Map data processing method, device and equipment and storage medium

Abstract

The invention relates to a map data processing method and device, equipment and a storage medium. The method comprises the following steps: acquiring a task box generated according to lane line data of a target road and driving track data corresponding to the task box; intercepting data intersected with the task box in the driving track data, and taking the data as intersection data; selecting a plurality of set points from the intersection data; projecting the plurality of set points to one side edge, parallel to the driving direction, of the task box to obtain a plurality of projection points; calculating an accumulated distance between every two adjacent projection points; and judging whether the accumulated distance and the length of the side edge, parallel to the driving direction, of the task frame meet a set relation or not, and using intersection data meeting the set relation to generate map data of the target road. And whether the data acquisition requirement is met is judged by combining the driving track, so that the integrity and accuracy of map data are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a map data processing method, device, equipment and storage medium. Background Art

[0002] With the development of intelligent networking of automobiles, the development of autonomous driving is becoming more and more mature. However, the development of autonomous driving technology is inseparable from sensors and high-precision maps. Among them, high-precision maps can assist unmanned vehicles in achieving high-precision positioning, provide assistance for perception and supplement a large amount of prior information, and provide lane-level network structure and road attribute information for planning and decision-making. Therefore, high-precision maps are particularly important for autonomous driving systems.

[0003] In related technologies, the lane lines of the target road are generally made into a polygonal task box that conforms to the map standard, and then the polygonal task box is sent to the autonomous driving vehicle. When the autonomous driving vehicle determines that it has entered the range of the polygonal task box, it starts to collect map data related to the target road. Then, by comparing the length of the autonomous driving vehicle's driving track with the length of one side of the polygonal task box parallel to the driving direction, if the length of the vehicle's driving track meets the requirements, it is considered that the collected map data can cover the range of the polygonal task box, and the map data can be used to make high-precision maps.

[0004] However, due to the various possibilities of the driving trajectory of an autonomous driving vehicle, such as parking, steering, U-turns, and delays in the start of collection, even if the length of the driving trajectory exceeds the length of one side of the polygonal task box parallel to the driving direction, it may actually only cover a portion of the polygonal task box, making the collected map data of the target road incomplete. Or when there is a delay in the end of collection, too much data will be collected, resulting in a waste of resources. Summary of the invention

[0005] In order to solve or partially solve the problems existing in the related art, the present application provides a map data processing method, device, equipment and storage medium, which improves the integrity and accuracy of map data by comparing the length of the vehicle's driving trajectory with the length of one side of the task box parallel to the driving direction, and combining the driving trajectory to determine whether the data collection requirements are met.

[0006] The first aspect of the present application provides a map data processing method, comprising: Acquire a task frame generated according to lane line data of a target road, and driving trajectory data corresponding to the task frame; intercepting data intersecting with the task frame from the driving trajectory data and using the data as intersection data; selecting a plurality of set points from the intersection data; Projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points; Sort the plurality of projection points according to the direction of travel of the lane line, and calculate the cumulative distance between adjacent projection points; It is determined whether the accumulated distance and the length of a side of the task frame parallel to the driving direction satisfy a set relationship, and the intersection data satisfying the set relationship is used to generate map data of the target road.

[0007] As an optional embodiment, the obtaining of a task frame generated according to lane line data of a target road includes: Obtain lane line data of the target road; Dividing the lane line data of the target road into a plurality of lane line segment data; The plurality of lane line segment data are subjected to polygon processing to generate a polygonal task frame.

[0008] As an optional embodiment, the obtaining of the driving trajectory data corresponding to the task box includes: Acquire first trajectory data of the vehicle traveling on the target road by a first acquisition device; Acquire second trajectory data of the vehicle traveling on the target road by a second acquisition device; Obtaining third trajectory data of the vehicle traveling on the target road by a third acquisition device; The first trajectory data, the second trajectory data and the third trajectory data of the vehicle traveling on the target road at the same time are fused to obtain fused trajectory data, and the fused trajectory data is used as the driving trajectory data corresponding to the task box.

