特征在于，所述第二终端采集的当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
  4. 根据权利要求2或3所述的方法，其特征在于，执行对所述当前帧补充特征点的处理，包括：
    获得用于对当前帧进行特征点提取的第一筛选阈值；
    根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
  5. 根据权利要求4所述的方法，其特征在于，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：
    将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
    从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
    根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
  7. 一种基于共享地图的定位方法，其特征在于，所述方法包括：
    第一终端进行图像采集，得到包含至少一个关键帧的全局地图数据；
    所述第一终端从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
    所述第一终端接收第二终端采集的当前帧，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送所述定位结果。
  8. 根据权利要求7所述的方法，其特征在于，所述第一终端从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据，包括：
    以所述关键帧为参考中心，将根据所述关键帧和预设提取范围得到的地图数据作为所述局部地图数据。
  9. 根据权利要求7或8所述的方法，其特征在于，所述将所述当前帧与所述局部地图数据进行特 征匹配，根据匹配结果得到当前帧的定位结果，包括：
    将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
    从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
    根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
  10. 一种基于共享地图的定位方法，其特征在于，所述方法包括：
    第二终端接收包含至少一个关键帧的全局地图数据，从所述全局地图数据中提取出与所述关键帧相关联的局部地图数据；
    所述第二终端进行图像采集，得到所采集图像中的当前帧；
    所述第二终端将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
  11. 根据权利要求10所述的方法，其特征在于，所述第二终端进行图像采集，得到所采集图像中的当前帧之前，所述方法还包括：判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
  12. 根据权利要求11所述的方法，其特征在于，所述当前帧，包括执行对所述当前帧补充特征点的处理后得到的当前帧。
  13. 根据权利要求11或12所述的方法，其特征在于，执行对所述当前帧补充特征点的处理，包括：
    获得用于对当前帧进行特征点提取的第一筛选阈值；
    根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
  14. 根据权利要求13所述的方法，其特征在于，所述参考信息包括：进行图像采集的环境信息、图像采集设备中参数信息、当前帧自身图像信息中的至少一种信息。
  15. 根据权利要求10-14任一项所述的方法，其特征在于，所述将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，包括：
    将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
    从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
    根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
  16. 一种基于共享地图的定位装置，其特征在于，所述装置包括：
    第一提取单元，用于从第一终端所采集图像的包含至少一个关键帧的全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
    第一获得单元，用于获得第二终端所采集图像中的当前帧；
    第一匹配单元，用于将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果。
  17. 根据权利要求16所述的装置，其特征在于，所述装置还包括：触发单元，用于：
    判断从所述当前帧中提取特征点的数量是否小于用于特征匹配的期望阈值，在小于所述期望阈值的情况下触发对所述当前帧补充特征点的处理。
  18. 根据权利要求16或17所述的装置，其特征在于，所述装置还包括：特征点增补单元，用于：
    获得用于对当前帧进行特征点提取的第一筛选阈值；
    根据参考信息对所述第一筛选阈值进行自适应调整，得到第二筛选阈值，根据所述第二筛选阈值增补特征点到所述当前帧中，使特征点数量大于实际采集所获取的特征点数量。
  19. 一种基于共享地图的定位装置，其特征在于，所述装置包括：
    第一采集单元，用于进行图像采集，得到包含至少一个关键帧的全局地图数据；
    第一提取单元，用于从所述全局地图数据中，提取出与所述关键帧相关联的局部地图数据；
    第一匹配单元，用于接收第二终端采集的当前帧，将所述当前帧与所述局部地图数据进行特征匹配，根据匹配结果得到当前帧的定位结果，发送所述定位结果。
  20. 根据权利要求19所述的装置，其特征在于，所述第一匹配单元，进一步用于：
    将所述当前帧与所述局部地图数据中的至少一个关键帧进行特征点2D的特征匹配，得到2D特征匹配结果；
    从所述2D特征匹配结果中，筛选出含有3D信息的2D特征匹配结果并提取出所述3D信息；
    根据所述3D信息得到所述当前帧的位姿，将所述当前帧的位姿作为所述定位结果。
  21. 一种电子设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1至6、权利要求7至9、权利要求10至15中任意一项所述的方法。
  22. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至6、权利要求7至9、权利要求10至15中任意一项所述的方法。
  23. 一种计算机程序，其中，所述计算机程序包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1至6、权利要求7至9、权利要求10至15中任意一项所述的方法。
PCT/CN2020/080465 2019-06-27 2020-03-20 一种基于共享地图的定位方法及装置、电子设备和存储介质 WO2020258936A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
SG11202108199YA SG11202108199YA (en) 2019-06-27 2020-03-20 Locating method and device employing shared map, electronic apparatus, and storage medium
JP2021543389A JP7261889B2 (ja) 2019-06-27 2020-03-20 共有地図に基づいた測位方法及び装置、電子機器並びに記憶媒体
US17/383,663 US20210350170A1 (en) 2019-06-27 2021-07-23 Localization method and apparatus based on shared map, electronic device and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910569120.6 2019-06-27
CN201910569120.6A CN112148815B (zh) 2019-06-27 2019-06-27 一种基于共享地图的定位方法及装置、电子设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/383,663 Continuation US20210350170A1 (en) 2019-06-27 2021-07-23 Localization method and apparatus based on shared map, electronic device and storage medium

