CN112597822B - Vehicle track determination method and device, electronic equipment and computer storage medium - Google Patents
Vehicle track determination method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN112597822B CN112597822B CN202011438299.0A CN202011438299A CN112597822B CN 112597822 B CN112597822 B CN 112597822B CN 202011438299 A CN202011438299 A CN 202011438299A CN 112597822 B CN112597822 B CN 112597822B
- Authority
- CN
- China
- Prior art keywords
- track
- vehicle
- target
- road
- historical traffic
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a track determining method and device of a vehicle, electronic equipment and a computer storage medium. The track determining method of the vehicle comprises the following steps: acquiring position features and motion features of a target vehicle; matching a target road mode from each preset road mode based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data; calculating a region constraint point based on the track tail end of the target road mode; generating a candidate track set based on the region constraint points; and determining the target track from the candidate track set according to the motion model of the target vehicle. According to the embodiment of the application, the track of the vehicle can be more accurately determined.
Description
Technical Field
The application belongs to the technical field of intelligent transportation, and particularly relates to a track determining method and device for a vehicle, electronic equipment and a computer storage medium.
Background
At present, single car intelligence has realized most traffic scenes, but has the self-limitation of limited perception range of surrounding environment. Most algorithms for predicting the track in the automatic driving field are based on real-time acquisition of state information of a vehicle end by a vehicle end sensor and prediction of the future vehicle running track. The implementation of the algorithm mostly depends on real-time vehicle-end state data of a vehicle-end sensor, and the global perception range of an automatic driving vehicle on a road is limited, so that perception errors on the surrounding environment due to shielding and the like are more likely to occur.
Therefore, how to determine the trajectory of the vehicle more accurately is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the application provides a track determining method and device for a vehicle, electronic equipment and a computer storage medium, which can determine the track of the vehicle more accurately.
In a first aspect, an embodiment of the present application provides a method for determining a track of a vehicle, including:
acquiring position features and motion features of a target vehicle;
matching a target road mode from each preset road mode based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data;
calculating a region constraint point based on the track tail end of the target road mode;
generating a candidate track set based on the region constraint points;
and determining the target track from the candidate track set according to the motion model of the target vehicle.
Optionally, before matching the target road mode from the preset road modes based on the position feature and the motion feature, the method further includes:
acquiring historical video stream data in the perception range of each road side camera;
based on the historical video stream data, utilizing a detection tracking algorithm to obtain historical vehicle stream data;
preprocessing the historical traffic data to obtain preprocessed historical traffic data;
clustering is carried out by utilizing the preprocessed historical traffic flow data, and each road mode is obtained.
Optionally, preprocessing the historical traffic data to obtain preprocessed historical traffic data, including:
and performing invalid short track filtration and track point time normalization on the historical traffic data to obtain preprocessed historical traffic data.
Optionally, clustering is performed by using the preprocessed historical traffic data to obtain each road mode, including:
calculating a track similarity matrix based on the preprocessed historical traffic data;
calculating a local density value and a cluster distance of each track according to the track similarity matrix;
and dividing the road modes based on the local density value of each track and the inter-cluster distance to obtain each road mode.
Optionally, dividing based on the local density value and the inter-cluster distance of each track to obtain each road mode, including:
obtaining a track weight dictionary according to the product value of the local density value and the inter-cluster distance;
and dividing according to the track weight dictionary and the acquired road environment information to obtain each road mode.
Optionally, matching the target road mode from each preset road mode based on the position feature and the motion feature includes:
based on the position features and the motion features, respectively calculating the matching degree of the main track of the target vehicle and each road mode;
and determining a target road mode according to the matching degree of each main track.
Optionally, determining the target track from the candidate track set according to the motion model of the target vehicle includes:
calculating average speed and speed change rate of the target vehicle in the first direction and the second direction respectively; wherein the first direction is perpendicular to the second direction;
a target trajectory is determined from the candidate trajectory set based on the average speed and the speed change rate.