[0009] As an optional embodiment, the plurality of set points include at least two of a maximum horizontal coordinate collection point, a minimum horizontal coordinate collection point, a maximum vertical coordinate collection point and a minimum vertical coordinate collection point.

[0010] As an optional embodiment, projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points includes: Dividing a side of the task frame parallel to the driving direction into a plurality of projection line segments; Determine the projection line segment corresponding to each of the set points; Each of the set points is projected onto a corresponding projection line segment to obtain a plurality of projection points.

[0011] As an optional embodiment, projecting each of the set points onto a corresponding projection line segment to obtain a plurality of projection points includes: If the angle between the projection line segment connected to the side edge of the task box perpendicular to the driving direction and the side edge is an obtuse angle, the projection line segment is extended in the extension direction of the projection line segment, and the set point corresponding to the projection line segment is projected onto its extended line segment to obtain the projection point.

[0012] As an optional embodiment, the setting relationship is: The ratio of the accumulated distance to the length of one side of the task box parallel to the driving direction is not less than a first threshold, or the difference between the length of one side of the task box parallel to the driving direction and the accumulated distance is not greater than a second threshold.

[0013] A second aspect of the present application provides a map data processing device, comprising: An acquisition module, used to acquire a task frame generated according to lane line data of a target road, and driving trajectory data corresponding to the task frame; An interception module, used for intercepting data intersecting with the task frame in the driving trajectory data and using it as intersection data; A selection module, used for selecting a plurality of set points from the intersection data; A projection module, used for projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points; A calculation module, used to sort the plurality of projection points according to the direction of travel of the lane line, and calculate the cumulative distance between adjacent projection points; The judgment module is used to judge whether the accumulated distance and the length of a side of the task frame parallel to the driving direction satisfy a set relationship, and use the intersection data satisfying the set relationship to generate the map data of the target road.

[0014] A third aspect of the present application provides an electronic device, including: Processor; and The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0015] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0016] The technical solution provided by this application may have the following beneficial effects: The present application first obtains a task frame generated by the lane line data of the target road, and the driving trajectory data corresponding to the task frame; then intercepts the data in the driving trajectory data that intersects with the task frame, and uses it as the intersection data. The present application only intercepts the data in the driving trajectory data that intersects with the task frame, which can avoid the problem of too much collected data caused by delays in the end of collection, etc.; then selects multiple set points from the intersection data, and projects the multiple set points to one side of the task frame parallel to the driving direction to obtain multiple projection points. By projecting the set points on one side of the task frame parallel to the driving direction, the driving collection points are converted into points on the lane line. This can avoid the calculation error of the accumulated length of the driving collection points. In addition, since the travel direction of the lane line is not necessarily a straight line, it may be inclined, curved, etc., and the projection points are sorted according to the travel direction of the lane line. After that, the adjacent projection points will be connected to form a linear line that is basically consistent with the direction of travel of the lane line. The accumulated distance between adjacent projection points is equivalent to the length of the lane line covered by the actual driving trajectory, which can reduce the accumulated calculation error of the driving trajectory; then the multiple projection points are sorted according to the direction of travel of the lane line, and the accumulated distance between each adjacent projection point is calculated; finally, it is determined whether the accumulated distance and the length of one side of the task box parallel to the driving direction meet the set relationship, and the intersection data that meets the set relationship is used to generate the map data of the target road. In this way, by determining whether the accumulated distance and the length of one side of the task box parallel to the driving direction meet the set relationship, even if the autonomous driving vehicle has problems such as turning, turning around, parking, and delay in the start of collection, the intersection data for generating map data can be filtered out, and the generated map data is more complete and more accurate.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0019] Figure 1 It is a schematic diagram showing that the collected map data of the target road is incomplete as shown in the embodiment of the present application; Figure 2 is a flowchart of a map data processing method shown in an embodiment of the present application; Figure 3 is a schematic diagram of the accumulated distances between adjacent projection points shown in an embodiment of the present application; Figure 4 is a schematic diagram of a task box and intersection data shown in an embodiment of the present application; Figure 5 is a structural schematic diagram of a map data processing device shown in an embodiment of the present application; Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[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 accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described 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 this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0022] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this 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 this 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 as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0023] In related technologies, the lane lines of the target road are generally made into a polygonal task box that conforms to the map standard, and then the polygonal task box is sent to the autonomous driving vehicle. When the autonomous driving vehicle determines that it has entered the range of the polygonal task box, it starts to collect map data related to the target road. Then, by comparing the length of the autonomous driving vehicle's driving track with the length of one side of the polygonal task box parallel to the driving direction, if the length of the vehicle's driving track meets the requirements, it is considered that the collected map data can cover the range of the polygonal task box, and the map data can be used to make high-precision maps.

