Road map construction method, vehicle, equipment and program product
By using lane line image data in autonomous driving technology to determine the distance between the point and the projection point, the existing lane line matching methods have been solved, and more efficient and accurate road map construction is achieved.
Patent Information
- Application Number
- CN202411448321.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing lane line matching methods have problems in autonomous driving technology with low matching accuracy and long matching time, which affects the construction accuracy and speed of road maps.
By obtaining the lane line image data captured by the camera device on the vehicle, we judge whether there is a projection point in the road map of each point, and calculate the minimum distance and maximum distance between the point and the projection point, and determine the lane line matching result based on these distances. Therefore, the road map is constructed.
It improves the accuracy and speed of lane line matching, improves the accuracy of road maps, avoids complex curve fitting processes, and reduces computing resource consumption.
Smart Images

Figure CN118980383A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of vehicle technology, and in particular to a road map construction method, a vehicle, a device, and a program product. Background Art
[0002] In autonomous driving technology, lanes identified by the vehicle's perception module can be used to construct road maps, thereby assisting the vehicle in planning its driving route more accurately and ensuring safe and efficient operation even in complex traffic environments.
[0003] In the process of constructing a road map, lane line matching is performed for each identified lane line. As an essential process in the composition process, the accuracy of the matching results affects the quality of the constructed road map. However, some common lane line matching methods, such as multiple curve fitting, usually have problems of low matching accuracy and long matching time, which reduces the accuracy and speed of the constructed road map. Summary of the invention
[0004] The embodiments of the present disclosure at least provide a road map construction method, vehicle, device and program product.
[0005] The present disclosure provides a method for constructing a road map, the method comprising: Acquire lane line data corresponding to a lane line image captured by a camera on a vehicle; the lane line data includes coordinate values of a plurality of points corresponding to at least one lane line; Taking each lane line in the lane line data as a first lane line, determining whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map, and if so, calculating the distance between the point and the projection point; Determine the minimum distance and the maximum distance between each point on the first lane line and its corresponding projection point; A matching result between the first lane line and the second lane line is determined according to the minimum distance and the maximum distance, and a road map is constructed based on the matching result.
[0006] In a possible implementation, determining a matching result between the first lane line and the second lane line according to the minimum distance and the maximum distance includes: If the minimum distance is less than a first threshold, the maximum distance is less than a second threshold, and the difference between the maximum distance and the minimum distance is less than a third threshold, it is determined that the first lane line matches the second lane line; otherwise, it is determined that the first lane line does not match the second lane line.
[0007] In a possible implementation, the second threshold is greater than the first threshold, the third threshold is less than the second threshold, and the third threshold is greater than the difference between the second threshold and the first threshold.
[0008] In a possible implementation, constructing a road map based on the matching result includes: If the matching result indicates that the first lane line matches the second lane line, adding a line segment corresponding to the first lane line to a line segment group corresponding to the second lane line; If the matching result indicates that the first lane line does not match the second lane line, determine whether to use a line segment of the first lane line as a line segment of a newly constructed lane line in the road map according to the confidence of the first lane line indicated in the lane line data.
[0009] In a possible implementation manner, determining whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map includes: It is determined whether, for each point on the first lane line, there is a corresponding projection point in the line segment last added to the line segment group of the second lane line.
[0010] In a possible implementation manner, before determining whether each point on the first lane line has a corresponding projection point in the line segment last added to the second lane line, the method further includes: According to the coordinate value of the center of the vehicle in the global coordinate system, converting the coordinate value of each point of the first lane line relative to the center of the vehicle into the coordinate value in the global coordinate system; The determining whether each point on the first lane line has a corresponding projection point in the line segment last added to the second lane line includes: Using the converted coordinate values corresponding to each point of the first lane line and the endpoint coordinate values of the last added line segment in the second lane line in the global coordinate system, it is determined whether each point of the first lane line has a corresponding projection point in the last added line segment in the second lane line.
[0011] In a possible implementation, determining whether to use a line segment of a first lane line indicated in the lane line data as a line segment of a newly constructed lane line in a road map includes: Determine a first vector between a position point of the vehicle when the camera device captures a previous lane line image and a position point of the vehicle when the camera device captures a current lane line image, and a second vector between a first point and a last point on the first lane line; If the angle between the first vector and the second vector is smaller than a set angle and the confidence level is greater than a set confidence level threshold, the line segment of the first lane line is used as a line segment of a newly constructed lane line in the road map.
[0012] In a possible implementation, each lane line in the lane line data is used as a first lane line, and before determining whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map, the method further includes: The lane lines indicated by the lane line data are sorted in descending order according to the number of points they contain, and the sorted order is used as the order for matching the lane lines in sequence.