In a second aspect, an embodiment of the present application provides a track determining apparatus for a vehicle, including:
the first acquisition module is used for acquiring the position characteristics and the motion characteristics of the target vehicle;
the matching module is used for matching a target road mode from all preset road modes based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data;
the calculation module is used for calculating the region constraint points based on the track tail end of the target road mode;
the generation module is used for generating a candidate track set based on the region constraint points;
and the determining module is used for determining the target track from the candidate track set according to the motion model of the target vehicle.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring historical video stream data in the perception range of each road side camera;
the third acquisition module is used for acquiring historical traffic flow data by utilizing a detection tracking algorithm based on the historical video flow data;
the preprocessing module is used for preprocessing the historical traffic flow data to obtain preprocessed historical traffic flow data;
and the clustering module is used for clustering by utilizing the preprocessed historical traffic flow data to obtain each road mode.
Optionally, the preprocessing module includes:
the preprocessing unit is used for performing invalid short track filtering and track point time normalization on the historical traffic data to obtain preprocessed historical traffic data.
Optionally, the clustering module includes:
the first calculation unit is used for calculating a track similarity matrix based on the preprocessed historical traffic data;
the second calculation unit is used for calculating the local density value and the inter-cluster distance of each track according to the track similarity matrix;
the dividing unit is used for dividing the road modes based on the local density value and the inter-cluster distance of each track.
Optionally, the dividing unit includes:
the acquisition subunit is used for acquiring a track weight dictionary according to the product value of the local density value and the inter-cluster distance;
and the dividing subunit is used for dividing according to the track weight dictionary and the acquired road environment information to obtain each road mode.
Optionally, the matching module includes:
the third calculation unit is used for calculating the matching degree of the main track of the target vehicle and each road mode based on the position characteristics and the motion characteristics;
and the first determining unit is used for determining a target road mode according to the matching degree of each main track.
Optionally, the determining module includes:
a fourth calculation unit for calculating average division speeds and speed change rates of the target vehicle in the first direction and the second direction, respectively; wherein the first direction is perpendicular to the second direction;
and a second determining unit for determining a target track from the candidate track set based on the average division speed and the speed change rate.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory storing computer program instructions;
the processor when executing the computer program instructions implements the track determining method of the vehicle as shown in the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method for determining a trajectory of a vehicle as shown in the first aspect.
The track determining method, the track determining device, the electronic equipment and the computer storage medium of the vehicle can determine the track of the vehicle more accurately. The track determining method of the vehicle obtains the position characteristic and the motion characteristic of a target vehicle; matching a target road mode from each preset road mode based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data; calculating a region constraint point based on the track tail end of the target road mode; generating a candidate track set based on the region constraint points; and determining the target track from the candidate track set according to the motion model of the target vehicle. Therefore, in the method, the road side camera is used for acquiring the historical traffic flow data, and has the advantages of wide range, fixed background and the like, namely, the road side camera has a wider visual angle than a bicycle sensor, the sensing range is larger, the sensing capability can continuously sense the static environment information, and the road side camera is insensitive to the sensed noise information. Therefore, the application can combine the position location with the road mode deeply excavated by utilizing the historical traffic flow data, predict the future track and the driving direction of the vehicle in the current perception range in advance, control the driving track of the global vehicle, especially at the intersection, early warn the potential collision risk of the vehicle in advance, help reduce the occurrence of traffic accidents, optimize the traffic flow in a small range and reduce the traffic jam condition.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are needed to be used in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
FIG. 1 is a flow chart of a method for determining a trajectory of a vehicle according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for determining a trajectory of a vehicle according to another embodiment of the present application;
FIG. 3 is a schematic view of a localized density-inter-cluster distance visualization provided by one embodiment of the present application;
FIG. 4 is a schematic diagram of visualization of local density-cluster pitch product values provided by one embodiment of the present application;
FIG. 5 is a flowchart of a primary track matching calculation provided by one embodiment of the present application;
FIG. 6 is a single-mode-multi-mode schematic provided by one embodiment of the application;
FIG. 7 is a schematic diagram illustrating a trajectory prediction process according to an embodiment of the present application;
FIG. 8 is a schematic diagram of an example trajectory prediction provided by one embodiment of the application;
fig. 9 is a schematic structural view of a track determining device for a vehicle according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings and the detailed embodiments. It should be understood that the particular embodiments described herein are meant to be illustrative of the application only and not limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the application by showing examples of the application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
As known from the background art, most algorithms for predicting the track in the automatic driving field are based on real-time acquisition of state information of a vehicle end by a vehicle end sensor, and prediction of the future vehicle running track. The implementation of the algorithm mostly depends on real-time vehicle-end state data of a vehicle-end sensor, and the global perception range of an automatic driving vehicle to a road is limited, so that perception errors to the surrounding environment due to shielding and the like are more likely to occur.
