CN109858374B - Automatic extraction method and device for arrow mark lines in high-precision map making - Google Patents
Automatic extraction method and device for arrow mark lines in high-precision map making Download PDFInfo
- Publication number
- CN109858374B CN109858374B CN201811650011.9A CN201811650011A CN109858374B CN 109858374 B CN109858374 B CN 109858374B CN 201811650011 A CN201811650011 A CN 201811650011A CN 109858374 B CN109858374 B CN 109858374B
- Authority
- CN
- China
- Prior art keywords
- arrow
- point cloud
- target
- coordinates
- image
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides an arrow mark line automatic extraction method and device in high-precision map manufacturing, three-dimensional point cloud data is used as input, arrow target shape points are automatically extracted end to end, arrow shape points are effectively extracted by an image key point regression method, and the arrow extraction precision is ensured to meet the high-precision map manufacturing requirement; the point cloud semantic segmentation is used for obtaining high-level semantic relation scene understanding, and algorithm robustness is improved; the method can effectively improve the accuracy of arrow mark line extraction and the automatic manufacturing efficiency of high-precision maps, and reduce the workload of manual marking.
Description
Technical Field
The embodiment of the invention relates to the technical field of high-precision map making, in particular to a method and a device for automatically extracting arrow mark lines in high-precision map making.
Background
The automobile changes the travel mode of human beings, strongly promotes the flow of commodities and people with convenience and rapidity, and plays an important role in the development of economy and society. With the continuous development of production technology, the new production mode reduces the unit production time of automobiles and the unit price of automobiles, so that the automobiles become a popular product. By 2010, there are about a total of 10 hundred million cars in the world, and this number is still growing at a high rate. However, with the increase in the amount of automobile keeping, the problem of traffic safety is becoming more prominent. More than 50 million traffic accidents occur in China every year, the number of dead people in the traffic accidents exceeds 10 million, and the economic loss caused by the traffic accidents can reach hundreds of billions of yuan every year.
At present, research on unmanned vehicles has been carried out successively in various countries, but limited by the development of technology, it takes some time for machines to completely replace humans to complete vehicle driving. Modern intelligent vehicles often employ a driving assistance system to ensure the safety of drivers. For example, an automatic parking assist system, a brake assist system, a reverse assist system, a driving assist system, a lane keeping assist system, and the like, which have been found in high-end vehicle models. The key technology of the lane keeping auxiliary system is detection of the road marking, the position relation between the vehicle and the road marking can be calculated through the lane keeping auxiliary system, a driver can be reminded of the driving state of the vehicle, the problem of road deviation caused by fatigue driving or human negligence can be effectively solved, and safety is improved.
The high-precision map is one of unmanned core technologies, and the precise map is crucial to positioning, navigation and control and safety of the unmanned vehicle. High-precision maps contain a large amount of driving assistance information, the most important of which is an accurate three-dimensional representation of the road network (centimeter-level precision). For example, the geometric structure of the road surface, the position of the road traffic marking, the point cloud model of the surrounding road environment, etc. The road traffic marking is a traffic safety facility formed by various lines, arrows, characters, vertical marks, raised road signs, contour marks and the like marked on the road surface, and has the function of controlling and guiding traffic.
Disclosure of Invention
The present invention provides a method and apparatus for automatically extracting arrow-like markings in high-precision mapping that overcomes or at least partially solves the above-mentioned problems.
In a first aspect, an embodiment of the present invention provides a method for automatically extracting arrow-like marked lines in high-precision map making, including:
acquiring three-dimensional point cloud data of a road scene in the ground high-precision map making, and obtaining target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing orthogonal projection inverse transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
Preferably, the acquiring three-dimensional point cloud data of a road scene in map making specifically includes:
acquiring three-dimensional point cloud data of a road scene based on a laser scanning radar:
P＝{pk＝(xk，yk，zk，ik)，1≤k≤n}
in the formula, pkIs a single point, (x)k，yk，zk) As point coordinates, ikThe dot intensity is represented by k, the serial number of the dot, and n, the number of the dot.