Publications (1)

Publication Number Publication Date
WO2020258936A1 true WO2020258936A1 (zh) 2020-12-30

Family

ID=73868781

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/080465 WO2020258936A1 (zh) 2019-06-27 2020-03-20 一种基于共享地图的定位方法及装置、电子设备和存储介质

Country Status (6)

Country Link
US (1) US20210350170A1 (zh)
JP (1) JP7261889B2 (zh)
CN (1) CN112148815B (zh)
SG (1) SG11202108199YA (zh)
TW (1) TWI748439B (zh)
WO (1) WO2020258936A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115727857A (zh) * 2021-08-31 2023-03-03 阿里巴巴达摩院(杭州)科技有限公司 定位方法、定位装置、车辆、存储介质和程序产品
CN113763475A (zh) * 2021-09-24 2021-12-07 北京百度网讯科技有限公司 定位方法、装置、设备、系统、介质和自动驾驶车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392964A (zh) * 2017-07-07 2017-11-24 武汉大学 基于室内特征点和结构线结合的室内slam方法
WO2018063608A1 (en) * 2016-09-29 2018-04-05 Intel Corporation Place recognition algorithm
CN108921893A (zh) * 2018-04-24 2018-11-30 华南理工大学 一种基于在线深度学习slam的图像云计算方法及系统
WO2019045711A1 (en) * 2017-08-31 2019-03-07 Sony Mobile Communications Inc. SIMULTANEOUS LOCALIZING AND MAPPING DEVICES (SLAM) WITH SCALE DETERMINATION AND METHODS OF OPERATION THEREOF
CN109509230A (zh) * 2018-11-13 2019-03-22 武汉大学 一种应用于多镜头组合式全景相机的slam方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104748736A (zh) * 2013-12-26 2015-07-01 电信科学技术研究院 一种定位方法及装置
US10068373B2 (en) * 2014-07-01 2018-09-04 Samsung Electronics Co., Ltd. Electronic device for providing map information
KR102332752B1 (ko) * 2014-11-24 2021-11-30 삼성전자주식회사 지도 서비스를 제공하는 전자 장치 및 방법
TWI657230B (zh) * 2017-09-18 2019-04-21 財團法人工業技術研究院 導航定位裝置及應用其之導航定位方法
CN107832331A (zh) * 2017-09-28 2018-03-23 阿里巴巴集团控股有限公司 可视化对象的生成方法、装置和设备
EP3474230B1 (en) * 2017-10-18 2020-07-22 Tata Consultancy Services Limited Systems and methods for edge points based monocular visual slam
CN107990899B (zh) * 2017-11-22 2020-06-30 驭势科技（北京）有限公司 一种基于slam的定位方法和系统
CN107818592B (zh) * 2017-11-24 2022-04-01 北京华捷艾米科技有限公司 协作式同步定位与地图构建的方法、系统及交互系统
TWI648556B (zh) * 2018-03-06 2019-01-21 仁寶電腦工業股份有限公司 同步定位與地圖建構及手勢辨識方法
CN109559277B (zh) * 2018-11-28 2023-02-28 中国人民解放军国防科技大学 一种面向数据共享的多无人机协同地图构建方法
CN109615698A (zh) 2018-12-03 2019-04-12 哈尔滨工业大学（深圳） 基于互回环检测的多无人机slam地图融合算法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018063608A1 (en) * 2016-09-29 2018-04-05 Intel Corporation Place recognition algorithm
CN107392964A (zh) * 2017-07-07 2017-11-24 武汉大学 基于室内特征点和结构线结合的室内slam方法
WO2019045711A1 (en) * 2017-08-31 2019-03-07 Sony Mobile Communications Inc. SIMULTANEOUS LOCALIZING AND MAPPING DEVICES (SLAM) WITH SCALE DETERMINATION AND METHODS OF OPERATION THEREOF
CN108921893A (zh) * 2018-04-24 2018-11-30 华南理工大学 一种基于在线深度学习slam的图像云计算方法及系统
CN109509230A (zh) * 2018-11-13 2019-03-22 武汉大学 一种应用于多镜头组合式全景相机的slam方法