In order to solve the problems in the prior art, the embodiment of the application provides a track determining method and device for a vehicle, electronic equipment and a computer storage medium. The following first describes a track determining method for a vehicle according to an embodiment of the present application.
Fig. 1 is a schematic flow chart of a track determining method of a vehicle according to an embodiment of the present application. As shown in fig. 1, the trajectory determination method of the vehicle may include:
s101, acquiring the position characteristic and the motion characteristic of the target vehicle.
S102, matching a target road mode from each preset road mode based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic data acquired by a road side camera and clustering the preprocessed historical traffic data.
In one embodiment, matching the target road pattern from each preset road pattern based on the position features and the motion features includes: based on the position features and the motion features, respectively calculating the matching degree of the main track of the target vehicle and each road mode; and determining a target road mode according to the matching degree of each main track.
In one embodiment, before matching the target road pattern from the respective preset road patterns based on the position feature and the motion feature, the method further includes:
acquiring historical video stream data in the perception range of each road side camera;
based on the historical video stream data, utilizing a detection tracking algorithm to obtain historical vehicle stream data;
preprocessing the historical traffic data to obtain preprocessed historical traffic data;
clustering is carried out by utilizing the preprocessed historical traffic flow data, and each road mode is obtained.
In one embodiment, preprocessing historical traffic data to obtain preprocessed historical traffic data includes:
and performing invalid short track filtration and track point time normalization on the historical traffic data to obtain preprocessed historical traffic data.
In one embodiment, clustering is performed by using the preprocessed historical traffic data to obtain each road mode, including:
calculating a track similarity matrix based on the preprocessed historical traffic data;
calculating a local density value and a cluster distance of each track according to the track similarity matrix;
and dividing the road modes based on the local density value of each track and the inter-cluster distance to obtain each road mode.
In one embodiment, the dividing based on the local density value and the inter-cluster distance of each track, to obtain each road mode includes:
obtaining a track weight dictionary according to the product value of the local density value and the inter-cluster distance;
and dividing according to the track weight dictionary and the acquired road environment information to obtain each road mode.
S103, calculating a region constraint point based on the track tail end of the target road mode.
S104, generating a candidate track set based on the region constraint points.
S105, determining a target track from the candidate track set according to the motion model of the target vehicle.
In one embodiment, determining a target track from a set of candidate tracks according to a motion model of a target vehicle includes:
calculating average speed and speed change rate of the target vehicle in the first direction and the second direction respectively; wherein the first direction is perpendicular to the second direction;
a target trajectory is determined from the candidate trajectory set based on the average speed and the speed change rate.
The track determining method of the vehicle obtains the position characteristic and the motion characteristic of a target vehicle; matching a target road mode from each preset road mode based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data; calculating a region constraint point based on the track tail end of the target road mode; generating a candidate track set based on the region constraint points; and determining the target track from the candidate track set according to the motion model of the target vehicle. Therefore, in the method, the road side camera is used for acquiring the historical traffic flow data, and has the advantages of wide range, fixed background and the like, namely, the road side camera has a wider visual angle than a bicycle sensor, the sensing range is larger, the sensing capability can continuously sense the static environment information, and the road side camera is insensitive to the sensed noise information. Therefore, the application can combine the position location with the road mode deeply excavated by utilizing the historical traffic flow data, predict the future track and the driving direction of the vehicle in the current perception range in advance, control the driving track of the global vehicle, especially at the intersection, early warn the potential collision risk of the vehicle in advance, help reduce the occurrence of traffic accidents, optimize the traffic flow in a small range and reduce the traffic jam condition.
The technical scheme is described below in a specific scene embodiment.
The method provided in this embodiment may be divided into three main parts: 1) Firstly, collecting historical traffic flow information in a historical video flow shot by a road side camera by using a detection tracking algorithm, and preprocessing traffic flow tracks; 2) Clustering and extracting features of the traffic flow track based on a rapid clustering algorithm, and judging a future running mode of the vehicle through position positioning; 3) A possible driving area of the terminal end of the future vehicle is calculated based on the track cluster in the future driving mode of the vehicle, and the driving track of the vehicle is regulated through the area constraint.
