Map detection method and device, equipment and storage medium

Abstract

The invention provides a map detection method and device, equipment and a storage medium. The method comprises the steps that road identification data and map identification data in the view field of a vehicle are acquired; matching the road identification data with the map identification data to obtain a matching result; and determining whether the map identification data is accurate or not according to the matching result. According to the method and the device, whether the map identification data in the visual field range is accurate or not is detected by detecting whether the record of the map identification data is different from the actual road condition or not, whether the high-precision map is accurate or not can be detected in time, and effective data is provided to support in-time processing of abnormity of the high-precision map.

Description

Technical Field

[0001] The present application belongs to the field of high-precision map technology, and specifically relates to a map detection method, device, equipment and storage medium. Background Art

[0002] High-precision maps refer to high-precision maps that contain detailed road elements such as road shape, lane attributes, road markings, traffic signs, etc., and are widely used in scenarios including autonomous driving.

[0003] In the autonomous driving scenario, autonomous vehicles rely on high-precision maps for operations such as automatic positioning and automatic lane changing. Therefore, there are high requirements for the accuracy of high-precision maps.

[0004] However, due to reasons such as insufficient data updates, situations such as inconsistency between the actual lane and the vehicle indicated on the map will cause the automatic driving to fail. Based on this, there is an urgent need for a technology that can detect whether the high-precision map is accurate in a timely manner to support timely processing of map anomalies. Summary of the invention

[0005] The present application proposes a map detection method, device, equipment and storage medium, which can timely detect whether a high-precision map is accurate to support timely repair of abnormal map areas.

[0006] The first embodiment of the present application proposes a map detection method, including:

[0007] Acquire road sign data and map sign data within the vehicle's field of view;

[0008] Matching the road identification data with the map identification data to obtain a matching result;

[0009] Determine whether the map identification data is accurate based on the matching result.

[0010] In some embodiments of the present application, the matching of the road identification data with the map identification data includes:

[0011] Determine the type of the road sign element corresponding to the road sign data to obtain at least one element type;

[0012] For any element type, detecting whether the number of road identification elements of the element type is the same as the number of map identification elements of the element type; the road identification element refers to the identification element corresponding to the road identification data, and the map identification element refers to the identification element corresponding to the map identification data;

[0013] If the number of road sign elements of the element type is the same as the number of map sign elements of the element type, and the number is greater than or equal to 2, calculating the matching data between each road sign element of the element type and each map sign element respectively;

[0014] According to the matching data between each road sign element and each map sign element, for each road sign element, a map sign element matching the road sign element is determined.

[0015] In some embodiments of the present application, the calculating of matching data between each road identification element of the element type and each map identification element respectively includes:

[0016] For each road sign element, matching data between the road sign element and each map sign element is determined according to distance data between the road sign element and each map sign element.

[0017] In some embodiments of the present application, the at least one element type includes a line type; for the line type, determining the matching data between the road sign element and each map sign element according to the distance data between the road sign element and each map sign element respectively, comprises:

[0018] For any map identification element, calculating the length distance from the road identification element to the map identification element;

[0019] When the length distance is greater than a first preset threshold, calculating a width distance between the road identification element and the map identification element;

[0020] The weights of the road sign element and the map sign element are calculated based on the length distance and the width distance. The weights are used to characterize the degree of matching between the road sign element and the map sign element. The matching data between the road sign element and the map sign element includes the length distance, the width distance and the weight.

[0021] In some embodiments of the present application, the calculating the length distance from the road identification element to the map identification element includes:

[0022] Acquire multiple sampling points of the road sign element;

[0023] For any sampling point, mapping the sampling point to the map identification element;

[0024] If the mapping position of the sampling point overlaps with the map identification element, calculating the length distance between the sampling point and a previous sampling point adjacent to the sampling point, and the distance between the previous sampling point and the vehicle is less than the distance between the sampling point and the vehicle;

[0025] If the mapping position of the sampling point does not overlap with the map identification element, the length distance between the previous sampling point adjacent to the sampling point and the first sampling point is calculated to obtain the length distance from the road identification element to the map identification element.

[0026] In some embodiments of the present application, the calculating the width distance between the road identification element and the map identification element includes:

[0027] Determine sampling points within the length distance range in the road sign element;

[0028] Calculate the width distance between each sampling point and the map identification element respectively;

[0029] An average value of the width distances corresponding to the sampling points is calculated, where the average value is the width distance between the road identification element and the map identification element.