[0013] The present disclosure also provides a vehicle, including a controller, wherein the controller includes: a memory for storing machine-readable instructions; and The processor is used to call and execute the machine-readable instructions stored in the memory to implement the above-mentioned road map construction method, or the steps in any possible implementation of the above-mentioned road map construction method.
[0014] An embodiment of the present disclosure further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the above-mentioned road map construction method or steps in any possible implementation of the above-mentioned road map construction method are executed.
[0015] The present disclosure also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned road map construction method, or the steps in any possible implementation of the above-mentioned road map construction method.
[0016] The road map construction method, vehicle, equipment and program product provided by the embodiments of the present disclosure use the newly identified points on the first lane line and the points on the constructed second lane line to match the lane lines, and determine the matching result in combination with the minimum distance and the maximum distance between each point on the first lane line and the corresponding projection point. Since there is no need to perform complex curve fitting and other processes, only the distance between points needs to be determined, which can improve the matching efficiency. Moreover, by considering the minimum distance and the maximum distance, the accuracy of the matching result can be improved to a certain extent. Therefore, the embodiments of the present disclosure can improve the accuracy of lane line matching and the accuracy of road maps while improving the matching speed and map construction speed.
[0017] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.
[0019] Figure 1 A flow chart of a road map construction method provided by an embodiment of the present disclosure is shown; Figure 2 A specific implementation flow chart of a road map construction method provided by an embodiment of the present disclosure is shown; Figure 3 A schematic structural diagram of an electronic device 300 provided in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0020] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.
[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0022] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.
[0023] Research has found that when matching lane lines perceived by the vehicle, the method usually used is to first perform multiple curve fitting on the collected lane lines, and then determine whether the lane lines match based on the similarity and overlap between the fitted curves. However, this method not only introduces fitting errors during curve fitting, but also fails to find matching point pairs when there are fewer points in the lane lines, affecting the accuracy of lane line matching and thus reducing the accuracy of map construction. Another method is to use the Iterative Closest Point (ICP) algorithm for lane line matching, but this method increases the consumption of vehicle computing resources, increases the computing time cost, affects the efficiency of lane matching, and thus reduces the speed of map construction.
[0024] Based on the above research, the present disclosure provides a road map construction method, vehicle, equipment and program product, which uses the newly identified points on the first lane line and the points on the constructed second lane line to match the lane lines, and combines the minimum distance and the maximum distance between each point on the first lane line and the corresponding projection point in the matching process. While improving the matching speed and map construction speed, it can avoid the problem of not being able to find matching point pairs in the first lane line and the second lane line, thereby improving the accuracy of lane line matching and improving the accuracy of road maps.
[0025] To facilitate understanding of this embodiment, a road map construction method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the road map construction method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device. The terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the road map construction method can be implemented by a processor calling a computer-readable instruction stored in a memory.
[0026] See also Figure 1 FIG. 1 is a flowchart of a road map construction method provided by an embodiment of the present disclosure, wherein the method includes steps S101 to S104, wherein: S101: Acquire lane line data corresponding to a lane line image captured by a camera on a vehicle; the lane line data includes coordinate values of a plurality of points corresponding to at least one lane line.
[0027] Here, lane line data refers to data related to lane lines on the road, which can be identified from lane line images taken by a camera. Moreover, the lane line identified from the lane line image often only belongs to a segment of a real lane line, so the lane line in the lane line data is a line segment. Since the lane line identified in the lane line image can include at least one lane line, the lane line data can include data related to at least one lane line, which can specifically be the coordinate values of each point included in the lane line relative to the center of the vehicle. The number of points included in different lane lines is different, and the coordinate value of each point can include three values of x, y, and z.
[0028] In the process of building a road map, a lane line is often identified in segments. Therefore, for each lane line, there may be a segment group, and each segment included in the segment group may be a lane line identified continuously at different times. Therefore, the lane line in the lane line data corresponding to any lane line image can be regarded as a segment corresponding to a lane line identified from the lane line image.
[0029] In specific implementation, after acquiring the lane line image captured by the camera device on the vehicle, lane line detection can be performed on the lane line image to determine each lane line. For each lane line, the coordinate value of each point on the lane line relative to the center of the vehicle can be determined based on the coordinate value of the center of the vehicle in the vehicle coordinate system and the distance of each point on the lane line relative to the center of the vehicle. According to the coordinate value of each point relative to the center of the vehicle, the lane line data corresponding to the lane line is determined.