The general flow chart of the method can be specifically seen in fig. 2, and the description of the road mode extraction problem and the optimal track prediction problem based on the historical traffic flow based on fig. 2 is performed. First, a road pattern extraction problem based on a history of traffic is explained.
In order to acquire the road mode and the corresponding track cluster, the present embodiment needs to perform three processes of track acquisition, track filtering and main track selection of the historical traffic.
1. Track acquisition:
1) Acquiring historical video stream data in the current road side camera perception range, and selecting video streams with clear weather and high definition;
2) Based on the selected video stream data, all vehicle tracks passing through the road side camera are obtained by using a detection tracking algorithm, and the vehicle tracks are stored.
2. Track pretreatment:
1) The invalid short tracks are filtered. The ineffective short track mainly comprises an excessively short track and a stop track, and a track with fewer track points may occur due to an error of target detection or tracking, and in this embodiment, the minimum track point threshold is set to 100, and the minimum track point threshold is adjustable according to the total number of tracks. The stopping track refers to a non-driving vehicle track where some vehicles wait at the roadside, and the track has less information provided for the driving mode of the vehicles and possibly becomes a noise track, and in this embodiment, the track with the distance smaller than 60 is deleted by taking the distance between the head point and the tail point of the track as a reference basis.
2) Track point time normalization. Since there is no unified time standard for the vehicle running track, it is necessary to align the time for the track to do the difference processing j Track is taken as an example, and the track is time-aligned:
t′ i =t i -t 1
i.e. current time minus track numberOne trace point time, all traces were normalized from time 0. The track set after track screening is defined asT n Represents the number of tracks +.>Wherein P is n Represents the number of track points, represents the information of one position point of the track, and is P k ={tid,cx k ,cy k ,t′ k Tid denotes the vehicle number, t k Representing the chronological order in the trajectory.
3. Primary track selection of historical traffic:
in the embodiment, historical traffic flow information is clustered, the clustered central track becomes a main track, and other tracks of the same cluster are called secondary tracks.
1) And calculating a track similarity matrix. The track similarity matrix is non-real-time updated data, accuracy and applicability can be simply considered in calculation, and real-time performance is not required to be considered, so that the longest public substring algorithm is selected in the embodiment.
Assume a trajectory T i And T j Respectively of length ofAnd->The longest common subsequence length of the track is then:
where gamma is the similarity threshold for the trace point,
the similarity between tracks is:
obtaining a track correlation matrix: smat= (S i,j ),i,j∈[1,T n ]
2) According to the track correlation matrix SMat, calculating the local density value of each track, wherein the calculation formula is as follows:
wherein the function is
S c > 0 and is an integer, is a truncated distance, and this value is specified by the user. ρ i Indicating that the ith track and other tracks are smaller than S c Number of trajectories of distance.
3) According to the track correlation matrix, the distance between clusters of each track is calculated according to the following calculation formula:
where α is a custom term, which is set to 0.1 in this embodiment. Fig. 3 is a schematic view of a visualization of local density-cluster spacing provided by an embodiment of the present application, where ρ and δ represent the abscissa of fig. 3, respectively.
4) Calculating ρ for each track i ·δ i After descending order of values, as shown in fig. 4, the dots represent main tracks, the pentagram represents sub-tracks, and the first C corresponding tracks are selected as road modes in the perception range in combination with the road complexity under the current camera, the main tracks are expressed asC represents the number of track clusters.
5) And dividing other tracks into corresponding road modes according to the correlation degree to obtain the road modes and sub-tracks under the corresponding modes.
The road pattern extraction problem based on the history traffic has been described above, and the optimum trajectory prediction problem is described below.
1. And calculating the matching degree of the target vehicle and the main track under the C road modes according to the position characteristics and the motion characteristics.
Calculating the distance matching degree of the current vehicle track and the history vehicle running main mode, and corresponding point index values, and traversing the main trackCalculating the distance between the target vehicle w and each main track, and sequencing the distances from small to large to represent the distance as P= { PosDis w_k },k∈[1,C]When the distance between the vehicle w and each main mode is smaller than the threshold value, the vehicle is indicated to have the driving intention of the direction, and the calculation flow is as shown in fig. 5.