[0030] In some embodiments of the present application, the at least one element type further includes a surface mark type; for the surface mark type, determining the matching data between the road mark element and each map mark element respectively according to the distance data between the road mark element and each map mark element respectively includes:

[0031] Determine the center position of the road sign element to obtain a first center position;

[0032] Determine the center position of each of the map identification elements to obtain a second center position set;

[0033] The distance data between the first center position and each second center position in the second center position set are calculated to serve as the matching data between the road identification element and each map identification element.

[0034] In some embodiments of the present application, determining whether the map identification data is accurate according to the matching result includes:

[0035] If the number of road identification elements of the element type is different from the number of map identification elements of the element type, it is determined that the map identification data is inaccurate.

[0036] In some embodiments of the present application, determining whether the map identification data is accurate according to the matching result includes:

[0037] When the type of the road identification element is a line type, for any set of matching road identification elements and map identification elements, if at least one of the following items exists, it is determined that the line type map identification element in the map identification data is inaccurate:

[0038] The line type of the road sign element is different from the line type of the map sign element; the length distance between the road sign element and the map sign element is less than a second preset threshold; the width distance between the road sign element and the map sign element is less than a third preset threshold;

[0039] When the type of the road identification element is a surface identification type, for any set of matching road identification elements and map identification elements, if the symbol type of the road identification element is different from the symbol type of the map identification element, it is determined that the map identification element of the surface identification type in the map identification data is inaccurate.

[0040] In some embodiments of the present application, it also includes:

[0041] If it is determined that the map identification data is inaccurate, storing the map identification data in a positive sample data set;

[0042] If it is determined that the map identification data is accurate, storing the map identification data in a negative sample data set;

[0043] The accuracy rate and missed detection rate of detection are determined by verifying the map identification data in the positive sample data set; and the false detection rate of detection is determined by verifying the map identification data in the negative sample data set.

[0044] The second aspect of the present application provides a map detection device, including:

[0045] An acquisition module, used to acquire road sign data and map sign data within the field of view of the vehicle;

[0046] A matching module, used for matching the road identification data with the map identification data to obtain a matching result;

[0047] A determination module is used to determine whether the map identification data is accurate according to the matching result.

[0048] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0049] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement the method described in the first aspect above.

[0050] The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

[0051] In an embodiment of the present application, road marking data and map marking data within the field of view of the vehicle are obtained, wherein the road marking data refers to the data of the actual road marking collected by the vehicle, and the map marking data refers to the data displayed on the map within the field of view. Furthermore, the road marking data and the map marking data are matched to obtain a matching result, and whether the map marking data is accurate is determined based on the matching result. In other words, the actual road marking data collected in real time is used as the reference data, and by matching the data recorded on the map with the reference data, it is detected whether there is a difference between the two, so as to detect whether the map marking data within the field of view is accurate. It can be seen that the adoption of this technical solution can timely detect whether the high-precision map is accurate, and provide effective data to support the timely processing of high-precision map anomalies.

[0052] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0054] In the attached picture:

[0055] Figure 1 A method flow chart of a map detection method provided by an embodiment of the present application is shown;

[0056] Figure 2A A schematic diagram of a lane matching scenario provided by an embodiment of the present application is shown;

[0057] Figure 2B A schematic diagram of a lane matching scenario provided by another embodiment of the present application is shown;

[0058] Figure 3 A schematic diagram of a scene of ground mark matching provided by an embodiment of the present application is shown;

[0059] Figure 4A schematic diagram of the structure of a map detection device provided by an embodiment of the present application is shown;

[0060] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0061] Figure 6 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0062] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary 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 in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0063] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0064] First, the technical terms involved in this application are explained:

[0065] Road identification data refers to the data of road surface identification elements contained in the real-time actual road collected by the vehicle. Map identification data refers to the data of road surface identification elements contained in the high-precision map. Road identification data and map identification data can include vector data and attribute data of identification elements.

[0066] The identification elements involved on the road surface may include lane lines, turn arrows, speed limit signs, bus lanes, median strips, guide strips / spikes, etc. This application can divide the identification elements into different element types according to the geometric characteristics of each identification element, and match the road signs and map signs in different matching methods according to different element types.

[0067] Vector data refers to the description of geometric features such as the position and shape of identification elements in the form of vectors. The geometric features include at least one of length, elevation, curvature and angle.

[0068] Attribute data, also called semantic data, is used to describe the name, type, level, color, line type, etc. of identification elements.

[0069] Given the level of detail and completeness of road sign elements displayed on HD maps, HD maps are often used in autonomous driving scenarios. However, in existing technologies, HD maps are not updated in a timely manner, and up to now, there is no reliable technology to support the timely update of HD maps, resulting in the actual situation in some areas or sections not matching the HD map records, making it impossible for autonomous driving related tasks to proceed smoothly.