Preferably, before obtaining the target point cloud forming the arrow target based on the trained point cloud semantic segmentation model, the method further includes:
marking arrow-shaped points of an arrow target in the three-dimensional point cloud data of the road scene;
intercepting a target point cloud only containing arrow targets based on the arrow-shaped points;
and performing orthogonal projection on the target point cloud to generate an arrow image, and converting the point cloud coordinate of the target point cloud into an image coordinate of the arrow image.
Preferably, after performing orthogonal projection on the target point cloud to generate an arrow image, the method further includes:
converting the arrow point coordinates into image coordinates as labeling information corresponding to orthogonal projection, and making a training set;
performing thermodynamic diagram regression training based on the convolutional neural network CNN model to obtain a key point regression model for extracting arrow point image coordinates in the arrow point image.
Preferably, after the arrow-shaped points of the arrow target in the three-dimensional point cloud data are labeled, the method further includes:
and manufacturing a point cloud semantic segmentation data set based on the arrow-shaped points marked with the arrow targets, and performing deep learning training based on the point cloud semantic segmentation data set to obtain a point cloud semantic segmentation model.
Preferably, the marking the arrow-shaped points of the arrow target in the three-dimensional point cloud data specifically includes:
based on the point cloud interactive labeling tool, labeling arrow-shaped points of the arrow target, and labeling information of each arrow-shaped point is Lc＝{(xj，yj，zj) J is more than or equal to 1 and less than or equal to m, wherein c is a label type, (x)j，yj，zj) For marking coordinates, j is the serial number of the shape points, and m is the number of the shape points.
Preferably, intercepting a target point cloud only including an arrow target based on the arrow-shaped point specifically includes:
forming a minimum circumscribed cube based on the marked arrow-shaped points, and expanding the minimum circumscribed cube in the directions of +/-X, + -Y and +/-Z by using the center of the minimum circumscribed cube, wherein the expansion coefficients in the directions of +/-X, + -Y and +/-Z are respectively alpha, beta and gamma;
and intercepting the point cloud based on the expanded cube to obtain the target point cloud.
In a second aspect, an embodiment of the present invention provides an automatic extraction apparatus for arrow-like markings in high-precision map making, including:
the system comprises a first module, a second module and a third module, wherein the first module is used for acquiring three-dimensional point cloud data of a road scene in map making and obtaining target point clouds forming arrow targets based on a trained point cloud semantic segmentation model;
and the second module is used for generating an arrow image based on the target point cloud orthogonal projection, obtaining the image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain the point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
The embodiment of the invention provides an automatic extraction method and device for arrow mark lines in high-precision map manufacturing, three-dimensional point cloud data is used as input, arrow target shape points are automatically extracted end to end, arrow shape points are effectively extracted by using an image key point regression method, and the arrow extraction precision is ensured to meet the high-precision map manufacturing requirement; the point cloud semantic segmentation is used for obtaining high-level semantic relation scene understanding, and algorithm robustness is improved; the method can effectively improve the accuracy of arrow mark line extraction and the automatic manufacturing efficiency of high-precision maps, and reduce the workload of manual marking.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an automatic extraction method for arrow-like reticle in high-precision map making according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a specific method for automatically extracting arrow-like marks in high-precision map making according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an apparatus for automatically extracting arrow-like markings in high-precision mapping according to an embodiment of the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the field of road safety evaluation and simulation, vehicle-mounted laser point cloud measuring systems have been widely applied. The real scene based on 360-degree panoramic photo makes the road environment visual and more real, and the matching and fusion of the road color laser point cloud data makes the measurable road visual environment. In this context, the extraction of the markings in the road facilitates mapping, analysis and safety evaluation in a measurable 360 ° real scene. However, the current point cloud data formats are different, most of the point cloud data formats need to rely on expensive measuring equipment, and the design of sufficient acquisition parameters is started from the design of the equipment, so that the complexity of the problem is increased. The road marking data is extracted from the conventional data of the point cloud quickly and effectively, and the problem to be solved at present is solved urgently.
Therefore, the embodiments of the invention provide a method and a device for automatically extracting arrow mark lines in high-precision map manufacturing, which can effectively improve the accuracy of extracting the arrow mark lines and the efficiency of automatically manufacturing the high-precision map. The following description and description will proceed with reference being made to various embodiments.