There may be multiple travel modes through the distance matching, such as single mode and multiple modes in fig. 6. Assuming that Z is less than or equal to C main modes obtained by filtering, in order to obtain the current optimal road mode of the vehicle, calculating the average speed of the x-axis of the target vehicle and the main track k based on the latest n track points of the target vehicle w and the corresponding track points of the Z main tracks And acceleration->y-axis average speed> And acceleration->Obtaining a degree of correlation based on the motion state:
the value is expressed as m= { MoveDis by the order of small to large w_k },k∈[1,Z]And selecting the main track corresponding to the minimum value as the current optimal running mode of the target vehicle.
2. And predicting the vehicle track in the optimal driving mode.
1) And calculating the region constraint point at the tail end of the track of the optimal running mode. Preparing a data set based on a driving mode of a vehicle and a corresponding track cluster, and extracting a feature expressed as F= { F from the track cluster 1 ,f 2 ,f 3 ,f 4 Label is label, f 1 Representing the distance between the track and the central line of the lane when the track exits the intersection, f 2 Express speed, f 3 Indicating acceleration, f 4 And the azimuth angle is represented, and the label represents the distance from the center line of the lane when the track passes through the intersection and enters the road.
A linear regression algorithm is selected to study the relation between label and the characteristic F, and the formula label=W is solved T ·F+w 0 Medium parameters W and W 0 After the parameters are obtained, extracting the characteristic input formula of the target vehicle to obtain the predicted valueNamely, the region constraint points indicated by "x" in fig. 7.
2) A candidate trajectory set is generated based on the region constraint points. The region constraint point is a place through which the end of a predicted track obtained based on the current vehicle running information in combination with the history traffic is most likely to pass, as shown in fig. 7, "o" represents the current vehicle history track, "o" represents the true track, the black solid line is a candidate track set obtained by adjustment of parameters ζ and η, η represents the distance from the farthest point of the baseline, and ζ represents the distance from the initial point after baseline projection.
3) And selecting an optimal track according to the motion model.
The average speed and the speed change rate alpha of the current speed of the target vehicle in the x axis and the y axis are calculated, and the vehicle predicts the vehicle track according to the uniform speed change formula, as shown by the broken line in fig. 7.
The motion model predicts the average minimum distance between k track points and the candidate track, and selects the candidate track with the corresponding minimum distance as the current predicted track of the vehicle.
According to the method, the advantages of the road side sensing equipment are fully utilized, the road mode and the corresponding track cluster are extracted based on the historical traffic flow, the running mode of the current target vehicle is predicted, the running mode and the candidate end point area of the corresponding track cluster are combined, the vehicle speed and the acceleration are restrained through the candidate end point area, a better fitting state is achieved for the vehicle, and therefore the final purpose of vehicle track prediction is achieved.
As shown in fig. 8, after the travel pattern of the track (2) is obtained, the constraint area points "x" are obtained based on the historical traffic prediction in the pattern, and the generated candidate track set is used for selecting the optimal track in the candidate track set by predicting the track through the motion model.
As shown in fig. 9, an embodiment of the present application further provides a trajectory determining device of a vehicle, including:
a first acquisition module 901, configured to acquire a position feature and a motion feature of a target vehicle;
the matching module 902 is configured to match a target road mode from each preset road mode based on the location feature and the motion feature; the road mode is obtained by preprocessing historical traffic flow data acquired by a road side camera and clustering the preprocessed historical traffic flow data;
a calculation module 903, configured to calculate a region constraint point based on a track end of the target road mode;
a generating module 904, configured to generate a candidate track set based on the region constraint points;
a determining module 905 is configured to determine a target track from the candidate track set according to a motion model of the target vehicle.
In one embodiment, the trajectory determining device of the vehicle further includes:
the second acquisition module is used for acquiring historical video stream data in the perception range of each road side camera;
the third acquisition module is used for acquiring historical traffic flow data by utilizing a detection tracking algorithm based on the historical video flow data;
the preprocessing module is used for preprocessing the historical traffic flow data to obtain preprocessed historical traffic flow data;
and the clustering module is used for clustering by utilizing the preprocessed historical traffic flow data to obtain each road mode.
In one embodiment, the preprocessing module includes:
the preprocessing unit is used for performing invalid short track filtering and track point time normalization on the historical traffic data to obtain preprocessed historical traffic data.