[0070] Based on this, in the technical solution provided by the embodiment of the present application, the vehicle can obtain road identification data and map identification data within the field of view, wherein the road identification data can refer to real-time actual road data. Furthermore, by detecting whether there is a difference between the record of the map identification data and the actual road conditions, it is possible to detect whether the map identification data within the field of view is accurate. In this way, it is possible to timely detect whether the high-precision map is accurate, and provide effective data to support the timely processing of high-precision map anomalies.

[0071] The execution subject of this technical solution can be any movable device that supports high-precision map detection, including vehicles, ships, aircraft or robots. Such devices can support map detection in the embodiment of this application through an autonomous driving system. The autonomous driving system can be provided with execution modules for related functions such as map image acquisition and detection algorithms. The detection algorithms involved in this technical solution can include topological algorithms and deep learning algorithms.

[0072] A map detection method, device and storage medium proposed according to an embodiment of the present application are described below in conjunction with the accompanying drawings. The technical solution of the present application is described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0073] See also Figure 1 , Figure 1 A method flow chart of a map detection method provided by an embodiment of the present application is shown, and the method specifically comprises the following steps:

[0074] Step S101, obtaining road identification data and map identification data within the field of vision of the vehicle.

[0075] The vehicle field of view may refer to the forward receptive field of the vehicle that can be captured by the vehicle camera.

[0076] It should be pointed out that the detection of map data can only be supported when the amount of road sign data reaches a certain level. The scene in which the vehicle camera collects road images is uncontrollable. In some scenes, there may be no obstacles within the forward receptive field of the vehicle, so the road signs in the collected road images can be relatively complete; in other scenes, there may be many obstacles within the forward receptive field of the vehicle, such as many other vehicles, so the road signs in the collected road images may be relatively small, for example, the length of the collected lane line is less than 0.5 meters.

[0077] Based on this, in some embodiments, after collecting a road image, data of all road sign elements in the road image can be extracted as an initial data set. Data of sign elements in the initial data set whose size is larger than a preset ratio of the standard size of the corresponding element is used as the road sign data of the present application.

[0078] The preset ratio can be flexibly set according to the requirements, for example, the preset ratio can be set to 40%, which will not be described in detail here.

[0079] For example, if the length of a lane line included in a road image is greater than 40% of the length of a standard lane line, the data of the lane line can be retained; if the length of the lane line is less than 40% of the length of the standard lane line, the length of the lane line is relatively small and may not be used to detect the map mark, and the data of the lane line can be deleted.

[0080] The map identification data may be a high-precision map pre-stored in the autonomous driving system, and a map data set corresponding to the area within the field of view of the vehicle.

[0081] Step S102: Match the road identification data with the map identification data to obtain a matching result.

[0082] Matching the road sign data with the map sign data may refer to determining the map sign corresponding to each road sign. Accordingly, the matching result may include a matched pair of road sign and map sign.

[0083] It should be noted that the ground identification elements can be divided into at least one element type according to their attributes, and then, for each element type, the road identification data of the element type can be matched with the map identification data of the element type.

[0084] In some embodiments, the at least one element type may include a line type and a ground sign type. The identification elements belonging to the line type may include, for example, lane lines, guide lines, etc.; the identification elements of the ground sign type may include, for example, turn arrows, speed limit signs, bus lane signs, etc.

[0085] Furthermore, for any element type, matching the road identification data of the element type with the map identification data of the element type can be implemented as follows: detecting whether the number of road identification elements of the element type is the same as the number of map identification elements of the element type. The road identification element here refers to the identification element corresponding to the road identification data, and the map identification element refers to the identification element corresponding to the map identification data. If the number of road identification elements of the element type is the same as the number of map identification elements of the element type, and the number is greater than or equal to 2, the matching data between each road identification element of the element type and each map identification element is calculated, and based on the matching data between each road identification element and each map identification element, for each road identification element, the map identification element that matches the road identification element is determined.

[0086] In other embodiments, if the number of road sign elements of the element type is different from the number of map sign elements of the element type, it means that the content of the actual road sign is different from that displayed on the map, and the map sign data can be determined to be inaccurate.

[0087] For line types, for example, the road marking data includes four lane lines, but the map marking data only includes three lane lines. It can be considered that there are lane line missing in the map marking data.