[0024] However, due to the various possibilities of the driving trajectory of an autonomous driving vehicle, such as parking, steering, U-turns, and delays in the start of collection, even if the length of the driving trajectory exceeds the length of one side of the polygonal task box parallel to the driving direction, it may actually only cover a portion of the polygonal task box, making the collected map data of the target road incomplete. Or when there is a delay in the end of collection, too much data will be collected, resulting in a waste of resources.

[0025] See also Figure 1 The red line frame is the task frame, and the black line frame is the driving track. The length of the driving track has reached or even exceeded the length of the task frame. However, due to the U-turn in the task frame, although the length of the driving track has met the requirements, the U-turn collection task has not actually been completed. Therefore, the above solution cannot correctly verify whether the collection task has been completed.

[0026] In response to the above problems, an embodiment of the present application provides a map data processing method, which improves the integrity and accuracy of map data by comparing the length of the vehicle's driving trajectory with the length of one side of the task box parallel to the driving direction, and combining the driving trajectory to determine whether the data collection requirements are met.

[0027] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0028] Figure 2 It is a flowchart of a map data processing method shown in an embodiment of the present application.

[0029] See also Figure 2 , the embodiment of the present application provides a map data processing method, including steps S1 to S6: S1. Obtain a task frame generated according to lane line data of a target road, and driving trajectory data corresponding to the task frame.

[0030] The target road in the embodiment of the present application may refer to a road whose map data needs to be updated. For example, when map elements such as lane lines, ground markings, etc. of a certain road change and the map data of the road needs to be updated, the road can be used as the target road.

[0031] The task box in the embodiment of the present application may refer to the range of map elements that need to be collected in the target road, and the map data within the range of the task box is collected by the autonomous driving vehicle driving into the task box.

[0032] It should be noted that the driving trajectory data corresponding to the task box in the embodiment of the present application may refer to the trajectory data of the vehicle when it is driving on the target road. These data may include trajectory data generated based on GPS data, image data, radar data, etc., among which GPS data can be collected through GPS, image data can be collected through camera equipment, and radar data can be collected through lidar.

[0033] S2. intercepting the data intersecting with the task box in the driving trajectory data and using it as the intersection data.

[0034] In the embodiment of the present application, data of the intersection of the trajectory data generated according to at least one of the trajectory data, image data, and radar data and the task box can be intercepted, or data of the intersection of the fused trajectory data obtained after the fusion of the trajectory data, image data, and radar data and the task box can be intercepted. The fusion of trajectory data, image data, and radar data includes the following steps: The first trajectory data of the vehicle traveling on the target road is obtained by a first acquisition device; wherein the first acquisition device may be a GPS, and the GPS data of the vehicle traveling on the target road is obtained by the GPS, and the GPS data is identified by a GPS algorithm to obtain the first trajectory data of the vehicle in the GPS data; The second trajectory data of the vehicle traveling on the target road is obtained by a second acquisition device; wherein the second acquisition device may be a camera device, and video data of the vehicle traveling on the target road is obtained by the camera device, and the video data is identified by a deep learning algorithm to obtain the second trajectory data of the vehicle in the video data; The third trajectory data of the vehicle traveling on the target road is obtained by a third acquisition device; wherein the third acquisition device may be a laser radar, and a scanning signal of the laser radar of the vehicle traveling on the target road is obtained by the laser radar, and point cloud data of the vehicle in the scanning signal is obtained by a laser radar recognition algorithm, and the third trajectory data is obtained according to the point cloud data; The first trajectory data, the second trajectory data and the third trajectory data of the vehicle traveling on the target road at the same time are fused to obtain fused trajectory data, and the fused trajectory data is used as the driving trajectory data corresponding to the task box.