Fig. 1 is a diagram illustrating an automatic extraction method of arrow-like marked lines in high-precision map making according to an embodiment of the present invention, including:
s1, acquiring three-dimensional point cloud data of a road scene in high-precision map making, and obtaining target point clouds forming arrow targets based on a trained point cloud semantic segmentation model;
s2, generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
In the embodiment, three-dimensional point cloud data is used as input, arrow target shape points are automatically extracted end to end, arrow shape points are effectively extracted by using an image key point regression method, and the arrow extraction precision is guaranteed to meet the high-precision map manufacturing requirement; the point cloud semantic segmentation is used for obtaining high-level semantic relation scene understanding, and algorithm robustness is improved; the method can effectively improve the accuracy of arrow mark line extraction and the automatic manufacturing efficiency of high-precision maps, and reduce the workload of manual marking.
On the basis of the above embodiment, acquiring three-dimensional point cloud data of a road scene in map making specifically includes:
acquiring three-dimensional point cloud data of a road scene based on a laser scanning radar:
P＝{pk＝(xk，yk，zk，ik)，1≤k≤n}
in the formula, pkIs a single point, (x)k，yk，zk) As point coordinates, ikThe dot intensity is represented by k, the serial number of the dot, and n, the number of the dot.
In the embodiment, the three-dimensional laser scanning technology is used as a means for extracting road characteristic information, and rapid reverse three-dimensional data acquisition and model reconstruction can be directly performed from a real object, so that the scanned real object is completely reconstructed with high precision, and original mapping data is rapidly obtained. The obtained coordinate information, color RGB value, road marking distribution characteristics, positions and the like of the road data points have important significance for automatic extraction and identification of road characteristic information.
On the basis of the foregoing embodiments, as shown in fig. 2, before obtaining a target point cloud constituting an arrow target based on a trained point cloud semantic segmentation model, the method further includes:
marking arrow-shaped points of an arrow target in the three-dimensional point cloud data of the road scene;
intercepting a target point cloud only containing arrow targets based on the arrow-shaped points;
and performing orthogonal projection on the target point cloud to generate an arrow image, and converting the point cloud coordinate of the target point cloud into an image coordinate of the arrow image.
On the basis of the above embodiments, after performing orthogonal projection on the target point cloud to generate an arrow image, the method further includes:
converting the arrow point coordinates into image coordinates as labeling information corresponding to orthogonal projection, and making a training set;
performing thermodynamic diagram regression training based on the convolutional neural network CNN model to obtain a key point regression model for extracting arrow point image coordinates in the arrow point image.
On the basis of the above embodiments, after the arrow-shaped points of the arrow target in the three-dimensional point cloud data are labeled, the method further includes:
and manufacturing a point cloud semantic segmentation data set based on the arrow-shaped points marked with the arrow targets, and performing deep learning training based on the point cloud semantic segmentation data set to obtain a point cloud semantic segmentation model.
On the basis of the above embodiments, labeling the arrow-shaped points of the arrow target in the three-dimensional point cloud data specifically includes:
based on the point cloud interactive labeling tool, labeling arrow-shaped points of the arrow target, and labeling information of each arrow-shaped point is Lc＝{(xj，yj，zj) J is more than or equal to 1 and less than or equal to m, wherein c is a label type, (x)j，yj，zj) For marking coordinates, j is the serial number of the shape points, and m is the number of the shape points.
On the basis of the above embodiments, intercepting a target point cloud only including an arrow target based on the arrow-shaped point specifically includes:
forming a minimum circumscribed cube based on the marked arrow-shaped points, and expanding the minimum circumscribed cube in the directions of +/-X, + -Y and +/-Z by using the center of the minimum circumscribed cube, wherein the expansion coefficients in the directions of +/-X, + -Y and +/-Z are respectively alpha, beta and gamma;
and intercepting the point cloud based on the expanded cube to obtain the target point cloud. And intercepting the three-dimensional point cloud data through the expanded cube to obtain the target point cloud.