[0030] Exemplarily, 5 lane lines are detected from the lane line image, each lane line may include 4-6 points, and the points in each lane line have coordinate values relative to the center of the vehicle. According to the coordinate values of each point, the lane line data corresponding to the lane line image is constructed.
[0031] S102: Take each lane line in the lane line data as a first lane line, determine whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map, and if so, calculate the distance between the point and the projection point.
[0032] Here, the purpose of the embodiment of the present disclosure is to construct a road map using lane lines, and the construction of the road map is a gradual improvement process, that is, it is necessary to construct a complete road map based on the lane lines that are continuously detected and matched. Therefore, before the current first lane line is detected, if there is a constructed road map, then each lane line in the road map can be called a constructed second lane line. In the constructed road map, the constructed second lane line can include one or more. If there is no constructed road map, then there will be no constructed second lane line.
[0033] Since the length of the lane line detected in the lane line image each time will not be infinite, and the actual lane line on the road will not be infinite, the identified first lane line and the constructed second lane line are both line segments with a certain length and will not be infinitely long straight lines.
[0034] The projection point can be understood as a point on the first lane line, which is obtained by projecting it onto the second lane line. When the projected point is within the second lane line, it can be determined that the projection point exists. Conversely, when the projected point is not within the second lane line, it is determined that the projection point does not exist. That is, whether the projection point exists depends on whether the projected point is within the second lane line. Exemplarily, for any point i in the first lane line, it is assumed that the projected point obtained by projecting point i onto the second lane line is point p. If point p is within the second lane line, point p is determined to be the projection point of point i, and the distance between point p and point i is calculated. If point p is not within the second lane line, it is determined that point i does not have a projection point on the second lane line, and point i is ignored.
[0035] In a specific implementation, each lane line in the lane line data can be used as the first lane line, and then it is determined whether there is a constructed road map. If so, each constructed second lane line can be obtained from the road map. Then, for each first lane line, it can be paired with each second lane line to obtain each line-to-line matching pair consisting of the first lane line and each second lane line. For the first lane line in each line-to-line matching pair, each point on the first lane line can be projected to the second lane line in the line-to-line matching pair in turn. According to whether the projected point is located on the second lane line, it is determined whether each point on the first lane line has a corresponding projection point in the second lane line. For each point that has a projection point in the second lane line, the distance between the point and the corresponding projection point can be calculated. Among them, when projecting each point on the first lane line to the second lane line, the coordinate value of the point on the first lane line can be converted from the coordinate value relative to the middle of the vehicle to the coordinate value in the global coordinate system, and then the coordinate value in the global coordinate system is used for projection to obtain the projected point.
[0036] It is understandable that for a certain line-line matching pair, there may be points on the first lane line in the line-line matching pair, but there are no corresponding projection points on the second lane line in the line-line matching pair. In this case, it can be directly determined that the first lane line and the second lane line do not match.
[0037] In this way, by using the above S102, it is possible to determine, among the points on any first lane line, the points on which projection points exist on the second lane lines, and the distances between the points and the projection points.
[0038] S103: Determine the minimum distance and the maximum distance among the distances between each point on the first lane line and its corresponding projection point.
[0039] Exemplarily, for a line-to-line matching pair consisting of any first lane line and any second lane line, the above S102 can be used to determine, for each point on the first lane line, a target point having a corresponding projection point in the second lane line, and a distance between the target point and the corresponding projection point. Then, the maximum distance and the minimum distance can be determined from the distances between each target point and the corresponding projection point, and the maximum distance and the minimum distance are used as the maximum distance and the minimum distance between the first lane line and the second lane line.
[0040] In this way, for any first lane line, the maximum distance and the minimum distance between the first lane line and the second lane line in any line matching pair corresponding to the first lane line can be determined.
[0041] Optionally, if all points on the first lane line do not have projection points in the second lane line, it can be determined that the maximum distance and the minimum distance between the first lane line and the second lane line are both empty, and it can be determined that the first lane line and the second lane line do not match.
[0042] S104: Determine a matching result between the first lane line and the second lane line according to the minimum distance and the maximum distance, and construct a road map based on the matching result.
[0043] Here, the matching result is used to indicate whether the first lane line and the second lane line are matched successfully. If the matching is successful, it can be explained that the first lane line and the second lane line belong to different line segments on the same lane line; conversely, if the matching fails, it can be explained that the first lane line and the second lane line do not belong to the same lane line.
[0044] For any first lane line, there is at most one second lane line among the second lane lines that successfully matches the first lane line.