In one embodiment, a clustering module includes:
the first calculation unit is used for calculating a track similarity matrix based on the preprocessed historical traffic data;
the second calculation unit is used for calculating the local density value and the inter-cluster distance of each track according to the track similarity matrix;
the dividing unit is used for dividing the road modes based on the local density value and the inter-cluster distance of each track.
In one embodiment, the partitioning unit includes:
the acquisition subunit is used for acquiring a track weight dictionary according to the product value of the local density value and the inter-cluster distance;
and the dividing subunit is used for dividing according to the track weight dictionary and the acquired road environment information to obtain each road mode.
In one embodiment, the matching module 902 includes:
the third calculation unit is used for calculating the matching degree of the main track of the target vehicle and each road mode based on the position characteristics and the motion characteristics;
and the first determining unit is used for determining a target road mode according to the matching degree of each main track.
In one embodiment, the determining module 905 includes:
a fourth calculation unit for calculating average division speeds and speed change rates of the target vehicle in the first direction and the second direction, respectively; wherein the first direction is perpendicular to the second direction;
and a second determining unit for determining a target track from the candidate track set based on the average division speed and the speed change rate.
The modules/units in the apparatus shown in fig. 9 have functions of implementing the steps in fig. 1, and achieve corresponding technical effects, which are not described herein for brevity.
Fig. 10 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
The electronic device may include a processor 1001 and a memory 1002 storing computer program instructions.
In particular, the processor 1001 described above may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.
Memory 1002 may include mass storage for data or instructions. By way of example, and not limitation, memory 1002 may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. The memory 1002 may include removable or non-removable (or fixed) media, where appropriate. The memory 1002 may be internal or external to the electronic device, where appropriate. In a particular embodiment, the memory 1002 may be a non-volatile solid state memory.
In one example, the Memory 1002 may be a Read Only Memory (ROM). In one example, the ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.
The processor 1001 reads and executes the computer program instructions stored in the memory 1002 to implement the trajectory determination method of any one of the vehicles of the above-described embodiments.
In one example, the electronic device may also include a communication interface 1003 and a bus 1010. As shown in fig. 10, the processor 1001, the memory 1002, and the communication interface 1003 are connected to each other by a bus 1010, and perform communication with each other.
The communication interface 1003 is mainly used for implementing communication among the modules, devices, units and/or apparatuses in the embodiment of the application.
Bus 1010 includes hardware, software, or both, coupling components of the online data flow billing device to each other. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. Bus 1010 may include one or more buses, where appropriate. Although embodiments of the application have been described and illustrated with respect to a particular bus, the application contemplates any suitable bus or interconnect.
In addition, embodiments of the present application may be implemented by providing a computer storage medium. The computer storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement the trajectory determination method of any one of the vehicles of the above embodiments.
It should be understood that the application is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present application, and they should be included in the scope of the present application.
Claims (10)
1. A track determining method of a vehicle, characterized by comprising:
acquiring position features and motion features of a target vehicle;
based on the position features and the motion features, matching a target road mode from each preset road mode; the road mode is obtained by preprocessing historical traffic data acquired by a road side camera and clustering the preprocessed historical traffic data;
calculating a region constraint point based on the track tail end of the target road mode, wherein the region constraint point is a place through which the predicted track tail end obtained by combining the current vehicle running information with the historical traffic flow is most likely to pass;
generating a candidate track set based on the region constraint points;
and determining a target track from the candidate track set according to the motion model of the target vehicle.
2. The trajectory determination method of a vehicle according to claim 1, characterized by further comprising, before the matching of the target road pattern from the respective preset road patterns based on the position feature and the motion feature:
acquiring historical video stream data in the perception range of each road side camera;
based on the historical video stream data, obtaining the historical vehicle stream data by using a detection tracking algorithm;
preprocessing the historical traffic flow data to obtain preprocessed historical traffic flow data;
and clustering by utilizing the preprocessed historical traffic flow data to obtain each road mode.
3. The method for determining a track of a vehicle according to claim 2, wherein the preprocessing the historical traffic data to obtain the preprocessed historical traffic data includes:
and performing invalid short track filtration and track point time normalization on the historical traffic data to obtain the preprocessed historical traffic data.
4. The method for determining a track of a vehicle according to claim 2, wherein the clustering using the preprocessed historical traffic data to obtain each of the road patterns includes:
calculating a track similarity matrix based on the preprocessed historical traffic data;
calculating a local density value and a cluster distance of each track according to the track similarity matrix;
and dividing the road modes based on the local density value and the inter-cluster distance of each track.