The present embodiment further provides an apparatus for automatically extracting arrow-like reticle in high-precision map making, based on the method for automatically extracting arrow-like reticle in high-precision map making in the above embodiments, as shown in fig. 3, including a first module 30 and a second module 40, where:
the first module 30 obtains three-dimensional point cloud data of a road scene in map making, and obtains a target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
the second module 40 generates an arrow image based on the target point cloud orthogonal projection, obtains image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performs inverse orthogonal projection transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracts an arrow target based on the point cloud coordinates.
Fig. 4 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call a computer program stored on the memory 830 and executable on the processor 810 to perform the method for automatically extracting arrow-like reticle in high-precision mapping provided by the above embodiments, for example, the method includes:
s1, acquiring three-dimensional point cloud data of a road scene in map making, and obtaining target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
s2, generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, is implemented to perform the method for automatically extracting arrow-like reticles in high-precision mapping provided in the foregoing embodiments, for example, the method includes:
s1, acquiring three-dimensional point cloud data of a road scene in map making, and obtaining target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
s2, generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the method for automatically extracting arrow-like reticle in high-precision mapping, including:
s1, acquiring three-dimensional point cloud data of a road scene in map making, and obtaining target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
s2, generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
In summary, according to the method and the device for automatically extracting arrow-like marked lines in high-precision map making provided by the embodiment of the invention, three-dimensional point cloud data is used as input, arrow target shape points are automatically extracted end to end, arrow shape points are effectively extracted by using an image key point regression method, and the arrow extraction precision is ensured to meet the high-precision map making requirement; the point cloud semantic segmentation is used for obtaining high-level semantic relation scene understanding, and algorithm robustness is improved; the method can effectively improve the accuracy of arrow mark line extraction and the automatic manufacturing efficiency of high-precision maps, and reduce the workload of manual marking.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. An automatic extraction method of arrow mark lines in high-precision map making is characterized by comprising the following steps:
acquiring three-dimensional point cloud data of a road scene in high-precision map making, and marking arrow-shaped points of arrow targets in the three-dimensional point cloud data of the road scene; intercepting a target point cloud containing only arrow targets based on the arrow-shaped points: forming a minimum circumscribed cube based on the marked arrow-shaped points, and expanding the minimum circumscribed cube in the directions of +/-X, + -Y and +/-Z by using the center of the minimum circumscribed cube, wherein the expansion coefficients in the directions of +/-X, + -Y and +/-Z are respectively alpha, beta and gamma; intercepting point clouds based on the expanded cube to obtain target point clouds; performing orthogonal projection on the target point cloud to generate an arrow image, and converting the point cloud coordinate of the target point cloud into an image coordinate of the arrow image;
manufacturing a point cloud semantic segmentation data set based on arrow-shaped points marked with arrow targets, and performing deep learning training based on the point cloud semantic segmentation data set to obtain a point cloud semantic segmentation model;
converting the arrow point coordinates into image coordinates as labeling information corresponding to orthogonal projection, and making a training set;
performing thermodynamic diagram regression training based on a Convolutional Neural Network (CNN) model to obtain a key point regression model for extracting arrow point image coordinates in an arrow point image;
obtaining a target point cloud forming an arrow target based on the trained point cloud semantic segmentation model;
generating an arrow image based on the target point cloud orthogonal projection, obtaining image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing orthogonal projection inverse transformation on the arrow-shaped points to obtain point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
2. The method for automatically extracting arrow-type marked lines in high-precision map making according to claim 1, wherein the step of obtaining three-dimensional point cloud data of a road scene in map making specifically comprises the steps of:
acquiring three-dimensional point cloud data of a road scene based on a laser scanning radar:
P={p k =（x k ，y k ，z k ，i k ），1≤k≤n}
in the formula (I), the compound is shown in the specification,p k is a single point, (x k ，y k ，z k ) In the form of point coordinates, the coordinates of the points,i k the dot intensity is represented by k, the serial number of the dot, and n, the number of the dot.
3. The method for automatically extracting arrow-like reticle in high-precision mapping according to claim 1, wherein labeling arrow-like points of an arrow target in the three-dimensional point cloud data specifically comprises:
based on the point cloud interactive labeling tool, the arrow-shaped points of the arrow target are labeled, and the labeling information of each arrow-shaped point isL c ={（x j ，y j ，z j ），1≤jLess than or equal to m, wherein,cfor labeling categories, (x j ，y j ，z j ) In order to label the coordinates of the object,jthe serial numbers of the figure points are shown,mthe number of the figure points.