[0045] During specific implementation, for any first lane line, the matching results corresponding to the first lane line and each second lane line can be determined based on the maximum distance and the minimum distance corresponding to the first lane line and each second lane line. Then, it is determined whether there is a second lane line with a successful matching result. If so, the second lane line can be used as a lane line that matches the first lane line, and the first lane line can be drawn in the road map based on the matching result. If there is no successful matching second lane line, the first lane line can be used as a newly appeared lane line, and the road map can be constructed based on the first lane line. Regarding the process of constructing a road map using lane lines, any method in the prior art can be used, and the embodiments of the present disclosure do not specifically limit it.
[0046] Among them, regarding the process of determining the matching result based on the maximum distance and the minimum distance, for example, whether the first lane line and the second lane line match can be determined based on the size relationship between values such as the difference / average value / variance between the maximum distance and the minimum distance and a preset comparison value.
[0047] In this way, the newly identified points on the first lane line and the points on the constructed second lane line are used to match the lane lines, and the matching result is determined by combining the minimum distance and the maximum distance between each point on the first lane line and the corresponding projection point. Since there is no need to perform complex curve fitting and other processes, only the distance between points needs to be judged, which can improve the matching efficiency. Moreover, through the dual consideration of the minimum distance and the maximum distance, the accuracy of the matching result can be improved to a certain extent. Therefore, the embodiment of the present disclosure can improve the accuracy of lane line matching and the accuracy of road maps while improving the matching speed and map construction speed.
[0048] In one embodiment, before executing the above S102, the lane lines indicated by the lane line data may be sorted in order from most to least number of points, and the sorted order is used as the order for matching the lane lines in sequence.
[0049] In specific implementation, after obtaining the lane line data corresponding to the lane line image of the current frame, for each lane line included in the lane line data, the number of points included in each lane line can be determined first, and then the lane lines are sorted in order from most to least points to obtain the sorted order. Then, the sorted order is used as the matching order of each lane line with the second lane line constructed in the road map.
[0050] For example, the lane lines included in the lane line data are lane lines 1 to 3, and the second lane lines include 4 to 6. After sorting lane lines 1 to 3 using the points in lane lines 1 to 3, the sorting order obtained is lane line 2, lane line 1, and lane line 3. Then, lane line 2 can be matched with lane lines 4 to 6 in sequence to determine whether lane line 2 matches any of lane lines 4 to 6. After lane line 2 is matched, lane line 1 can be matched with lane lines 4 to 6 in sequence to determine whether lane line 1 matches any of lane lines 4 to 6. Finally, lane line 3 can be matched with lane lines 4 to 6 in sequence to determine whether lane line 3 matches any of lane lines 4 to 6.
[0051] In this way, by giving priority to matching lane lines with more points, the impact of abnormal perception results on matching results can be effectively reduced.
[0052] In one embodiment, the step of determining the matching result in S104 may also be implemented as follows: If the minimum distance is less than the first threshold, the maximum distance is less than the second threshold, and the difference between the maximum distance and the minimum distance is less than the third threshold, it is determined that the first lane line matches the second lane line; otherwise, it is determined that the first lane line does not match the second lane line.
[0053] The second threshold is greater than the first threshold, the third threshold is less than the second threshold, and the third threshold is greater than the difference between the second threshold and the first threshold. By setting the third threshold to be greater than the difference between the second threshold and the first threshold, a certain error tolerance space can be ensured when matching lane lines.
[0054] Here, the first threshold, the second threshold, and the third threshold can all be set based on experience, and the embodiments of the present disclosure do not specifically limit them. However, when setting the three thresholds, it is necessary to ensure that the following two conditions are met: 1. The second threshold is greater than the first threshold; 2. The third threshold is less than the second threshold and is greater than the difference between the second threshold and the first threshold. For example, the first threshold can be 1m, the second threshold can be 1.5m, and the third threshold can be 1m.
[0055] In specific implementation, for the first lane line and the second lane line, after obtaining the corresponding maximum distance and minimum distance between the first lane line and the second lane line, it can be determined whether the following three conditions are met at the same time: 1. The minimum distance is less than the first threshold; 2. The maximum distance is less than the second threshold; 3. The distance between the maximum distance and the minimum distance is less than the third threshold. If these three conditions are met at the same time, it can be determined that the first lane line and the second lane line are matched successfully. Conversely, if these three conditions cannot be met at the same time, it can be determined that the first lane line and the second lane line are matched unsuccessfully.
[0056] In one embodiment, in the process of constructing a road map, a lane line is often identified in segments, so there may be a segment group for each lane line, and the segments included in the segment group may be continuously identified at different times. For any frame of lane line image, the first lane line identified therefrom is often a segment of a certain lane line, so after identifying the first lane line, if it is determined that it matches a certain lane line, the first lane line can be added to the corresponding segment group, thereby finding different segments corresponding to the lane line. In this case, the step of "constructing a road map based on matching results" in S104 can be implemented as follows: If the matching result indicates that the first lane line matches the second lane line, the line segment corresponding to the first lane line is added to the line segment group corresponding to the second lane line.
[0057] Here, the matching result indicates that the first lane line matches the second lane line, which means that the first lane line and the second lane line match successfully and both belong to the same lane line. The line segment group corresponding to the second lane line is the line segment group of the real lane line to which the second lane line belongs, and this line segment group may include at least one line segment, which is the lane line identified from the lane line image acquired previously.
[0058] Taking lane line 1 as the second lane line as an example, the line segment group to which lane line 1 belongs includes the line segment corresponding to lane line 1 identified from the first frame lane line image, the line segment corresponding to lane line 1 identified from the second frame lane line image, the line segment corresponding to lane line 1 identified from the third frame lane line image, etc. After the first lane line is identified from the lane line image of the current frame, if the matching result of the first lane line and lane line 1 indicates that the two are successfully matched, the line segment of the first lane line can be taken as a new line segment and added to the line segment group to which lane line 1 belongs.
[0059] After the line segment corresponding to the first lane line is added to the line segment group corresponding to the second lane line, a road map may be constructed according to the line segment corresponding to the first lane line.
[0060] In addition, if the matching result indicates that the first lane line does not match the second lane line, it is determined whether to use the line segment of the first lane line as the line segment of the newly constructed lane line in the road map according to the confidence of the first lane line indicated in the lane line data.
[0061] Here, the matching result indicates that the first lane line and the second lane line do not match, which means that the first lane line and the second lane line fail to match and they do not belong to the same lane line. The newly constructed lane line is the lane line that needs to be newly drawn in the road map, and the lane line did not exist in the road map before. The confidence of the first lane line can be output when the first lane line is identified from the lane line image, and the confidence belongs to the lane line data.
[0062] For example, if the matching result indicates that the first lane line does not match any of the second lane lines, the confidence of the first lane line can be obtained based on the lane line data of the first lane line. Then, based on the relationship between the confidence and the preset confidence, it is determined whether to use the line segment of the first lane line as the line segment of the newly constructed lane line in the road map, that is, it is determined whether it is necessary to construct a line segment group of the newly constructed lane line and add the line segment of the first lane line to the line segment group. Then, based on the line segment of the first lane line, the corresponding new lane line can be drawn in the road map.
[0063] In one embodiment, the step of “determining whether to use the line segment of the first lane line as the line segment of the newly constructed lane line in the road map according to the confidence level of the first lane line” can be implemented according to the following steps: Step 1: Determine the first vector between the position of the vehicle when the camera device captured the previous lane line image and the position of the vehicle when the camera device captured the current lane line image, and the second vector between the first point and the last point on the first lane line.
[0064] Here, when the vehicle uses a camera to capture a lane line image, there is vehicle positioning data, which can be the coordinates of the center of the vehicle in the global coordinate system. ,in, represents the position of the i-th positioning trajectory point of the vehicle, They represent the values in different coordinate directions respectively.
[0065] During the driving process, the vehicle continuously captures lane line images and performs lane line recognition and matching. At the same time, the vehicle is also continuously positioned, and the vehicle positioning data obtained is also continuous. Therefore, in a specific implementation, when it is determined that the first lane line identified from the current frame lane line image does not match any second lane line, the vehicle positioning data when the previous frame lane line image was captured by the camera device can be obtained, and the position of the vehicle when the previous frame lane line image was captured can be determined based on the vehicle positioning data, and the vehicle positioning data when the current frame lane line image was captured by the camera device can be obtained, and the position of the vehicle when the current frame lane line image was captured can be determined based on the vehicle positioning data. In other words, the lane line corresponding to the current frame lane line image can be obtained. , and the lane line image corresponding to the previous frame Then, according to the position points corresponding to the two lane line images, a vector composed of the lane line image of the previous frame can be determined, and the vector is used as the first vector. The direction of the first vector can be used to indicate the driving direction of the vehicle, and the magnitude of the first vector can be used to indicate the change in the posture of the vehicle when shooting adjacent lane line images.
[0066] At the same time, the coordinate value of the first point on the first lane line in the global coordinates and the coordinate value of the last point on the first lane line in the global coordinates can be obtained, and the second vector corresponding to the first vehicle line can be determined according to the two coordinate values. The direction of the second vector can be used to indicate the direction of the first lane line, and the magnitude of the second vector can be used to indicate the length of the first lane line.