5. The track determining method of the vehicle according to claim 4, wherein the dividing based on the local density value and the inter-cluster distance of each track to obtain each of the road patterns includes:
obtaining a track weight dictionary according to the product value of the local density value and the inter-cluster distance;
and dividing according to the track weight dictionary and the acquired road environment information to obtain each road mode.
6. The trajectory determination method of a vehicle according to claim 1, wherein said matching a target road pattern from among respective preset road patterns based on the position feature and the motion feature includes:
based on the position features and the motion features, respectively calculating the main track matching degree of the target vehicle and each road mode;
and determining the target road mode according to the matching degree of the main tracks.
7. The method for determining a trajectory of a vehicle according to claim 1, wherein determining a target trajectory from the candidate trajectory set according to a motion model of the target vehicle includes:
calculating average speed and speed change rate of the target vehicle in a first direction and a second direction respectively; wherein the first direction is perpendicular to the second direction;
the target trajectory is determined from the candidate trajectory set based on the average division speed and the speed change rate.
8. A track determining device of a vehicle, characterized by comprising:
the first acquisition module is used for acquiring the position characteristics and the motion characteristics of the target vehicle;
the matching module is used for matching a target road mode from all preset road modes based on the position characteristics and the motion characteristics; the road mode is obtained by preprocessing historical traffic data acquired by a road side camera and clustering the preprocessed historical traffic data;
the calculation module is used for calculating a region constraint point based on the track tail end of the target road mode, wherein the region constraint point is a place through which the predicted track tail end obtained by combining the current vehicle running information with the historical traffic flow is most likely to pass;
the generation module is used for generating a candidate track set based on the region constraint points;
and the determining module is used for determining a target track from the candidate track set according to the motion model of the target vehicle.
9. An electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the trajectory determination method of a vehicle as claimed in any one of claims 1 to 7.
10. A computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of determining a trajectory of a vehicle as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011438299.0A CN112597822B (en) | 2020-12-11 | 2020-12-11 | Vehicle track determination method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011438299.0A CN112597822B (en) | 2020-12-11 | 2020-12-11 | Vehicle track determination method and device, electronic equipment and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112597822A CN112597822A (en) | 2021-04-02 |
CN112597822B true CN112597822B (en) | 2023-08-15 |
Family
ID=75192342
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011438299.0A Active CN112597822B (en) | 2020-12-11 | 2020-12-11 | Vehicle track determination method and device, electronic equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112597822B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221677B (en) * | 2021-04-26 | 2024-04-16 | 阿波罗智联(北京)科技有限公司 | Track abnormality detection method and device, road side equipment and cloud control platform |
CN113157848A (en) * | 2021-05-06 | 2021-07-23 | 清华大学 | Method and device for determining air route, electronic equipment and storage medium |
CN113252062B (en) * | 2021-06-01 | 2021-12-10 | 智道网联科技(北京)有限公司 | Method and device for generating real-time map, electronic equipment and storage medium |
CN113593219B (en) * | 2021-06-30 | 2023-02-28 | 北京百度网讯科技有限公司 | Traffic flow statistical method and device, electronic equipment and storage medium |
CN113763430B (en) * | 2021-09-13 | 2024-07-02 | 智道网联科技(北京)有限公司 | Method, apparatus and computer readable storage medium for detecting moving object |
CN113879333B (en) * | 2021-09-30 | 2023-08-22 | 深圳市商汤科技有限公司 | Track prediction method, track prediction device, electronic equipment and storage medium |
CN114092911B (en) * | 2021-11-23 | 2023-08-01 | 北京百度网讯科技有限公司 | Road identification method, device, electronic equipment and storage medium |
CN114355839B (en) * | 2022-03-18 | 2022-07-29 | 浙江西图盟数字科技有限公司 | Motion trail processing method, device, equipment and storage medium |
CN114973684B (en) * | 2022-07-25 | 2022-10-14 | 深圳联和智慧科技有限公司 | Fixed-point monitoring method and system for construction site |