[0035] The following uses fusion trajectory data as an example to illustrate: Since autonomous vehicles may stop, turn, make a U-turn, or have delays in the start or end of collection, these situations are described in detail below: When an autonomous driving vehicle enters the task box, it may go straight for two-thirds of the way and then turn. The accumulated sum of the fused trajectory data of the straight and turning may exceed the length of the long side of one side of the task box, but the actual driving trajectory length is less than the length of the long side of one side of the task box, which will result in incomplete collected map data.

[0036] When an autonomous driving vehicle enters the task frame, it may go straight to one-third of the way and then turn around to return to the starting point. The accumulated sum of the fused trajectory data of the straight and the turn may exceed the length of the long side of one side of the task frame, but the actual driving trajectory length is less than the length of the long side of one side of the task frame, which will result in incomplete collected map data.

[0037] When an autonomous driving vehicle enters the task frame, it may stop for a period of time, but data will still be collected during the parking process. The fused trajectory data during the parking period is dense and concentrated. The accumulation of the spacing of the dense fused trajectory data in the parking section may exceed the length of one long side of the task frame, but the actual driving trajectory length is less than the length of one long side of the task frame, which will result in incomplete collected map data.

[0038] If there is a delay in the start of collection, that is, collection begins after the autonomous driving vehicle has entered the mission box and traveled a certain distance, the collected map data will be incomplete.

[0039] If there is a delay in the end of collection, and the collection is stopped only after the autonomous driving vehicle has driven a certain distance outside the task box, it will result in too much map data being collected, wasting resources.

[0040] The embodiment of the present application only intercepts the data intersecting with the task box in the fused trajectory data, which can avoid the problem of excessive collection of data caused by delays in the end of collection and the like.

[0041] S3. Select multiple set points from the intersection data.

[0042] The multiple set points in the embodiment of the present application include at least two of the maximum horizontal coordinate collection point, the minimum horizontal coordinate collection point, the maximum vertical coordinate collection point and the minimum vertical coordinate collection point.

[0043] Taking the trajectory points of vehicle turning and U-turn as an example, the multiple set points selected include the first and last endpoints and the inflection point.

[0044] S4. Projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points.

[0045] Since the driving trajectory is not necessarily parallel to the direction of travel of the lane line, directly accumulating the distances between adjacent driving collection points may result in a larger trajectory length. However, the embodiment of the present application projects the set point on one side of the task frame parallel to the driving direction, converting the driving collection points into points on the lane line, thereby avoiding the calculation error of the accumulated length of the driving collection points.

[0046] In addition, the side of the task box parallel to the driving direction in the embodiment of the present application may refer to the lane line data of the side of the generated polygonal task box parallel to the driving direction, such as the long side generated based on the leftmost lane line data.

[0047] S5. Sort the multiple projection points according to the direction of travel of the lane line, and calculate the cumulative distance between adjacent projection points.

[0048] Since the direction of the lane line is not necessarily a straight line, it may be inclined, curved, etc. After the projection points are sorted according to the direction of the lane line, adjacent projection points will be connected to form a linear line that is basically consistent with the direction of the lane line. For example, four points and three line segments can be used to accumulate distances in the same direction. The accumulated distance between adjacent projection points is equivalent to the length of the lane line covered by the actual driving trajectory, which can reduce the accumulated calculation error of the driving trajectory.

[0049] In one embodiment, see Figure 3 The red line frame is the task frame, the black line frame is the driving trajectory. The driving trajectory has a U-turn. The four set points are on the four sides of the circumscribed rectangle. The projection line segments of the U-turn part should also be accumulated, which is four points and three line segments. Among them, two line segments a and b are the accumulation of the forward direction, and one line segment c is the accumulation of the U-turn direction, that is, a+b+c.

[0050] S6. Determine whether the accumulated distance and the length of one side of the task frame parallel to the driving direction satisfy a set relationship, and use the intersection data satisfying the set relationship to generate map data of the target road.