[0067] Step 2: If the angle between the first vector and the second vector is smaller than the set angle and the confidence is greater than the set confidence threshold, the line segment of the first lane line is used as the line segment of the newly constructed lane line in the road map.
[0068] Here, the setting angle and the setting confidence threshold can be set based on experience, and the embodiment of the present disclosure does not specifically limit them. For example, the setting angle can be 5 degrees, and the setting confidence threshold can be 0.35.
[0069] For example, after obtaining the first vector and the second vector, the angle between the first vector and the second vector can be determined, and then it is determined whether the angle is less than a set angle and the confidence of the first lane line is greater than a set confidence threshold. If so, it can be determined that the first lane line is a new lane line appearing in the direction of vehicle travel, so the line segment of the first lane line can be used as the line segment of the newly constructed lane line in the road map, and the line segment of the first lane line is added to the line segment group of the newly constructed lane line. If the above conditions cannot be met, the first lane line can be discarded.
[0070] In one embodiment, when there are line segment groups for each constructed second lane line in the road map, the order in which the line segments of each identified lane line are added to the corresponding line segment group is often the order in which the lane line image where the lane line is located is collected, and the lane line in the road map can be composed of each line segment in the line segment group corresponding to the lane line. At the same time, when there are line segment groups, for the step of "determining whether each point on the first lane line has a corresponding projection point in the second lane line constructed in the road map" in S102, it is also possible to directly determine whether each point on the first lane line has a corresponding projection point in the line segment last added to the line segment group of the second lane line.
[0071] That is, in a specific implementation, for any first lane line, the last added line segments corresponding to each second lane line can be obtained from the line segment groups of each constructed second lane line. Then, the first lane line is matched with the last added line segments corresponding to each second lane line to obtain each line-line matching pair corresponding to the first lane line. Then, for any line-line matching pair, any point of the first lane line is projected onto the last added line segment of the second lane to determine whether the projected point is located in the last added line segment. If so, it is determined that the point has a projection point, and if not, it is determined that the point does not have a projection point.
[0072] In this way, the projection point is determined using the line segment last added to the line segment group corresponding to the second lane line, which can reduce the amount of calculation while ensuring accuracy and improve matching efficiency.
[0073] It is understandable that after the lane lines indicated by the lane line data are sorted in order of the number of points contained therein from most to least, the first lane line can be matched with the last added line segment in the line segment group of each second lane line in the sorted order.
[0074] In one embodiment, since the coordinate values of the multiple points of the lane line included in the lane line data are the coordinate values of the points on the lane line relative to the center of the vehicle, and the coordinate value of the center of the vehicle is the coordinate value in the global coordinate system, in order to ensure the uniformity of the coordinate system, before executing S102, the coordinate conversion may be performed first. Specifically, the coordinate value of each point of the first lane line relative to the center of the vehicle may be converted into a coordinate value in the global coordinate system according to the coordinate value of the center of the vehicle in the global coordinate system.
[0075] Exemplarily, the coordinate value of the center of the vehicle in the global coordinate system can be used as the coordinate origin to construct a local global coordinate system, and then the coordinate value of each point of the first lane line relative to the center of the vehicle is converted into a coordinate value in the local global coordinate system.
[0076] Furthermore, for the above step of “determining whether each point on the first lane line has a corresponding projection point in the line segment last added to the line segment group of the second lane line”, it can also be determined according to the following steps: Using the converted coordinate values corresponding to each point of the first lane line and the endpoint coordinate values of the last line segment added to the second lane line in the global coordinate system, it is determined whether each point of the first lane line has a corresponding projection point in the last line segment added to the second lane line.
[0077] Here, the endpoint coordinate values may be the coordinate values of the two endpoints of the line segment last added to the second lane line in the global coordinate system.
[0078] Take any point of the first lane line as point p and the last line segment added to the second lane line as line segment AB as an example, the following steps can be used to determine whether point p is located in line segment AB: ①. Take any endpoint of line segment AB (for example, point A) as the starting point and calculate the vector corresponding to line segment AB and the vector corresponding to line segment AP. Vector AB and vector AP can be determined using the following formulas 1-1 and 1-2: ;(Formula 1-1) ;(Formula 1-2) in, That is, vector AB, B represents the endpoint coordinate value of the endpoint B of line segment AB in the global coordinate system. Indicates the endpoint coordinate value of the endpoint A of the line segment AB in the global coordinate system. Represents the converted coordinate value corresponding to point P in the first lane line.
[0079] ②. Based on vector AB and vector AP, use the following formula 2-1 to calculate the parameterized position used to characterize whether the projection point is located on line segment AB: ;(Formula 2-1) in, Represents a parameterized position.
[0080] ③. Use the following formula 3-1 to calculate the projected point obtained by projecting point P onto line segment AB: ;(Formula 3-1) Wherein, Q represents the coordinate value of the projected point corresponding to point P.
[0081] ④. Use the following formula 4-1 to determine whether the projected point is within line segment AB: ;(Formula 4-1) in, In other words, when the parameterized position t is greater than or equal to 0 and less than or equal to 1, Q can be determined to be the projection point of point P in line segment AB, otherwise, it is determined that point P does not have a projection point in line segment AB.
[0082] Therefore, in a specific implementation, for any first lane line, the converted coordinate values corresponding to each point of the first lane line and the endpoint coordinate values of the last line segment added to the second lane line in the global coordinate system can be used to determine whether each point of the first lane line has a corresponding projection point in the last line segment added to the second lane line according to the above steps ① to ④.
[0083] Furthermore, if each point of the first lane line does not have a corresponding projection point in the line segment last added to the second lane line, it can be determined that the first lane line and the second lane line have failed to match. If some points of the first lane line have corresponding projection points in the line segment last added to the second lane line, the road map can be constructed according to the above steps S103 to S104.
[0084] like Figure 2 As shown, a specific implementation flow chart of a road map construction method provided by an embodiment of the present disclosure may include the following steps: S201: Acquire lane line data corresponding to a lane line image captured by a camera on a vehicle; the lane line data includes coordinate values of a plurality of points corresponding to at least one lane line.
[0085] S202: sorting the lane lines indicated by the lane line data in descending order of the number of points they contain, and using the sorted order as a matching order for sequentially matching the lane lines.
[0086] S203: According to the coordinate value of the center of the vehicle in the global coordinate system, the coordinate value of each point of each lane line indicated by the lane line data relative to the center of the vehicle is converted into a coordinate value in the global coordinate system.
[0087] S204: Determine whether there is a segment group of the constructed second lane line in the road map.
[0088] If yes, execute the following S205~S208; if no, execute the following S209~S210.
[0089] S205: Take each lane line in the lane line data as the first lane line, determine whether each point on the first lane line has a corresponding projection point in the line segment last added to the line segment group of the second lane line, and if so, calculate the distance between the point and the projection point.
[0090] S206: Determine the minimum distance and the maximum distance among the distances between each point on the first lane line and its corresponding projection point.
[0091] S207: Determine a matching result between the first lane line and the second lane line according to the minimum distance and the maximum distance.
[0092] When the matching result indicates that the first lane line matches the second lane line, the following S208 is executed; when the matching result indicates that the first lane line does not match the second lane line, the following S209~S210 are executed.
[0093] S208: Add the line segment corresponding to the first lane line to the line segment group corresponding to the second lane line, and construct a road map according to the first lane line.
[0094] S209: Determine a first vector between the position point where the vehicle was when capturing the previous lane line image and the position point where the vehicle was when capturing the current lane line image, and a second vector between the first point and the last point on the first lane line.
[0095] S210: If the angle between the first vector and the second vector is smaller than the set angle and the confidence of the first lane line is greater than the set confidence threshold, the line segment of the first lane line is added to the line segment group of the newly constructed lane line in the road map.
[0096] On the contrary, if the angle between the first vector and the second vector is not less than the set angle, and / or the confidence of the first lane line is not greater than the set confidence threshold, the first lane line is discarded.
[0097] Regarding the specific implementation steps of the above S201~S210, reference can be made to the above embodiments, which will not be repeated here.
[0098] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.
[0099] In addition, another vehicle provided in an embodiment of the present disclosure includes a controller, wherein the controller includes: a memory for storing machine-readable instructions; and The processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps in the above road map construction method or the steps in any one of the above embodiments.
[0100] Corresponds to Figure 1 The road map construction method in the present disclosure also provides an electronic device 300, such as Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device 300 provided in an embodiment of the present disclosure, including: Processor 301, memory 302 and bus 303; memory 302 is used to store execution instructions, including memory 3021 and external memory 3022; memory 3021 here is also called internal memory, which is used to temporarily store the operation data in processor 301 and the data exchanged with external memory 3022 such as hard disk. Processor 301 exchanges data with external memory 3022 through memory 3021. When the electronic device 300 is running, the processor 301 communicates with the memory 302 through bus 303, so that the processor 301 executes Figure 1 and Figure 2 Steps of the road map construction method in .
[0101] In addition, an embodiment of the present disclosure further provides a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the steps of the road map construction method provided in any of the above embodiments of the present disclosure are executed. For details, please refer to the above method embodiments, which will not be repeated here.
[0102] The computer program product may be implemented in hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.
[0103] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment and devices can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0105] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0107] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.
Claims
1. A road map construction method, It is characterized in that The method comprises: Acquire lane line data corresponding to a lane line image captured by a camera on a vehicle; the lane line data includes coordinate values of a plurality of points corresponding to at least one lane line; Taking each lane line in the lane line data as a first lane line, determining whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map, and if so, calculating the distance between the point and the projection point; Determine the minimum distance and the maximum distance between each point on the first lane line and its corresponding projection point; A matching result between the first lane line and the second lane line is determined according to the minimum distance and the maximum distance, and a road map is constructed based on the matching result.
2. The method according to claim 1, It is characterized in that Determining a matching result between the first lane line and the second lane line according to the minimum distance and the maximum distance includes: If the minimum distance is less than a first threshold, the maximum distance is less than a second threshold, and the difference between the maximum distance and the minimum distance is less than a third threshold, it is determined that the first lane line matches the second lane line; otherwise, it is determined that the first lane line does not match the second lane line.
3. The method according to claim 2, It is characterized in that The second threshold is greater than the first threshold, the third threshold is less than the second threshold, and the third threshold is greater than a difference between the second threshold and the first threshold.
4. The method according to any one of claims 1 to 3, It is characterized in that The road map construction based on the matching result includes: If the matching result indicates that the first lane line matches the second lane line, adding a line segment corresponding to the first lane line to a line segment group corresponding to the second lane line; If the matching result indicates that the first lane line does not match the second lane line, determine whether to use a line segment of the first lane line as a line segment of a newly constructed lane line in the road map according to the confidence of the first lane line indicated in the lane line data.
5. The method according to claim 4, It is characterized in that The determining whether each point on the first lane line has a corresponding projection point on a second lane line constructed in the road map includes: It is determined whether, for each point on the first lane line, there is a corresponding projection point in the line segment last added to the line segment group of the second lane line.
6. The method according to claim 5, It is characterized in that Before determining whether each point on the first lane line has a corresponding projection point in the line segment last added to the second lane line, the method further includes: According to the coordinate value of the center of the vehicle in the global coordinate system, converting the coordinate value of each point of the first lane line relative to the center of the vehicle into the coordinate value in the global coordinate system; The determining whether each point on the first lane line has a corresponding projection point in the line segment last added to the second lane line includes: Using the converted coordinate values corresponding to each point of the first lane line and the endpoint coordinate values of the last added line segment in the second lane line in the global coordinate system, it is determined whether each point of the first lane line has a corresponding projection point in the last added line segment in the second lane line.
7. The method according to claim 4, It is characterized in that Determining whether to use a line segment of the first lane line as a line segment of a newly constructed lane line in the road map according to the confidence of the first lane line indicated in the lane line data includes: Determine a first vector between a position point of the vehicle when the camera device captures a previous lane line image and a position point of the vehicle when the camera device captures a current lane line image, and a second vector between a first point and a last point on the first lane line; If the angle between the first vector and the second vector is smaller than a set angle and the confidence level is greater than a set confidence level threshold, the line segment of the first lane line is used as a line segment of a newly constructed lane line in the road map.
8. The method according to any one of claims 1 to 3, It is characterized in that Before taking each lane line in the lane line data as a first lane line and determining whether each point on the first lane line has a corresponding projection point in a second lane line constructed in the road map, the method further includes: The lane lines indicated by the lane line data are sorted in descending order according to the number of points they contain, and the sorted order is used as the order for matching the lane lines in sequence.
9. A vehicle, It is characterized in that A controller is included, the controller comprising: a memory for storing machine-readable instructions; and A processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps of the road map construction method as described in any one of claims 1 to 8.
10. An electronic device, It is characterized in that include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the road map construction method as described in any one of claims 1 to 8 are performed.
11. A computer program product, It is characterized in that The computer program product stores a computer program, and when the computer program is executed by a processor, the steps of the road map construction method according to any one of claims 1 to 8 are executed.
Citation Information
Patent Citations
Sign and lane creation for high definition maps used for autonomous vehicles
CN111542860A
High-precision map lane line generation method and device and electronic equipment
CN113932796A
Lane line map construction method, computer equipment and storage medium
CN115661299A
Map updating method and device, automatic driving control method and device, medium and vehicle
CN115962787A
Autonomous vehicle localization method, apparatus and computer program using traffic lane information
KR102562031B1