Also Published As

Publication number Publication date
US20210350170A1 (en) 2021-11-11
TW202100955A (zh) 2021-01-01
CN112148815A (zh) 2020-12-29
SG11202108199YA (en) 2021-08-30
CN112148815B (zh) 2022-09-27
JP2022518810A (ja) 2022-03-16
JP7261889B2 (ja) 2023-04-20
TWI748439B (zh) 2021-12-01

Similar Documents

Publication Publication Date Title
WO2021164469A1 (zh) 目标对象的检测方法、装置、设备和存储介质
CN106651955B (zh) 图片中目标物的定位方法及装置
CN106778773B (zh) 图片中目标物的定位方法及装置
CN111105454B (zh) 一种获取定位信息的方法、装置及介质
JP6348611B2 (ja) 自動ピント合わせ方法、装置、プログラム及び記録媒体
CN110503689B (zh) 位姿预测方法、模型训练方法及装置
CN112001321A (zh) 网络训练、行人重识别方法及装置、电子设备和存储介质
CN109584362B (zh) 三维模型构建方法及装置、电子设备和存储介质
CN113205549B (zh) 深度估计方法及装置、电子设备和存储介质
WO2020258937A1 (zh) 一种坐标系对齐的方法及装置、电子设备和存储介质
CN111563138B (zh) 定位方法及装置、电子设备和存储介质
CN114088061B (zh) 目标定位方法及装置、电子设备和存储介质
KR102367648B1 (ko) 전 방향 시차 영상 합성 방법, 장치 및 저장 매체
TWI748439B (zh) 一種基於共享地圖的定位方法及裝置、電子設備和電腦可讀儲存媒體
CN111325786B (zh) 图像处理方法及装置、电子设备和存储介质
CN112700468A (zh) 位姿确定方法及装置、电子设备和存储介质
CN112330721B (zh) 三维坐标的恢复方法及装置、电子设备和存储介质
CN112767541A (zh) 三维重建方法及装置、电子设备和存储介质
EP3599763A2 (en) Method and apparatus for controlling image display
WO2021136979A1 (en) Image processing method and apparatus, electronic device, and storage medium
CN113808216B (zh) 相机标定方法及装置、电子设备和存储介质
CN112837361B (zh) 一种深度估计方法及装置、电子设备和存储介质
CN118941623A (zh) 视觉重定位方法、装置、设备及存储介质
KR102179432B1 (ko) 3차원 정보를 검출하는 방법 및 장치
CN116664887A (zh) 定位精度确定方法、装置、电子设备及可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20830878

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021543389

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20830878

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20830878

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 230622)

122 Ep: pct application non-entry in european phase

Ref document number: 20830878

Country of ref document: EP

Kind code of ref document: A1