4. An arrow mark line automatic extraction device in high accuracy map making, its characterized in that includes:
the system comprises a first module, a second module and a third module, wherein the first module is used for acquiring three-dimensional point cloud data of a road scene in map making and marking arrow-shaped points of arrow targets in the three-dimensional point cloud data of the road scene; intercepting a target point cloud containing only arrow targets based on the arrow-shaped points: forming a minimum circumscribed cube based on the marked arrow-shaped points, and expanding the minimum circumscribed cube in the directions of +/-X, + -Y and +/-Z by using the center of the minimum circumscribed cube, wherein the expansion coefficients in the directions of +/-X, + -Y and +/-Z are respectively alpha, beta and gamma; intercepting point clouds based on the expanded cube to obtain target point clouds; performing orthogonal projection on the target point cloud to generate an arrow image, converting point cloud coordinates of the target point cloud into image coordinates of the arrow image, and obtaining the target point cloud forming an arrow target based on a trained point cloud semantic segmentation model;
manufacturing a point cloud semantic segmentation data set based on arrow-shaped points marked with arrow targets, and performing deep learning training based on the point cloud semantic segmentation data set to obtain a point cloud semantic segmentation model;
converting the arrow point coordinates into image coordinates as labeling information corresponding to orthogonal projection, and making a training set;
performing thermodynamic diagram regression training based on a Convolutional Neural Network (CNN) model to obtain a key point regression model for extracting arrow point image coordinates in an arrow point image;
and the second module is used for generating an arrow image based on the target point cloud orthogonal projection, obtaining the image coordinates of arrow-shaped points in the arrow image based on the trained key point regression model, performing inverse orthogonal projection transformation on the arrow-shaped points to obtain the point cloud coordinates of the arrow-shaped points in the target point cloud, and extracting an arrow target based on the point cloud coordinates.
5. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 3 are implemented when the processor executes the program.
6. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811650011.9A CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811650011.9A CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858374A CN109858374A (en) | 2019-06-07 |
| CN109858374B true CN109858374B (en) | 2021-08-17 |
Family
ID=66893568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811650011.9A Active CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858374B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192311B (en) * | 2019-12-31 | 2022-05-17 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making |
| CN111210456B (en) * | 2019-12-31 | 2023-03-10 | 武汉中海庭数据技术有限公司 | High-precision direction arrow extraction method and system based on point cloud |
| CN111209826B (en) * | 2019-12-31 | 2022-05-27 | 武汉中海庭数据技术有限公司 | Semi-automatic point cloud extraction method and device for high-precision map guardrail |
| CN111652179B (en) * | 2020-06-15 | 2024-01-09 | 东风汽车股份有限公司 | Semantic high-precision map construction and positioning method based on point-line feature fusion laser |
| CN111932621B (en) * | 2020-08-07 | 2022-06-17 | 武汉中海庭数据技术有限公司 | Method and device for evaluating arrow extraction confidence |
| CN112258519B (en) * | 2020-10-12 | 2022-09-20 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for way-giving line of road in high-precision map making |
| CN113569652A (en) * | 2021-06-30 | 2021-10-29 | 惠州市德赛西威智能交通技术研究院有限公司 | Method for detecting short obstacles by automatic parking all-round looking camera |
| CN114120349B (en) * | 2022-01-10 | 2022-05-03 | 深圳市菁优智慧教育股份有限公司 | Test paper identification method and system based on deep learning |
| CN118587670A (en) * | 2024-06-06 | 2024-09-03 | 苏州柏川数据科技有限公司 | Method capable of quickly marking arrows on road surface point cloud |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
| CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
| CN108090423A (en) * | 2017-12-01 | 2018-05-29 | 上海工程技术大学 | A kind of depth detection method of license plate returned based on thermodynamic chart and key point |
| CN108319957A (en) * | 2018-02-09 | 2018-07-24 | 深圳市唯特视科技有限公司 | A kind of large-scale point cloud semantic segmentation method based on overtrick figure |