[0088] It should be pointed out that for an element type, even if the number of road identification elements and map identification elements is the same, the electronic device does not know the correspondence between each road identification element and each map identification element, that is, it does not know which identification element on the map should correspond to each road identification element. Based on this, if the number of road identification elements and map identification elements of this element type is 1, it can be determined that the two match. If the number of road identification elements and map identification elements of this element type is greater than or equal to 2, the matching data between each road identification element and each map identification element can be calculated to determine the map identification element on the map corresponding to each road identification element, that is, the map identification element that matches each road identification element, based on the matching data.

[0089] In some embodiments, for each road sign element, matching data between the road sign element and each map sign element may be determined based on distance data between the road sign element and each map sign element.

[0090] It should be understood that the road information corresponding to the identification elements of different element types has different meanings. For example, the road information corresponding to the lane line includes information such as lane width and whether a turn is allowed, while the numbers in the surface signs, for example, indicate that the vehicle speed limit is the speed specified by the number. Based on this, the implementation of distance data and matching data may be different for different element types.

[0091] For example, for line types, for any road sign element and any map sign element, the length distance of the road sign element mapped to the map sign element can be calculated, that is, the length of the overlap between the road sign element and the map sign element. It should be understood that when the length of the overlap between the road sign element and the map sign element is greater than a certain value, the possibility of the road sign element matching the map sign element is greater. If the length of the overlap between the road sign element and the map sign element is relatively small, the possibility of the road sign element matching the map sign element is relatively small. Based on this, when the length distance is greater than the first preset threshold, the width distance between the road sign element and the map sign element is calculated. Among them, the length distance and the width distance are two-dimensional parameters that characterize the degree of matching between the road sign element and the map sign element. Further, the weight of the road sign element and the map sign element can be calculated according to the length distance and the width distance, and the weight is used to characterize the degree of matching between the road sign element and the map sign element. The matching data between the road sign element and the map sign element includes the length distance, the width distance and the weight.

[0092] Exemplarily, according to a pairing algorithm such as the Kuhn-Munkers algorithm, pairs of road sign elements and map sign elements can be calculated based on all calculated weights, and each pair of road sign elements and map sign elements is a set of matching road sign elements and map sign elements.

[0093] For an example calculation of length distance, width distance and weight, see Figure 2A The description of the corresponding embodiments will not be expanded here.

[0094] It should be pointed out that for line-type sign elements, the overlap length between the road sign element and the map sign element is proportional to the weight, and the width distance is inversely proportional to the weight. The larger the overlap length and the smaller the width distance, the greater the weight of the road sign element and the map sign element, that is, the greater the matching degree between the two. For each road sign element, the map sign element with the largest weight can be used as the map sign element that matches the road sign element.

[0095] For another example, for any road sign type, the center position of the road sign element can be determined to obtain a first center position. Also, the center position of each map sign element can be determined to obtain a second center position set. Furthermore, the distance data between the first center position and each second center position in the second center position set can be calculated to serve as the matching data between the road sign element and each map sign element. Figure 3 The description of the corresponding embodiment is not expanded here. Afterwards, the map identification element corresponding to the second center position with the smallest distance can be used as the map identification element that matches the road identification element.

[0096] It can be seen that by adopting the present implementation method, the road sign elements and map sign elements corresponding to each element type can be matched according to the element type. On the one hand, the map sign elements corresponding to each road sign element when it is presented on the map can be obtained. On the other hand, the association data between the matched road sign elements and the road sign elements can be obtained, which is beneficial to detect the accuracy of the map sign data from the level of the sign elements.

[0097] Step S103: determining whether the map identification data is accurate according to the matching result.

[0098] Combined with the above description of the matching process, the matching results may include whether the number of road sign elements and map sign elements of each element type is the same, various distance data between any road sign element and a map sign element of the same element type, the pairing results of the road sign elements and the map sign elements, and other information.

[0099] Furthermore, if the number of road identification elements and map identification elements of any element type is the same, it is possible to detect whether the map identification data is accurate based on each pair of matched road identification elements and map identification elements.

[0100] In some embodiments, for each pair of matching road identification elements and map identification elements, the following dimensions may be detected:

[0101] First dimension: Based on the attribute data of the road sign element and the attribute data of the map sign element, detect whether the line type of the road sign element is the same as the line type of the map sign element. If the line type of the road sign element is different from the line type of the map sign element, for example, the road sign element is a straight lane line and the map sign element is a curved lane line; for example, the road sign element is a dotted lane line and the map sign element is a solid lane line, it can be considered that the lane line attribute corresponding to the map sign element is wrong.

[0102] Second dimension: Detect the length of the road marking element and the length of the map marking element based on the geometric features of the road marking element and the geometric features of the map marking element. If the length distance of the map marking element is less than the second preset threshold, it can be considered that the lane line corresponding to the map marking element is missing.

[0103] Exemplarily, the second preset threshold may be set to half of the lane standard line, such as 1.6 meters.

[0104] The third dimension: according to the geometric features of the road marking elements and the geometric features of the map marking elements, the width distance between two adjacent map marking elements and the width distance between two adjacent map marking elements are detected. If the width distance between any group of two adjacent map marking elements is less than the third threshold, it is determined that the width distance between the two map marking elements is inaccurate.

[0105] In other embodiments, for the surface marking type, for each pair of matching road marking elements and map marking elements, it is detected whether the symbol type of the road marking element is the same as the symbol type of the map marking element based on the attribute data of the road marking element and the attribute data of the map marking element; if the symbol type of the road marking element is different from the symbol type of the map marking element, it is determined that the map marking element of the surface marking type in the map marking data is inaccurate.

[0106] It should be understood that the above map identification data detection dimensions and inaccurate situations are only exemplary descriptions of the embodiments of the present application and do not constitute a limitation on the technical solution of the present application. In actual implementation, the element type may also include other types, and identification elements for different element types may also detect data from other dimensions, which is not limited here.

[0107] In an embodiment of the present application, road marking data and map marking data within the field of view of the vehicle are obtained, wherein the road marking data refers to the data of the actual road marking collected by the vehicle, and the map marking data refers to the data displayed on the map within the field of view. Furthermore, the road marking data and the map marking data are matched to obtain a matching result, and whether the map marking data is accurate is determined based on the matching result. In other words, the actual road marking data collected in real time is used as the reference data, and by matching the data recorded on the map with the reference data, it is detected whether there is a difference between the two, so as to detect whether the map marking data within the field of view is accurate. It can be seen that the adoption of this technical solution can timely detect whether the high-precision map is accurate, and provide effective data to support the timely processing of high-precision map anomalies.

[0108] The following describes the matching process of identification elements of different element types involved in the embodiments of the present application with reference to examples.

[0109] It should be noted that, for linear type identification elements, the length distance of the road identification element mapped to the map identification element can be calculated based on the sampling points. Specifically, multiple sampling points of the road identification element can be obtained, and for any sampling point, the sampling point is mapped to the map identification element. If the mapping position of the sampling point overlaps with the map identification element, the length distance between the sampling point and the previous sampling point adjacent to the sampling point is calculated, and the distance between the previous sampling point and the vehicle is less than the distance between the sampling point and the vehicle. If the mapping position of the sampling point does not overlap with the map identification element, the length distance between the previous sampling point adjacent to the sampling point and the first sampling point is calculated to obtain the length distance of the road identification element mapped to the map identification element.

[0110] The fact that the mapping position of the sampling point does not overlap with the map identification element may mean that the position to which the sampling point is mapped is on the extension line of the map identification element.

[0111] For example, Figure 2A The scene of lane matching is shown in the figure. The four solid lines in the scene are the actual lane lines of the collected road, which are recorded as lane line P1, lane line P2, lane line P3, and lane line P4. The four dotted lines are the lane lines of the map, which are recorded as map line M1, map line M2, map line M3, and map line M4. Further, the overlap distances between lane line P1 and M1, M2, M3, and M4 are calculated, the overlap distances between lane line P2 and M1, M2, M3, and M4 are calculated, the overlap distances between lane line P3 and M1, M2, M3, and M4 are calculated, and the overlap distances between lane line P4 and M1, M2, M3, and M4 are calculated.

[0112] Taking the calculation of the overlap distance between P1 and M1 as an example, P1 can be sampled from the vehicle direction to the vehicle forward direction to obtain multiple sampling points of P1. Afterwards, starting from the first sampling point, it can be mapped to M1. If the first sampling point is mapped to M1, the first sampling point is an overlap point. Afterwards, the first sampling point is mapped to M1. If the second sampling point is mapped to M1, the distance between the second sampling point and the first sampling point is calculated. Afterwards, the same operation is performed on each sampling point in sequence until the xth sampling point is mapped to the extension line of M1. Then, the distance from the x-1th sampling point to the first sampling point can be calculated to obtain the overlap distance between P1 and M1. Exemplarily, the distances between two adjacent sampling points can be accumulated to obtain the distance from the x-1th sampling point to the first sampling point. Wherein, x is an integer greater than or equal to 2.

[0113] The calculation of the overlap distances between P1 and M2, M3 and M4, and the calculation of the overlap distances between P2, P3 and P4 and M1, M2, M3 and M4, are the same as the above processing procedures and will not be described in detail here.

[0114] Furthermore, after obtaining 16 overlap distances, the lane lines associated with the overlap distances greater than the first preset threshold can be subjected to width distance calculation. Exemplarily, the sampling points within the length distance range of the road identification element can be determined, and then the width distances between each sampling point and the map identification element can be calculated respectively. The average value of the width distances corresponding to the sampling points is calculated, and the average value is the width distance between the road identification element and the map identification element.

[0115] For example, if the overlap distances between P1 and M1, M2 and M3 are all greater than the first preset threshold, the width distances between P1 and M1, M2 and M3 can be calculated respectively. Figure 2B As shown, the width distance dis from each sampling point to M1 can be calculated among the n sampling points of the overlap part of P1 and M1. i Then, calculate the average width distance corresponding to the n sampling points The average is the width distance between P1 and M1.

[0116] In some other embodiments, the average value of the width distance of n sampling points cannot well represent whether the two lines are completely parallel. Based on this, the mean square error σ can also be calculated as a parallelism test of P1 and M1. The mean square error σ can satisfy:

[0117] Of course, the calculation of the width distance between P1 and M2 and M3, as well as the width distance between other road lane lines and map lines whose overlap distance is greater than the first preset threshold, can refer to the calculation process between P1 and M1, which will not be elaborated here.

[0118] Furthermore, the weight of the matching degree between each lane line and each map line can be determined based on the overlap distance and the width distance. Among them, the greater the overlap distance and the smaller the width distance between the two lines, the greater the weight. Afterwards, the overlap distance, width distance and weight can be input into the Kuhn-Munkers algorithm to obtain the pairing result. The pairing result can be a matching line pair, such as (P1, M1), (P2, M2), etc. (P1, M1) can indicate that P1 matches M1, and (P2, M2) can indicate that P2 matches M2. Afterwards, the matching data of each line pair can be tested to determine whether the map identification data is accurate.

[0119] The above is the matching process for linear identification elements. For surface identification elements, matching can be performed based on the distance between center positions.

[0120] like Figure 3 As shown, a scene of surface mark matching is illustrated. The three solid-line boxes in this scene are the actual surface marks of the collected roads, denoted as mark D1, mark D2, and mark D3, and the three dotted-line boxes are the surface marks of the map. Further, the center positions of the above six marks can be determined, and then, the distances between the center position of D1 and the center positions of the three map surface marks (such as dotted-line boxes), the distances between the center position of D2 and the center positions of the three map surface marks (such as dotted-line boxes), and the distances between the center position of D3 and the center positions of the three map surface marks (such as dotted-line boxes) are calculated. For D1, D2, and D3, the map surface mark with the smallest distance is used as the matching surface mark.

[0121] It should be understood that the above matching process and matching algorithm are only exemplary descriptions of the embodiments of the present application and do not constitute a limitation on the technical solution of the present application. In actual implementation, other matching algorithms may also be included. This is not limited here.

[0122] By adopting this implementation method, the road sign elements and map sign elements corresponding to each element type are matched, not only the map sign elements corresponding to each road sign element when it is presented on the map are obtained, but also the association data between the matched road sign elements and the road sign elements are obtained, providing data support for the accuracy detection of the map sign data.

[0123] In addition, after determining that the map identification data is inaccurate, the map identification data can be stored in a positive sample data set. If the map identification data is determined to be accurate, the map identification data can be stored in a negative sample data set. Furthermore, the accuracy rate and missed detection rate of the detection can be determined by verifying the map identification data in the positive sample data set. And the false detection rate of the detection can be determined by verifying the map identification data in the negative sample data set.

[0124] In this way, offline detection can be provided, and the detection results can be verified, and the detection algorithm involved in the above-mentioned detection process of the embodiment of the present application can be optimized based on the verification results.

[0125] The present application also provides a map detection device, which is used to execute the map detection method provided in any of the above embodiments. Figure 4 As shown, the device includes: an acquisition module 41, a matching module 42 and a determination module 43.

[0126] The acquisition module 41 is used to acquire the road marking data and map marking data within the field of view of the vehicle; the matching module 42 is used to match the road marking data with the map marking data to obtain a matching result; the determination module 43 is used to determine whether the map marking data is accurate based on the matching result.

[0127] Optionally, the matching module 42 is further used for:

[0128] Determine the type of the road sign element corresponding to the road sign data to obtain at least one element type;

[0129] For any element type, detecting whether the number of road identification elements of the element type is the same as the number of map identification elements of the element type; the road identification element refers to the identification element corresponding to the road identification data, and the map identification element refers to the identification element corresponding to the map identification data;

[0130] If the number of road sign elements of the element type is the same as the number of map sign elements of the element type, and the number is greater than or equal to 2, calculating the matching data between each road sign element of the element type and each map sign element respectively;

[0131] According to the matching data between each road sign element and each map sign element, for each road sign element, a map sign element matching the road sign element is determined.

[0132] Optionally, the matching module 42 is further used for:

[0133] For each road sign element, matching data between the road sign element and each map sign element is determined according to distance data between the road sign element and each map sign element.

[0134] Optionally, the at least one element type includes a line type; for the line type, the matching module 42 is further configured to:

[0135] For any map identification element, calculating the length distance from the road identification element to the map identification element;

[0136] When the length distance is greater than a first preset threshold, calculating a width distance between the road identification element and the map identification element;

[0137] The weights of the road sign element and the map sign element are calculated based on the length distance and the width distance. The weights are used to characterize the degree of matching between the road sign element and the map sign element. The matching data between the road sign element and the map sign element includes the length distance, the width distance and the weight.

[0138] Optionally, the matching module 42 is further used to: obtain a plurality of sampling points of the road sign element;

[0139] For any sampling point, mapping the sampling point to the map identification element;

[0140] If the mapping position of the sampling point overlaps with the map identification element, calculating the length distance between the sampling point and a previous sampling point adjacent to the sampling point, and the distance between the previous sampling point and the vehicle is less than the distance between the sampling point and the vehicle;

[0141] If the mapping position of the sampling point does not overlap with the map identification element, the length distance between the previous sampling point adjacent to the sampling point and the first sampling point is calculated to obtain the length distance from the road identification element to the map identification element.

[0142] Optionally, the matching module 42 is further used to: determine a sampling point within the length distance range in the road sign element;

[0143] Calculate the width distance between each sampling point and the map identification element respectively;

[0144] An average value of the width distances corresponding to the sampling points is calculated, where the average value is the width distance between the road identification element and the map identification element.

[0145] Optionally, the at least one element type further includes a surface mark type; for the surface mark type, the matching module 42 is further configured to:

[0146] Determine the center position of the road sign element to obtain a first center position;

[0147] Determine the center position of each of the map identification elements to obtain a second center position set;

[0148] The distance data between the first center position and each second center position in the second center position set are calculated to serve as the matching data between the road identification element and each map identification element.

[0149] Optionally, the determination module 43 is further configured to determine that the map identification data is inaccurate if the number of road identification elements of the element type is different from the number of map identification elements of the element type.

[0150] Optionally, the determination module 43 is further configured to, when the type of the road identification element is a line type, determine that the line type map identification element in the map identification data is inaccurate if at least one of the following items exists for any set of matching road identification elements and map identification elements:

[0151] The line type of the road identification element is different from the line type of the map identification element; the length distance of the map identification elements is less than the second preset threshold; the width distance between any group of two adjacent map identification elements is less than the third threshold;

[0152] The determination module 43 is also used to determine that the map identification element of the surface identification type in the map identification data is inaccurate when the type of the road identification element is a surface identification type, for any set of matching road identification elements and map identification elements, if the symbol type of the road identification element is different from the symbol type of the map identification element.

[0153] Optionally, the map detection device further includes: a storage module and a verification module. The storage module is used to store the map identification data in a positive sample data set if it is determined that the map identification data is inaccurate; and is also used to store the map identification data in a negative sample data set if it is determined that the map identification data is accurate. The verification module is used to determine the accuracy rate and missed detection rate of detection by verifying the map identification data in the positive sample data set; and is also used to determine the false detection rate of detection by verifying the map identification data in the negative sample data set.

[0154] The map detection device provided in the embodiment of the present application and the map detection method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0155] The present application also provides an electronic device to perform the above map detection method. Figure 5 It shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 5 As shown, the electronic device 5 includes: a processor 500, a memory 501, a bus 502 and a communication interface 503, wherein the processor 500, the communication interface 503 and the memory 501 are connected via the bus 502; the memory 501 stores a computer program that can be run on the processor 500, and when the processor 500 runs the computer program, the map detection method provided in any of the aforementioned embodiments of the present application is executed.

[0156] The memory 501 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 503 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0157] The bus 502 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 501 is used to store programs, and the processor 500 executes the programs after receiving execution instructions. The map detection method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 500, or implemented by the processor 500.

[0158] The processor 500 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 500. The above processor 500 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 501, and the processor 500 reads the information in the memory 501 and completes the steps of the above method in combination with its hardware.

[0159] The electronic device provided in the embodiment of the present application and the map detection method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0160] The present application also provides a computer-readable storage medium corresponding to the map detection method provided in the above embodiment. Figure 6 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the map detection method provided by any of the aforementioned embodiments will be executed.

[0161] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0162] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the map detection method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0163] It should be noted that:

[0164] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0165] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0166] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0167] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A map detection method, characterized in that: include: Acquire road sign data and map sign data within the vehicle's field of view; Matching the road identification data with the map identification data to obtain a matching result; Determine whether the map identification data is accurate based on the matching result.

2. The method according to claim 1, characterized in that The matching of the road identification data with the map identification data includes: Determine the type of the road sign element corresponding to the road sign data to obtain at least one element type; For any element type, detecting whether the number of road identification elements of the element type is the same as the number of map identification elements of the element type; the road identification element refers to the identification element corresponding to the road identification data, and the map identification element refers to the identification element corresponding to the map identification data; If the number of road sign elements of the element type is the same as the number of map sign elements of the element type, and the number is greater than or equal to 2, calculating the matching data between each road sign element of the element type and each map sign element respectively; According to the matching data between each road sign element and each map sign element, for each road sign element, a map sign element matching the road sign element is determined.

3. The method according to claim 2, characterized in that The calculating of the matching data between each road identification element of the element type and each map identification element respectively includes: For each road sign element, matching data between the road sign element and each map sign element is determined according to distance data between the road sign element and each map sign element.

4. The method according to claim 3, characterized in that The at least one element type includes a line type; for the line type, determining the matching data between the road sign element and each map sign element according to the distance data between the road sign element and each map sign element, comprises: For any map identification element, calculating the length distance from the road identification element to the map identification element; When the length distance is greater than a first preset threshold, calculating a width distance between the road identification element and the map identification element; The weights of the road sign element and the map sign element are calculated based on the length distance and the width distance. The weights are used to characterize the degree of matching between the road sign element and the map sign element. The matching data between the road sign element and the map sign element includes the length distance, the width distance and the weight.

5. The method according to claim 4, characterized in that The calculating the length distance from the road identification element to the map identification element includes: Acquire multiple sampling points of the road sign element; For any sampling point, mapping the sampling point to the map identification element; If the mapping position of the sampling point overlaps with the map identification element, calculating the length distance between the sampling point and a previous sampling point adjacent to the sampling point, and the distance between the previous sampling point and the vehicle is less than the distance between the sampling point and the vehicle; If the mapping position of the sampling point does not overlap with the map identification element, the length distance between the previous sampling point adjacent to the sampling point and the first sampling point is calculated to obtain the length distance from the road identification element to the map identification element.

6. The method according to claim 4, characterized in that The calculating the width distance between the road identification element and the map identification element comprises: Determine sampling points within the length distance range in the road sign element; Calculate the width distance between each sampling point and the map identification element respectively; An average value of the width distances corresponding to the sampling points is calculated, where the average value is the width distance between the road identification element and the map identification element.

7. The method according to claim 3, characterized in that The at least one element type further includes a surface mark type; for the surface mark type, determining the matching data between the road mark element and each map mark element respectively according to the distance data between the road mark element and each map mark element respectively, comprises: Determine the center position of the road sign element to obtain a first center position; Determine the center position of each of the map identification elements to obtain a second center position set; The distance data between the first center position and each second center position in the second center position set are calculated to serve as the matching data between the road identification element and each map identification element.

8. The method according to claim 4 or 7, characterized in that: Determining whether the map identification data is accurate according to the matching result includes: When the type of the road identification element is a line type, for any set of matching road identification elements and map identification elements, if at least one of the following items exists, it is determined that the line type map identification element in the map identification data is inaccurate: The line type of the road identification element is different from the line type of the map identification element; the length distance of the map identification elements is less than the second preset threshold; the width distance between any group of two adjacent map identification elements is less than the third threshold; When the type of the road identification element is a surface identification type, for any set of matching road identification elements and map identification elements, if the symbol type of the road identification element is different from the symbol type of the map identification element, it is determined that the map identification element of the surface identification type in the map identification data is inaccurate.

9. A map detection device, characterized in that: include: An acquisition module, used to acquire road marking data and map marking data within the field of view of the vehicle; A matching module, used for matching the road identification data with the map identification data to obtain a matching result; A determination module is used to determine whether the map identification data is accurate according to the matching result.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 8.

Images