[0051] The setting relationship in the embodiment of the present application can be: the ratio of the accumulated distance to the length of one side of the task box parallel to the driving direction is not less than the first threshold, or the difference between the length of one side of the task box parallel to the driving direction and the accumulated distance is not greater than the second threshold.

[0052] The embodiment of the present application determines whether the accumulated distance and the length of one side of the task box parallel to the driving direction satisfy a set relationship. Even if the autonomous driving vehicle has problems such as steering, U-turn, parking, or delayed collection start, the map data that satisfies the set relationship can be filtered out. The filtered map data is more complete and more accurate.

[0053] The embodiment of the present application first obtains a task frame generated by the lane line data of the target road, and the driving trajectory data corresponding to the task frame; then intercepts the data in the driving trajectory data that intersects with the task frame and uses it as the intersection data. The embodiment of the present application only intercepts the data in the driving trajectory data that intersects with the task frame, which can avoid the problem of too much collected data caused by delays in the end of collection, etc.; then selects multiple set points from the intersection data, and projects the multiple set points to one side of the task frame parallel to the driving direction to obtain multiple projection points. By projecting the set points on one side of the task frame parallel to the driving direction, the driving collection points are converted into points on the lane line. In this way, the calculation error of the accumulated length of the driving collection points can be avoided. In addition, since the traveling direction of the lane line is not necessarily a straight line direction, it may be inclined, curved, etc., and the projection points are projected according to the traveling direction of the lane line. After the directions are sorted, adjacent projection points are connected to form a linear line that is basically consistent with the direction of travel of the lane line. The accumulated distance between adjacent projection points is equivalent to the length of the lane line covered by the actual driving trajectory, which can reduce the accumulated calculation error of the driving trajectory. Then, multiple projection points are sorted according to the direction of travel of the lane line, and the accumulated distance between adjacent projection points is calculated. Finally, it is determined whether the accumulated distance and the length of one side of the task box parallel to the driving direction meet the set relationship, and the intersection data that meets the set relationship is used to generate the map data of the target road. In this way, by determining whether the accumulated distance and the length of one side of the task box parallel to the driving direction meet the set relationship, even if the autonomous driving vehicle has problems such as turning, turning around, parking, and delay in the start of collection, the intersection data for generating map data can be filtered out, and the generated map data is more complete and more accurate.

[0054] As an optional embodiment, obtaining a task frame generated by lane line data of a target road includes: S11. Acquire lane line data of the target road.

[0055] In the embodiment of the present application, the lane line data of the target road may include left and right lane line data on both sides of the road, as well as intersection lane line data.

[0056] S12. Divide the lane line data of the target road into a plurality of lane line segment data.

[0057] The lane line data of the target road is divided into a plurality of discrete lane line segment data according to a set lane line segment length or an empirical value.

[0058] S13, performing polygon processing on the multiple lane segment data to generate a polygonal task frame.

[0059] In the embodiment of the present application, the task frame of the lane line obtained by calculation can be realized by, for example, Zhang's calibration method and homography matrix. Zhang's calibration method is based on the calibration of a planar chessboard, and multiple images are taken by changing the direction of the chessboard to obtain richer coordinate information. The homography matrix performs a mapping calculation between the calibration object plane and the image plane to obtain the coordinate mapping relationship between the pixel coordinate system and the world coordinate system.

[0060] In an optional example, you first need to prepare a checkerboard calibration object, which is a calibration plate composed of black and white squares. Use this calibration object to take multiple lane line images of the target road in different directions to obtain rich coordinate information. Then, use these images to calculate the homography matrix, which describes the projection mapping relationship from the calibration object plane to the image plane. Finally, using this homography matrix, the points on the calibration object can be mapped to the corresponding points on the image, thereby calculating the task box of the lane line.

[0061] In an optional example, the embodiment of the present application can determine the first lane line in the lane line data whose length is less than a length threshold based on the acquired lane line data; then generate the second lane line based on the first lane line according to the lane line merging rule; wherein the lane line merging rule is used to characterize that there is an adjacent relationship or an intersection relationship between two lane lines; the length of the second lane line is greater than or equal to the length threshold; finally, a task frame is generated based on the second lane line; the task frame is a quadrilateral formed by the first point and the last point on the second lane line; the task frame is used as a basis for the collection vehicle to collect lane data. ‌

[0062] As an optional embodiment, data intersecting with the task box in the driving trajectory data is intercepted and used as intersection data, including: S21. Determine a longitudinal range according to the longitudinal coordinates of each lane line point on both sides of the task frame parallel to the driving direction.

[0063] In the embodiment of the present application, the longitudinal coordinate of the lane line point can be the longitudinal coordinate on the map coordinate system, and can be obtained by mapping and transforming the pixel coordinates of the lane line image on the pixel coordinate system. The minimum longitudinal coordinate and the maximum longitudinal coordinate of the lane line points on both sides parallel to the driving direction constitute the longitudinal range.

[0064] S22. Determine a lateral range according to the horizontal coordinates of each lane line point on both sides of the task frame perpendicular to the driving direction.

[0065] In the embodiment of the present application, the horizontal coordinate of the lane line point can be the horizontal coordinate on the map coordinate system, and can be obtained by mapping and transforming the pixel coordinates of the lane line image on the pixel coordinate system. The minimum horizontal coordinate and the maximum horizontal coordinate of the lane line points on both sides perpendicular to the driving direction constitute the horizontal range.

[0066] S23. According to the horizontal coordinate and the vertical coordinate of each collection point in the driving trajectory data, the collection points whose horizontal coordinate and vertical coordinate are both within the horizontal range and the vertical range in the driving trajectory data are intercepted and used as intersection data.

[0067] In the embodiment of the present application, the horizontal coordinate and vertical coordinate of each collection point in the driving trajectory data can be converted into the horizontal coordinate and vertical coordinate on the map coordinate system through GPS data or radar data mapping. If the horizontal coordinate of the collection point in the driving trajectory data is within the horizontal range, and the vertical coordinate of the collection point in the driving trajectory data is within the vertical range, it is intercepted as intersection data.

[0068] In another optional example, the task box is generated based on two outer frames of the lane line, and the starting points and end points of the two outer frames are respectively connected to form a cutoff line, which together with the two outer frames form the task box.

[0069] As another optional embodiment, data intersecting with the task box in the driving trajectory data is intercepted and used as intersection data, including: mapping the driving trajectory and the task box to the same coordinate system diagram, in which the driving trajectory data in and on the task box is used as intersection data.

[0070] As an optional embodiment, the plurality of set points include at least two of a maximum abscissa collection point, a minimum abscissa collection point, a maximum ordinate collection point, and a minimum ordinate collection point.

[0071] In the embodiment of the present application, the longitude mapping of the set point can be converted into the horizontal coordinate on the map coordinate system, and the latitude mapping of the set point can be converted into the vertical coordinate on the map coordinate system.

[0072] Taking the vehicle going straight as an example, the multiple set points selected include the first and last endpoints (i.e., the two points of maximum longitude and minimum longitude); taking the vehicle turning and U-turning as an example, the multiple set points selected include the first and last endpoints and the turning point (e.g., the three points of maximum longitude, minimum longitude, and maximum latitude).

[0073] As an optional embodiment, multiple set points are projected onto a side of the task frame parallel to the driving direction to obtain multiple projection points, including: S41, dividing a side of the task frame parallel to the driving direction into a plurality of projection line segments.

[0074] S42, determining the projection line segment corresponding to each set point.

[0075] S43, projecting each set point onto the corresponding projection line segment to obtain a plurality of projection points.

[0076] See also Figure 4 As shown, Figure 4The side of the task box parallel to the driving direction is divided into projection line segment La, projection line segment Lb and projection line segment Lc. Multiple set points include a, b, and c, a corresponds to projection line segment La, b corresponds to projection line segment Lb, and c corresponds to projection line segment Lc. The correspondence between the set point and the projection line segment can be determined based on the horizontal coordinate of the set point and the horizontal coordinate range of the two end points of the projection line segment. If the horizontal coordinate of the set point is within the horizontal coordinate range of the two end points of the projection line segment or does not exceed the set value, it is determined that the set point corresponds to the projection line segment. Among them, the set value can be the length of one side of the task box perpendicular to the driving direction or other empirical values, which is not limited in this application.

[0077] The projection point of the set point a on the projection line segment La is a', the projection point of the set point b on the projection line segment Lb is b', and the projection point of the set point c on the projection line segment Lc is c'. Since the set point c is not within the horizontal coordinate range of the two end points of the projection line segment Lc and does not exceed the set value, and the projection line segment Lc is a line segment connected to a side edge of the task box that is perpendicular to the driving direction, and the angle between the projection line segment Lc and the side edge is an obtuse angle, then the projection line segment Lc can be extended in the extension direction of the projection line segment Lc, and the set point c can be projected on its extended line segment Lc' to obtain the projection point c'.

[0078] As an optional embodiment, the relationship is set as follows: the ratio of the accumulated distance to the length of one side of the task box parallel to the driving direction is not less than a first threshold, or the difference between the length of one side of the task box parallel to the driving direction and the accumulated distance is not greater than a second threshold.

[0079] In the embodiment of the present application, the first threshold value may be 90% or other empirical values, and the second threshold value may be 32m or other empirical values, which is not limited in the present application.

[0080] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a map data processing device, an electronic device and corresponding embodiments.

[0081] Figure 5 It is a schematic diagram of the structure of a map data processing device shown in an embodiment of the present application.

[0082] See also Figure 5 The embodiment of the present application provides a map data processing device, including an acquisition module 510, a capture module 511, a selection module 512, a projection module 5, a calculation module 514 and a judgment module 515.

[0083] The acquisition module 510 is used to acquire the task frame generated according to the lane line data of the target road, and the driving trajectory data corresponding to the task frame; wherein the acquisition module 510 is used to acquire the lane line data of the target road; divide the lane line data of the target road into multiple lane line segment data; perform polygon processing on the multiple lane line segment data through plane object calculation to generate a polygonal task frame. The acquisition module 510 is also used to acquire the first trajectory data of the vehicle driving on the target road through the first acquisition device; acquire the second trajectory data of the vehicle driving on the target road through the second acquisition device; acquire the third trajectory data of the vehicle driving on the target road through the third acquisition device; fuse the first trajectory data, the second trajectory data and the third trajectory data of the vehicle driving on the target road at the same time to obtain the fused trajectory data, and use the fused trajectory data as the driving trajectory data corresponding to the task frame.

[0084] The interception module 511 is used to intercept the data in the driving trajectory data that intersects with the task box and use it as the intersection data; wherein, the interception module 511 is used to determine the longitudinal range according to the longitudinal coordinates of each lane line point on both sides of the task box parallel to the driving direction; determine the lateral range according to the transverse coordinates of each lane line point on both sides of the task box perpendicular to the driving direction; according to the transverse and longitudinal coordinates of each collection point in the driving trajectory data, intercept the collection points in the driving trajectory data whose transverse and longitudinal coordinates are within the transverse range and the longitudinal range, and use them as the intersection data.

[0085] The selection module 512 is used to select a plurality of set points from the intersection data; wherein the plurality of set points include at least two of the maximum horizontal coordinate collection point, the minimum horizontal coordinate collection point, the maximum vertical coordinate collection point and the minimum vertical coordinate collection point.

[0086] The projection module 513 is used to project multiple set points onto one side of the task box parallel to the driving direction to obtain multiple projection points; wherein, the projection module 513 is used to divide the one side of the task box parallel to the driving direction into multiple projection line segments; determine the projection line segment corresponding to each set point; and project each set point onto the corresponding projection line segment to obtain multiple projection points.

[0087] The calculation module 514 is used to sort the multiple projection points according to the direction of travel of the lane line and calculate the accumulated distance between each adjacent projection point.

[0088] The judgment module 515 is used to judge whether the accumulated distance and the length of one side of the task box parallel to the driving direction meet the set relationship, and use the intersection data that meets the set relationship to generate the map data of the target road. Among them, the ratio of the accumulated distance to the length of one side of the task box parallel to the driving direction is not less than the first threshold, or the difference between the length of one side of the task box parallel to the driving direction and the accumulated distance is not greater than the second threshold.

[0089] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0090] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0091] See also Figure 6 , the electronic device 600 includes a memory 610 and a processor 620 .

[0092] The processor 620 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0093] The memory 610 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 620 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a 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 readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at runtime. In addition, the memory 610 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 disks and / or optical disks may also be used. In some embodiments, the memory 610 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0094] The memory 610 stores executable codes, and when the executable codes are processed by the processor 620 , the processor 620 can execute part or all of the above-mentioned methods.

[0095] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0096] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0097] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A map data processing method, characterized in that: include: Acquire a task frame generated according to lane line data of a target road, and driving trajectory data corresponding to the task frame; intercepting data intersecting with the task frame from the driving trajectory data and using the data as intersection data; selecting a plurality of set points from the intersection data; Projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points; Sort the plurality of projection points according to the direction of travel of the lane line, and calculate the cumulative distance between adjacent projection points; It is determined whether the accumulated distance and the length of a side of the task frame parallel to the driving direction satisfy a set relationship, and the intersection data satisfying the set relationship is used to generate map data of the target road.

2. The method according to claim 1, characterized in that The step of obtaining a task frame generated according to lane line data of a target road includes: Obtain lane line data of the target road; Dividing the lane line data of the target road into a plurality of lane line segment data; The plurality of lane line segment data are subjected to polygon processing to generate a polygonal task frame.

3. The method according to claim 1, characterized in that The obtaining of the driving trajectory data corresponding to the task frame includes: Acquire first trajectory data of the vehicle traveling on the target road by a first acquisition device; Acquire second trajectory data of the vehicle traveling on the target road by a second acquisition device; Obtaining third trajectory data of the vehicle traveling on the target road by a third acquisition device; The first trajectory data, the second trajectory data and the third trajectory data of the vehicle traveling on the target road at the same time are fused to obtain fused trajectory data, and the fused trajectory data is used as the driving trajectory data corresponding to the task box.

4. The method according to claim 1, characterized in that: The plurality of set points include at least two of a maximum abscissa collection point, a minimum abscissa collection point, a maximum ordinate collection point, and a minimum ordinate collection point.

5. The method according to claim 1, characterized in that The step of projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points includes: Dividing a side of the task frame parallel to the driving direction into a plurality of projection line segments; Determine the projection line segment corresponding to each of the set points; Each of the set points is projected onto a corresponding projection line segment to obtain a plurality of projection points.

6. The method according to claim 5, characterized in that The step of projecting each of the set points onto a corresponding projection line segment to obtain a plurality of projection points comprises: If the angle between the projection line segment connected to the side edge of the task box perpendicular to the driving direction and the side edge is an obtuse angle, the projection line segment is extended in the extension direction of the projection line segment, and the set point corresponding to the projection line segment is projected onto its extended line segment to obtain the projection point.

7. The method according to claim 1, characterized in that The setting relationship is: The ratio of the accumulated distance to the length of one side of the task box parallel to the driving direction is not less than a first threshold, or the difference between the length of one side of the task box parallel to the driving direction and the accumulated distance is not greater than a second threshold.

8. A map data processing device, characterized in that: include: An acquisition module, used to acquire a task frame generated according to lane line data of a target road, and driving trajectory data corresponding to the task frame; An interception module, used for intercepting data intersecting with the task frame in the driving trajectory data and using it as intersection data; A selection module, used for selecting a plurality of set points from the intersection data; A projection module, used for projecting the plurality of set points onto a side of the task frame parallel to the driving direction to obtain a plurality of projection points; A calculation module, used to sort the plurality of projection points according to the direction of travel of the lane line, and calculate the cumulative distance between adjacent projection points; The judgment module is used to judge whether the accumulated distance and the length of a side of the task frame parallel to the driving direction satisfy a set relationship, and use the intersection data satisfying the set relationship to generate the map data of the target road.

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 7.

10. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 7.

Images