| CN108470159A (en) * | 2018-03-09 | 2018-08-31 | 腾讯科技（深圳）有限公司 | Lane line data processing method, device, computer equipment and storage medium |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9349056B2 (en) * | 2013-02-15 | 2016-05-24 | Gordon Peckover | Method of measuring road markings |
| CN103226833B (en) * | 2013-05-08 | 2015-08-05 | 清华大学 | A kind of point cloud data segmentation method based on three-dimensional laser radar |
| CN105260699B (en) * | 2015-09-10 | 2018-06-26 | 百度在线网络技术（北京）有限公司 | A kind of processing method and processing device of lane line data |
| CN105426861B (en) * | 2015-12-02 | 2019-05-21 | 百度在线网络技术（北京）有限公司 | Lane line determines method and device |
| CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Road barrier identification method and device |
| US10126141B2 (en) * | 2016-05-02 | 2018-11-13 | Google Llc | Systems and methods for using real-time imagery in navigation |
| CN108415032B (en) * | 2018-03-05 | 2021-06-25 | 中山大学 | Point cloud semantic map construction method based on deep learning and laser radar |
-
2018
- 2018-12-31 CN CN201811650011.9A patent/CN109858374B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
| CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
| CN108090423A (en) * | 2017-12-01 | 2018-05-29 | 上海工程技术大学 | A kind of depth detection method of license plate returned based on thermodynamic chart and key point |
| CN108319957A (en) * | 2018-02-09 | 2018-07-24 | 深圳市唯特视科技有限公司 | A kind of large-scale point cloud semantic segmentation method based on overtrick figure |
| CN108470159A (en) * | 2018-03-09 | 2018-08-31 | 腾讯科技（深圳）有限公司 | Lane line data processing method, device, computer equipment and storage medium |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
Non-Patent Citations (1)
| Title |
|---|
| SEGCloud: Semantic Segmentation of 3D Point Clouds;Lyne P. Tchapmi, 等;《2017 International Conference on 3D Vision (3DV)》;20180607;第1-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858374A (en) | 2019-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858374B (en) | Automatic extraction method and device for arrow mark lines in high-precision map making | |
| CN108388641B (en) | Traffic facility map generation method and system based on deep learning | |
| CN111192311B (en) | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making | |
| JP2022522385A (en) | Road sign recognition methods, map generation methods, and related products | |
| CN111160360B (en) | Image recognition method, device and system | |
| CN111221808A (en) | Unattended high-precision map quality inspection method and device | |
| CN116529784A (en) | Method and system for adding lidar data | |
| CN110599497A (en) | Drivable region segmentation method based on deep neural network | |
| CN114295139A (en) | Cooperative sensing positioning method and system | |
| EP4198901A1 (en) | Camera extrinsic parameter calibration method and apparatus | |
| CN117274388B (en) | Unsupervised three-dimensional visual positioning method and system based on visual text relation alignment | |
| CN113624223B (en) | Indoor parking lot map construction method and device | |
| WO2024002014A1 (en) | Traffic marking identification method and apparatus, computer device and storage medium | |
| CN116665003B (en) | Point cloud three-dimensional target detection method and device based on feature interaction and fusion | |
| CN109583312A (en) | Lane detection method, apparatus, equipment and storage medium | |
| CN113724387A (en) | Laser and camera fused map construction method | |
| CN112381876B (en) | Traffic sign marking method and device and computer equipment | |
| CN103218820A (en) | Camera calibration error compensation method based on multi-dimensional characteristics | |
| CN117079238A (en) | Road edge detection method, device, equipment and storage medium | |
| Du | Lane line detection and vehicle identification using monocular camera based on matlab | |
| CN112651986B (en) | Environment recognition method, recognition device, recognition system, electronic equipment and medium | |
| CN114386223A (en) | Real scene-based driving test simulator examination room model creation method | |
| Du et al. | Validation of vehicle detection and distance measurement method using virtual vehicle approach | |
| CN111340050B (en) | Map road full-factor feature extraction method and system | |
| CN115294186A (en) | Point cloud processing method, electronic device and program product |
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 |