CN115423393B (en) * | 2022-08-12 | 2023-04-18 | 北京邮电大学 | Order scheduling method and device of dynamic self-adaptive scheduling period based on LSTM |
CN115238024B (en) * | 2022-09-26 | 2022-12-20 | 交通运输部科学研究院 | Highway facility positioning method and device, electronic equipment and storage medium |
CN115907159B (en) * | 2022-11-22 | 2023-08-29 | 应急管理部国家减灾中心 | Method, device, equipment and medium for determining typhoons in similar paths |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5266948A (en) * | 1990-11-28 | 1993-11-30 | Honda Giken Kogyo Kabushiki Kaisha | Apparatus and method for displaying a travel position |
JP2010190721A (en) * | 2009-02-18 | 2010-09-02 | Aisin Aw Co Ltd | On-vehicle navigation device and vehicle orientation change part determination program |
CN111402580A (en) * | 2020-03-04 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Vehicle running track prediction method and device and electronic equipment |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2278576A1 (en) * | 2002-03-29 | 2011-01-26 | Panasonic Corporation | Map matching method, map matching device, database for shape matching, and shape matching device |
JP4910510B2 (en) * | 2006-06-30 | 2012-04-04 | 株式会社デンソー | Control information storage device and program |
JP5126263B2 (en) * | 2010-03-23 | 2013-01-23 | 株式会社デンソー | Vehicle navigation device |
CN109583151B (en) * | 2019-02-20 | 2023-07-21 | 阿波罗智能技术(北京)有限公司 | Method and device for predicting running track of vehicle |
-
2020
- 2020-12-11 CN CN202011438299.0A patent/CN112597822B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5266948A (en) * | 1990-11-28 | 1993-11-30 | Honda Giken Kogyo Kabushiki Kaisha | Apparatus and method for displaying a travel position |
JP2010190721A (en) * | 2009-02-18 | 2010-09-02 | Aisin Aw Co Ltd | On-vehicle navigation device and vehicle orientation change part determination program |
CN111402580A (en) * | 2020-03-04 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Vehicle running track prediction method and device and electronic equipment |
Non-Patent Citations (1)
Title |
---|
基于模糊模式识别的车辆定位地图匹配算法;孙棣华;王春丽;;计算机工程与应用(25);第231-234页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112597822A (en) | 2021-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112597822B (en) | Vehicle track determination method and device, electronic equipment and computer storage medium | |
CN112665590B (en) | Vehicle track determination method and device, electronic equipment and computer storage medium | |
US8606539B2 (en) | Road configuration estimation apparatus, computer program, and road configuration estimation method | |
JP6330651B2 (en) | Anomaly detection device | |
CN106569214A (en) | Method and system for processing vehicle-mounted radar data of adaptive cruise vehicle in conjunction with navigation information | |
CN111103587A (en) | Method and apparatus for predicting simultaneous and concurrent vehicles and vehicle including the same | |
CN110307841A (en) | One kind measuring incomplete vehicle movement parameter estimation method based on information | |
CN110705484B (en) | Method for recognizing continuous lane change illegal behaviors by utilizing driving track | |
CN114822044A (en) | Driving safety early warning method and device based on tunnel | |
CN111738323B (en) | Hybrid enhanced intelligent track prediction method and device based on gray Markov model | |
CN111582317B (en) | Road positioning method and device | |
CN116224317A (en) | Method and device for predicting motion trail of non-motor vehicle and related equipment | |
JP5573780B2 (en) | Course evaluation device and course evaluation method | |
WO2013128486A1 (en) | Traffic amount prediction system | |
CN112572471B (en) | Automatic driving method, device, electronic equipment and computer storage medium | |
CN113176562A (en) | Multi-target tracking method and device, electronic equipment and readable storage medium | |
CN110940981B (en) | Method for judging whether position of object in front of vehicle is in own lane | |
CN111488417B (en) | Information processing method, system, device, equipment and computer storage medium | |
CN116481560B (en) | Vehicle driving mileage calculation method, device, terminal and storage medium | |
CN113470070B (en) | Driving scene target tracking method, device, equipment and storage medium | |
CN117523914A (en) | Collision early warning method, device, equipment, readable storage medium and program product | |
CN114234975A (en) | Low-frequency real-time track matching method, system, computer device and storage medium | |
CN116894225B (en) | Driving behavior abnormality analysis method, device, equipment and medium thereof | |
CN115661797B (en) | Target tracking method, device and equipment | |
CN115270967A (en) | Data processing method, equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |