High-precision map lane line processing method and device, electronic equipment and storage medium
By processing lane line data based on vehicle position and position information in high-precision map, the problem of occluded data interference in deep learning model training is solved, and the precise display and processing of visible lane line data in high-precision map is achieved.
Patent Information
- Application Number
- CN202510292034.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-12
- Publication Date
- 2025-06-17
AI Technical Summary
In the high-precision map generation method based on deep learning models, the prior art is difficult to effectively process the obscured lane line data in the high-precision map, resulting in inconsistent training input and truth value, affecting the convergence speed and accuracy of the model.
The lane line data set of the set distance range is obtained based on the position information of the vehicle, and converted it into a vehicle coordinate system based on the position information of the vehicle. Then, the roadside data and lane line data in the vehicle coordinate system are used to obtain the visible lane line data data set.
It realizes that without introducing additional errors, filtering invisible lane line data in the high-precision map, reproducing the blocked visible lane line data, and accurately displaying the visible lane line data in the high-precision map.
Smart Images
Figure CN120162393A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of map data processing, and particularly to a method, device, electronic device, and storage medium for processing lane lines in a high-precision map. Background Art
[0002] In the end-to-end high-precision map generation method based on a deep learning model, coordinate data of lane lines and roadside lines are obtained from the high-precision map according to vehicle positioning information, and using the vehicle pose information, the coordinate data of the lane lines and roadside lines obtained from the high-precision map are converted from the world coordinate system to the vehicle coordinate system.
[0003] To train an accurate deep learning model, related technologies use the coordinate data of high-precision map lane lines and roadside lines as training ground truths. Since there are other vehicles, static obstacles in the actual road or for other reasons, some lane lines in the road are invisible, and there are partially occluded data in the high-precision map. However, in the training process of the deep learning model based on the high-precision map as the training ground truth, the lane lines and roadside lines in the high-precision map are defaulted to be all visible, resulting in inconsistent training inputs and training ground truths. The partially occluded data cause great interference to the model during the training of the deep learning model, resulting in slow convergence and low accuracy of the deep learning model during training.
[0004] Therefore, how to reproduce the occluded data (occluded visible data) in the high-precision map, filter out interference data (invisible data), and accurately obtain the visible data (unoccluded visible data and occluded visible data) in the high-precision map is a difficult problem to be solved in the training process of the deep learning model based on the high-precision map. Summary of the Invention
[0005] To solve or partially solve the problems existing in the related technologies, this application provides a method, device, electronic device, and storage medium for processing lane lines in a high-precision map, which can filter out invisible data or non-lane line data in the high-precision map, reproduce the occluded visible lane line data in the high-precision map, and accurately display the visible lane line data in the high-precision map.
[0006] The first aspect of this application provides a method for processing lane lines in a high-precision map, and the method includes: Obtain a first lane line dataset and a first roadside line dataset within a set distance range according to the position information of the vehicle; Convert the first lane line dataset to a second lane line dataset in the vehicle coordinate system, and convert the first roadside line dataset to a second roadside line dataset in the vehicle coordinate system according to the pose information of the vehicle; Obtain the visible lane line data of the first lane line dataset according to the spatial positions of the roadside line data in the second roadside line dataset and the lane line data in the second lane line dataset in the vehicle coordinate system.
[0007] Preferably, the obtaining of the first lane line dataset and the first roadside line dataset within a set distance range according to the position information of the vehicle includes: Obtain the position coordinates of the vehicle according to the position information of the vehicle; Determine the set distance range with the position coordinates of the vehicle as the center point and a set distance, and obtain the first lane line dataset and the first roadside line dataset within the set distance range from the high-precision map.
[0008] Preferably, the converting of the first lane line dataset into the second lane line dataset in the vehicle coordinate system and the converting of the first roadside line dataset into the second roadside line dataset in the vehicle coordinate system according to the pose information of the vehicle include: Taking the first lane line dataset and the first roadside line dataset as data in the world coordinate system, convert the first lane line dataset into the second lane line dataset in the vehicle coordinate system and convert the first roadside line dataset into the second roadside line dataset in the vehicle coordinate system according to the pose information of the vehicle.
[0009] Preferably, the obtaining of the visible lane line data of the first lane line dataset according to the spatial positions of the roadside line data in the second roadside line dataset and the lane line data in the second lane line dataset in the vehicle coordinate system includes: Generate a first set of vertical line segments and a second set of vertical line segments with a set length and perpendicular to the X-axis of the vehicle coordinate system at the set distance in the positive direction of the X-axis of the vehicle coordinate system at a set interval distance, wherein the first set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system and the second set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system; Generate a third set of vertical line segments and a fourth set of vertical line segments with the set length and perpendicular to the X-axis of the vehicle coordinate system at the set distance in the negative direction of the X-axis of the vehicle coordinate system at the set interval distance, wherein the third set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system and the fourth set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system; If there are no intersection points between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments and the fourth set of vertical line segments, obtain the second lane line data in the second lane line dataset that intersects with the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments and the fourth set of vertical line segments; Obtain the first lane line data corresponding to the second lane line data in the first lane line dataset, and use the first lane line data as the visible lane line data in the first lane line dataset.
[0010] Preferably, the method further includes: If the roadside line data in the second roadside line dataset has intersections with the perpendicular line segments of the first group, the second group, the third group, and the fourth group of perpendicular line segments, obtain the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; Generate a fifth group of perpendicular line segments perpendicular to the X-axis of the vehicle coordinate system through the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; Obtain the third lane line data in the second lane line dataset that intersects with the perpendicular line segments of the fifth group of perpendicular line segments; Obtain the fourth lane line data corresponding to the third lane line data in the first lane line dataset, and use the fourth lane line data as the visible lane line data in the first lane line dataset.
[0011] Preferably, the method further includes: performing duplicate removal processing on the visible lane line data in the first lane line dataset to obtain the visible lane line data after duplicate removal processing in the first lane line dataset.
[0012] A second aspect of the present application provides a high-precision map lane line processing device, and the device includes: An acquisition module, configured to acquire a first lane line dataset and a first roadside line dataset within a set distance range according to the position information of the vehicle; A conversion module, configured to convert the first lane line dataset acquired by the acquisition module into a second lane line dataset in the vehicle coordinate system according to the pose information of the vehicle, and convert the first roadside line dataset acquired by the acquisition module into a second roadside line dataset in the vehicle coordinate system; A screening module, configured to acquire the visible lane line data of the first lane line dataset according to the spatial positions of the roadside line data in the second roadside line dataset and the lane line data in the second lane line dataset converted by the conversion module in the vehicle coordinate system.
[0013] Preferably, the device further includes: A duplicate removal module, configured to perform duplicate removal processing on the visible lane line data in the first lane line dataset acquired by the screening module to obtain the visible lane line data after duplicate removal processing in the first lane line dataset.
[0014] A third aspect of the present application provides an electronic device, including: A processor; and A memory stores executable code thereon, which, when executed by the processor, causes the processor to execute the method as described above.
[0015] The fourth aspect of the present application provides a computer-readable storage medium storing executable code thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method as described above.
[0016] The technical solution provided by the present application may include the following beneficial effects: The technical solution of the present application obtains a first lane line data set and a first roadside line data set within a set distance range according to the position information of the vehicle; according to the pose information of the vehicle, converts the first lane line data set into a second lane line data set in the vehicle coordinate system, and converts the first roadside line data set into a second roadside line data set in the vehicle coordinate system; obtains visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system; can, based on the obtained first lane line data set and first roadside line data set, without other additional reference data and without introducing other errors, filter invisible lane line data or non-lane line data in the high-precision map, reproduce the visible lane line data occluded in the high-precision map, and accurately display the visible lane line data in the high-precision map.
[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] By describing the exemplary embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features and advantages of the present application will become more obvious, wherein, in the exemplary embodiments of the present application, the same reference numerals generally represent the same components.
[0019] Figure 1 is a schematic flowchart of a method for processing lane lines in a high-precision map shown in an embodiment of the present application; Figure 2 is another schematic flowchart of a method for processing lane lines in a high-precision map shown in an embodiment of the present application; Figure 3 is a schematic structural diagram of a device for processing lane lines in a high-precision map shown in an embodiment of the present application; Figure 4 is another schematic structural diagram of a device for processing lane lines in a high-precision map shown in an embodiment of the present application; Figure 5 is a schematic structural diagram of an electronic device shown in an embodiment of the present application; Figure 6It is a schematic diagram of the scenario of the high-precision map lane line processing method shown in the embodiments of the present application. Detailed implementation manners
[0020] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0021] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "said", and "the" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
[0022] It should be understood that although the terms "first", "second", "third", etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.
[0023] The embodiments of the present application provide a high-precision map lane line processing method, which can filter invisible lane line data or non-lane line data in the high-precision map, reproduce the visible lane line data occluded in the high-precision map, and accurately display the visible lane line data in the high-precision map.
[0024] The technical solutions of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.
[0025] Figure 1 It is a schematic flowchart of the high-precision map lane line processing method shown in the embodiments of the present application.
[0026] See Figure 1 , a high-precision map lane line processing method, including: Step 101, according to the position information of the vehicle, obtain a first lane line data set and a first roadside line data set within a set distance range.
[0027] In one embodiment, the position information of the vehicle at the current moment can be obtained, where the position information of the vehicle at the current moment can be represented by the coordinates of the vehicle at the current moment; taking the coordinates of the vehicle at the current moment as the center point, road data within a set distance range around the coordinates of the vehicle at the current moment is obtained from the high-precision map, and the road data includes, but is not limited to, the first lane line data set and the first roadside line data set.
[0028] Step 102: According to the pose information of the vehicle, convert the first lane line data set into a second lane line data set in the vehicle coordinate system, and convert the first roadside line data set into a second roadside line data set in the vehicle coordinate system.
[0029] In one embodiment, the pose information of the vehicle at the current moment can be obtained; according to the pose information of the vehicle at the current moment, the first lane line data set obtained from the high-precision map is converted into a second lane line data set in the vehicle coordinate system; according to the pose information of the vehicle at the current moment, the first roadside line data set obtained from the high-precision map is converted into a second roadside line data set in the vehicle coordinate system.
[0030] Step 103: According to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system, obtain the visible lane line data of the first lane line data set.
[0031] In one embodiment, the lane line data in the second lane line data set within the range of the roadside line data in the second roadside line data set can be obtained according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system; the lane line data of the first lane line data set corresponding to the lane line data in the second lane line data set within the range of the roadside line data in the second roadside line data set is used as the visible lane line data of the first lane line data set, and the visible lane line data includes unobstructed visible lane line data and obstructed visible lane line data.
[0032] The high-precision map lane line processing method according to the embodiments of the present application obtains a first lane line data set and a first roadside line data set within a set distance range according to the position information of the vehicle; converts the first lane line data set into a second lane line data set in the vehicle coordinate system and converts the first roadside line data set into a second roadside line data set in the vehicle coordinate system according to the pose information of the vehicle; obtains visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system; can, based on the obtained first lane line data set and first roadside line data set, without other additional reference data and without introducing other errors, filter out invisible lane line data or non-lane line data in the high-precision map, reproduce the visible lane line data blocked in the high-precision map, and accurately obtain and display the visible lane line data in the high-precision map.
[0033] Figure 2 It is another process schematic diagram of the high-precision map lane line processing method shown in the embodiments of the present application. Figure 2 Relative to Figure 1 The solution of the present application is described in more detail.
[0034] See Figure 2 , a high-precision map lane line processing method, including: Step 201, obtain the position coordinates and pose information of the vehicle.
[0035] In one embodiment, the position information and pose information of the vehicle at the current moment can be obtained according to the in-vehicle intelligent device or roadside device of the vehicle.
[0036] In one embodiment, the in-vehicle intelligent device can be an in-vehicle positioning device, for example, but not limited to, an in-vehicle GPS (Global Positioning System), and the position information and pose information of the vehicle at the current moment are obtained through the in-vehicle positioning device.
[0037] In one embodiment, the roadside device can be a roadside unit deployed on the roadside. The roadside unit includes a roadside camera, and the vehicle can be positioned according to the image of the roadside camera to obtain the position information and pose information of the vehicle at the current moment.
[0038] Step 202, obtain a first lane line data set and a first roadside line data set within a set distance range according to the position information of the vehicle.
[0039] In one embodiment, according to the position information of the vehicle, the position coordinates L of the vehicle can be obtained car ; Determine the position coordinates L of the vehicle carTaking the center point as the center, a set distance range with a set distance is set, and a first lane line data set and a first roadside line data set within the set distance range are obtained from the high-precision map.
[0040] In one embodiment, the set distance can be determined according to the required distance of the lane line data for the vehicle during automatic driving decision-making of the vehicle; the set distance can be set to 50 - 120 meters.
[0041] In one embodiment, according to the position coordinate L of the vehicle car , a first lane line data set and a first roadside line data set within the set distance range with a set distance of 100 meters from the position coordinate L of the vehicle are obtained from the high-precision map. car
[0042] Step 203: According to the pose information of the vehicle, convert the first lane line data set into a second lane line data set in the vehicle coordinate system, and convert the first roadside line data set into a second roadside line data set in the vehicle coordinate system.
[0043] In one embodiment, taking the first lane line data set and the first roadside line data set as data in the world coordinate system, according to the pose information of the vehicle, convert the first lane line data set into a second lane line data set in the vehicle coordinate system, and convert the first roadside line data set into a second roadside line data set in the vehicle coordinate system.
[0044] In one embodiment, the pose information of the vehicle at the current moment can be represented by the pose data P of the vehicle at the current moment car . According to the pose data P of the vehicle car , taking the first lane line data set as data in the world coordinate system, convert the first lane line data set into a second lane line data set in the vehicle coordinate system; according to the pose data P of the vehicle car , taking the first roadside line data set as data in the world coordinate system, convert the first roadside line data set into a second roadside line data set in the vehicle coordinate system.
[0045] Step 204: Obtain the visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system.
[0046] In one embodiment, the vehicle coordinate system is a special moving coordinate system used to describe the movement of the vehicle, and can also be called the vehicle body coordinate system; its origin coincides with the vehicle's center of mass. When the vehicle is stationary on a horizontal road surface, the X-axis is parallel to the ground and points in the vehicle's forward direction, the Z-axis passes through the vehicle's center of mass and points upward, and the Y-axis points to the left of the vehicle.
[0047] In one embodiment, a first set of vertical line segments and a second set of vertical line segments that are perpendicular to the X-axis of the vehicle coordinate system and have a set length can be generated at a set distance in the positive direction of the X-axis of the vehicle coordinate system at a set interval distance, wherein the first set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the second set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system.
[0048] In one embodiment, a third set of vertical line segments and a fourth set of vertical line segments that are perpendicular to the X-axis of the vehicle coordinate system and have a set length can be generated at a set distance in the negative direction of the X-axis of the vehicle coordinate system at a set interval distance, wherein the third set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the fourth set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system.
[0049] In one embodiment, it is possible to determine whether there are intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments; if there are no intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the second lane line data in the second lane line dataset that intersects the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments; obtain the first lane line data corresponding to the second lane line data in the first lane line dataset, and use the first lane line data as the visible lane line data in the first lane line dataset.
[0050] In one embodiment, if there are intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; generate a fifth set of vertical line segments perpendicular to the X-axis of the vehicle coordinate system through the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; obtain the third lane line data in the second lane line dataset that intersects the vertical line segments of the fifth set of vertical line segments; obtain the fourth lane line data corresponding to the third lane line data in the first lane line dataset, and use the fourth lane line data as the visible lane line data in the first lane line dataset.
[0051] In one embodiment, the set interval distance can be set according to the map accuracy of the high-precision map; wherein, the set interval distance can be 0.05 meters - 0.2 meters.
[0052] In one embodiment, the lane line width can be obtained according to the lane line data in the first lane line dataset, and the set length can be set according to the lane line width; wherein, the set length can be an integer multiple of the lane line width.
[0053] In one embodiment, the road width can be obtained according to the roadside line data in the first roadside line dataset, and the set length can be set according to the road width; wherein, the road width can be set as the set length.
[0054] In one embodiment, the set length can be 14 meters to 40 meters.
[0055] In a specific embodiment, a first set of vertical line segments and a second set of vertical line segments with a set length of 15 meters and perpendicular to the X-axis of the vehicle coordinate system can be generated at intervals of 0.1 meters within a set distance of 0 - 100 meters in the positive direction of the X-axis of the vehicle coordinate system. Among them, the first set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the second set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system.
[0056] In a set distance of 0 - (-100 meters) in the negative direction of the X-axis of the vehicle coordinate system, a third set of vertical line segments and a fourth set of vertical line segments with a set length of 15 meters and perpendicular to the X-axis of the vehicle coordinate system are generated at intervals of 0.1 meters. Among them, the third set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the fourth set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system.
[0057] Determine whether there are intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments; if there are no intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the second lane line data in the second lane line dataset that intersects with the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments; obtain the first lane line data corresponding to the second lane line data in the first lane line dataset, and use the first lane line data as the visible lane line data in the first lane line dataset.
[0058] If there are intersections between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; generate a fifth set of vertical line segments perpendicular to the X-axis of the vehicle coordinate system through the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; obtain the third lane line data in the second lane line dataset that intersects with the vertical line segments of the fifth set of vertical line segments; obtain the fourth lane line data corresponding to the third lane line data in the first lane line dataset, and use the fourth lane line data as the visible lane line data in the first lane line dataset.
[0059] Step 205: Perform duplicate removal processing on the visible lane line data in the first lane line dataset to obtain the visible lane line data after duplicate removal processing in the first lane line dataset.
[0060] In one embodiment, based on the visible lane line data in the first lane line dataset, the lane line ID attribute of the visible lane line data can be obtained. The lane line ID attribute is used to identify and distinguish different lane lines. According to the lane line ID attribute of the visible lane line data, duplicate removal processing is performed on the visible lane line data to obtain the visible lane line data after duplicate removal processing in the first lane line dataset.
[0061] Figure 6 It is a schematic diagram of the scenario of the high-precision map lane line processing method shown in the embodiments of the present application.
[0062] As Figure 6 shown, the line 601 is the edge of the staggered green belt or other roadside lines recognized as lines during the machine recognition process, which should be displayed as invisible data or non-lane line data in the high-precision map; the line 602 is the visible lane line data of the current forward road; the line 603 is the occluded visible lane line data of the current forward road that should be displayed as visible lane line data in the high-precision map. In the related art, all the invisible line data or non-lane line data of the line 601 and the occluded visible lane line data of the line 603 are defaulted to invisible data; or, all the invisible line data or non-lane line data of the line 601, the visible lane line data of the line 602, and the occluded visible lane line data of the line 603 are defaulted to visible lane line data. The high-precision map lane line processing method of the embodiments of the present application obtains the first lane line dataset and the first roadside line dataset within a set distance range according to the position information of the vehicle; according to the pose information of the vehicle, the first lane line dataset is converted into the second lane line dataset in the vehicle coordinate system, and the first roadside line dataset is converted into the second roadside line dataset in the vehicle coordinate system; according to the spatial positions of the roadside line data in the second roadside line dataset and the lane line data in the second lane line dataset in the vehicle coordinate system, the visible lane line data of the first lane line dataset is obtained; based on the obtained first lane line dataset and the first roadside line dataset, without other additional reference data, it can filter the invisible data or non-lane line data represented by the line 601 in the high-precision map, reproduce the occluded visible lane line data of the line 603, and accurately obtain and display the visible lane line data (the visible lane line data of the line 602 and the occluded visible lane line data of the line 603) in the high-precision map.
[0063] Furthermore, for the high-precision map lane line processing method of the embodiments of the present application, duplicate removal processing is performed on the visible lane line data in the first lane line dataset to obtain the visible lane line data after duplicate removal processing in the first lane line dataset, which can further filter the obtained duplicate lane line data and accurately obtain the visible lane line data in the high-precision map.
[0064] Corresponding to the foregoing embodiments of the application function implementation method, the present application also provides a high-precision map lane line processing device, an electronic device, and corresponding embodiments.
[0065] Figure 3 It is a schematic structural diagram of the high-precision map lane line processing device shown in the embodiments of the present application.
[0066] Refer to Figure 3 , a high-precision map lane line processing device, including an acquisition module 301, a conversion module 302, and a screening module 303.
[0067] The acquisition module 301 is configured to acquire a first lane line data set and a first roadside line data set within a set distance range according to the position information of the vehicle.
[0068] In one embodiment, the acquisition module 301 can acquire the position information of the vehicle at the current moment, where the position information of the vehicle at the current moment can be represented by the coordinates of the vehicle at the current moment; taking the coordinates of the vehicle at the current moment as the center point, road data within a set distance range around the coordinates of the vehicle at the current moment is acquired from the high-precision map, and the road data includes, but is not limited to, the first lane line data set and the first roadside line data set.
[0069] The conversion module 302 is configured to convert the first lane line data set acquired by the acquisition module 301 into a second lane line data set in the vehicle coordinate system according to the pose information of the vehicle, and convert the first roadside line data set acquired by the acquisition module 301 into a second roadside line data set in the vehicle coordinate system.
[0070] In one embodiment, the conversion module 302 can acquire the pose information of the vehicle at the current moment; according to the pose information of the vehicle at the current moment, convert the first lane line data set acquired by the acquisition module 301 from the high-precision map into a second lane line data set in the vehicle coordinate system; according to the pose information of the vehicle at the current moment, convert the first roadside line data set acquired by the acquisition module 301 from the high-precision map into a second roadside line data set in the vehicle coordinate system.
[0071] The screening module 303 is configured to acquire visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set converted by the conversion module 302 in the vehicle coordinate system.
[0072] In one embodiment, the screening module 303 may obtain the lane line data within the roadside line data range in the second roadside line dataset from the spatial positions of the roadside line data in the second roadside line dataset converted by the conversion module 302 and the spatial positions of the lane line data in the second lane line dataset converted by the conversion module 302 in the vehicle coordinate system; and use the lane line data in the first lane line dataset corresponding to the lane line data within the roadside line data range in the second roadside line dataset in the second lane line dataset as the visible lane line data of the first lane line dataset.
[0073] The technical solution of the embodiment of the present application obtains the first lane line dataset and the first roadside line dataset within a set distance range according to the position information of the vehicle; converts the first lane line dataset into the second lane line dataset in the vehicle coordinate system and converts the first roadside line dataset into the second roadside line dataset in the vehicle coordinate system according to the pose information of the vehicle; and obtains the visible lane line data of the first lane line dataset according to the spatial positions of the roadside line data in the second roadside line dataset and the lane line data in the second lane line dataset in the vehicle coordinate system. Without other additional reference data and without introducing other errors, it can filter out the invisible lane line data or non-lane line data in the high-precision map, reproduce the visible lane line data blocked in the high-precision map, and accurately obtain and display the visible lane line data in the high-precision map.
[0074] Figure 4 It is another structural schematic diagram of the high-precision map lane line processing device shown in the embodiment of the present application.
[0075] See Figure 4 , a high-precision map lane line processing device, including an acquisition module 301, a conversion module 302, a screening module 303, and a duplicate removal module 401.
[0076] The acquisition module 301 is used to obtain the position coordinates of the vehicle according to the position information of the vehicle; determine a set distance range with the position coordinates of the vehicle as the center point and a set distance, and obtain the first lane line dataset and the first roadside line dataset within the set distance range.
[0077] The conversion module 302 is used to use the first lane line dataset and the first roadside line dataset as the data in the world coordinate system, and convert the first lane line dataset into the second lane line dataset in the vehicle coordinate system and convert the first roadside line dataset into the second roadside line dataset in the vehicle coordinate system according to the pose information of the vehicle.
[0078] The screening module 303 is configured to generate a first set of vertical line segments and a second set of vertical line segments that are perpendicular to the X-axis of the vehicle coordinate system, have a set length, and are spaced at a set interval distance at a set distance in the positive direction of the X-axis of the vehicle coordinate system. Among them, the first set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the second set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system; at a set distance in the negative direction of the X-axis of the vehicle coordinate system, generate a third set of vertical line segments and a fourth set of vertical line segments that are perpendicular to the X-axis of the vehicle coordinate system, have a set length, and are spaced at a set interval distance. Among them, the third set of vertical line segments faces the positive direction of the Y-axis of the vehicle coordinate system, and the fourth set of vertical line segments faces the negative direction of the Y-axis of the vehicle coordinate system; if there is no intersection between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the second lane line data in the second lane line dataset that intersects the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments; obtain the first lane line data in the first lane line dataset corresponding to the second lane line data, and use the first lane line data as the visible lane line data in the first lane line dataset.
[0079] In one embodiment, the screening module 303 is further configured to, if there is an intersection between the roadside line data in the second roadside line dataset and the vertical line segments of the first set of vertical line segments, the second set of vertical line segments, the third set of vertical line segments, and the fourth set of vertical line segments, then obtain the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; generate a fifth set of vertical line segments perpendicular to the X-axis of the vehicle coordinate system through the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; obtain the third lane line data in the second lane line dataset that intersects the vertical line segments of the fifth set of vertical line segments; obtain the fourth lane line data in the first lane line dataset corresponding to the third lane line data, and use the fourth lane line data as the visible lane line data in the first lane line dataset.
[0080] The duplicate removal module 401 is configured to perform duplicate removal processing on the visible lane line data in the first lane line dataset obtained by the screening module 303 to obtain the visible lane line data after duplicate removal processing in the first lane line dataset.
[0081] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0082] Figure 5 It is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
[0083] See Figure 5 , the electronic device 1000 includes a memory 1010 and a processor 1020.
[0084] The processor 1020 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0085] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, the ROM may store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a read-write storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even when the computer is powered off. In some embodiments, the permanent storage device uses a mass storage device (such as a magnetic or optical disk, flash memory) as the permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. The system memory may store some or all of the instructions and data required by the processor during operation. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and magnetic disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a removable storage device that is readable and / or writable, such as a compact disc (CD), read-only digital versatile disc (such as DVD-ROM, dual-layer DVD-ROM), read-only Blu-ray disc, super density disc, flash memory card (such as SD card, min SD card, Micro-SD card, etc.), magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and instantaneous electronic signals transmitted wirelessly or wired.
[0086] An executable code is stored on the memory 1010, and when the executable code is processed by the processor 1020, it may cause the processor 1020 to execute some or all of the methods described above.
[0087] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for performing some or all of the steps in the above method of the present application.
[0088] Alternatively, the present application can also be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium), on which executable code (or a computer program or computer instruction code) is stored. When the executable code (or the computer program or computer instruction code) is executed by a processor of an electronic device (or a server, etc.), the processor is caused to execute some or all of the steps of the above method according to the present application.
[0089] The embodiments of the present application have been described above. The above description is exemplary and not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, the practical application or the improvement of the technology in the market, or to enable other ordinary skill in the art in the technical field to understand the disclosed embodiments.
Claims
1. A method for processing lane lines in a high-precision map, characterized in that: include: According to the position information of the vehicle, a first lane line dataset and a first roadside line dataset within a set distance range are obtained; According to the position information of the vehicle, converting the first lane line dataset into a second lane line dataset of the vehicle coordinate system, and converting the first roadside line dataset into a second roadside line dataset of the vehicle coordinate system; Obtain visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system.
2. The method according to claim 1, characterized in that The step of acquiring a first lane line dataset and a first roadside line dataset within a set distance range according to the position information of the vehicle includes: Acquiring the position coordinates of the vehicle according to the position information of the vehicle; Determine the set distance range with the position coordinates of the vehicle as the center point and the set distance, and obtain the first lane line data set and the first roadside line data set in the set distance range from the high-precision map.
3. The method according to claim 1, characterized in that: The method of converting the first lane line dataset into a second lane line dataset of a vehicle coordinate system according to the position information of the vehicle, and converting the first roadside line dataset into a second roadside line dataset of the vehicle coordinate system, comprises: Taking the first lane line dataset and the first roadside line dataset as data of the world coordinate system, according to the posture information of the vehicle, the first lane line dataset is converted into a second lane line dataset of the vehicle coordinate system, and the first roadside line dataset is converted into a second roadside line dataset of the vehicle coordinate system.
4. The method according to claim 2, characterized in that: The acquiring, according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set in the vehicle coordinate system, the visible lane line data of the first lane line data set comprises: At the set distance in the positive direction of the vehicle coordinate system X-axis, a first group of vertical line segments and a second group of vertical line segments of a set length perpendicular to the vehicle coordinate system X-axis are generated at a set interval distance, wherein the first group of vertical line segments faces the positive direction of the vehicle coordinate system Y-axis, and the second group of vertical line segments faces the negative direction of the vehicle coordinate system Y-axis; At the set distance in the negative direction of the X-axis of the vehicle coordinate system, a third group of vertical line segments and a fourth group of vertical line segments of the set length perpendicular to the X-axis of the vehicle coordinate system are generated at the set interval distance, wherein the third group of vertical line segments face the positive direction of the Y-axis of the vehicle coordinate system, and the fourth group of vertical line segments face the negative direction of the Y-axis of the vehicle coordinate system; If the roadside line data in the second roadside line data set has no intersection with the vertical line segments of the first group of vertical line segments, the second group of vertical line segments, the third group of vertical line segments, and the fourth group of vertical line segments, then obtaining the second lane line data in the second lane line data set that intersects with the vertical line segments of the first group of vertical line segments, the second group of vertical line segments, the third group of vertical line segments, and the fourth group of vertical line segments; First lane line data corresponding to the second lane line data in the first lane line data set is obtained, and the first lane line data is used as visible lane line data in the first lane line data set.
5. The method according to claim 4, characterized in that The method further comprises: If the roadside line data in the second roadside line data set have intersections with the vertical line segments of the first group of vertical line segments, the second group of vertical line segments, the third group of vertical line segments and the fourth group of vertical line segments, then obtaining the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; Generating a fifth set of vertical line segments perpendicular to the X-axis of the vehicle coordinate system through the intersection point with the smallest distance from the X-axis of the vehicle coordinate system; Acquire third lane line data in the second lane line data set that intersects with the vertical line segments of the fifth group of vertical line segments; Acquire fourth lane line data corresponding to the third lane line data in the first lane line data set, and use the fourth lane line data as visible lane line data in the first lane line data set.
6. The method according to any one of claims 1 to 5, characterized in that The method further includes: performing deduplication processing on the visible lane line data in the first lane line data set to obtain the deduplication-processed visible lane line data in the first lane line data set.
7. A high-precision map lane line processing device, characterized in that: include: An acquisition module, used for acquiring a first lane line data set and a first roadside line data set within a set distance range according to the position information of the vehicle; a conversion module, configured to convert the first lane line data set acquired by the acquisition module into a second lane line data set of a vehicle coordinate system, and to convert the first roadside line data set acquired by the acquisition module into a second roadside line data set of the vehicle coordinate system according to the posture information of the vehicle; The screening module is used to obtain the visible lane line data of the first lane line data set according to the spatial positions of the roadside line data in the second roadside line data set and the lane line data in the second lane line data set converted by the conversion module in the vehicle coordinate system.
8. The device according to claim 7, characterized in that The device also includes: A deduplication module is used to perform deduplication processing on the visible lane line data in the first lane line data set acquired by the screening module to obtain the visible lane line data after deduplication processing in the first lane line data set.
9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 6.