Method, device, medium device and product for calculating attributes of vulnerable road users

Abstract

The application discloses a weak road user attribute calculation method, device, medium, equipment and product, and belongs to the technical field of high-precision maps. The method comprises the following steps: acquiring a road type of a road connection line corresponding to a road section in a map, wherein the road type comprises a highway and an urban highway; determining a weak road user theoretical attribute of the road connection line within a predetermined range by using the road type; when the road type is a non-highway or a non-urban highway, the weak road user theoretical attribute of the road connection line is high; and when the road type is a highway or an urban highway, the weak road user theoretical attribute of the road connection line corresponding to the road section is determined according to a lane type and a ground object of the road connection line. The application realizes efficient and accurate identification of the weak road user attribute by automatically checking the difference between the map data and the theoretical value, guarantees the correctness and freshness of the data, and guarantees the safety of automatic driving.

Description

Technical Field

[0001] This application relates to the field of high-precision map technology, and in particular to a method, apparatus, storage medium, electronic device and computer program product for calculating the attributes of vulnerable road users, and an automatic detection and correction method for the attributes of vulnerable road users. Background Technology

[0002] The potential risks posed by vulnerable road users, such as pedestrians and non-motorized vehicle drivers, to autonomous driving safety and personal safety are crucial. Current technologies primarily rely on onboard hardware such as LiDAR, radio wave radar, and cameras to identify and detect the likelihood of vulnerable road users, and also utilize high-precision maps for auxiliary detection. However, in existing high-precision map-assisted detection technologies, the attributes of vulnerable road users are largely created, checked, and updated manually based on point clouds and street view photographs.

[0003] Manually creating, verifying, and updating the attributes of vulnerable road users in high-precision maps can lead to errors, omissions, incorrect scope of creation, or untimely updates due to variations in sampling ratios, personnel skill levels, judgment experience, and the update speed of other relevant on-site factors. These issues can result in inaccurate map representations and consequently compromise the safety of autonomous driving. Summary of the Invention

[0004] To address the problems of long update cycles and poor data quality of vulnerable road user attributes in existing technologies, this application mainly provides a method, apparatus, storage medium, electronic device, and computer program product for calculating vulnerable road user attributes, as well as an automatic detection and correction method for vulnerable road user attributes.

[0005] To achieve the above objectives, the first technical solution adopted in this application is a method for calculating the attributes of vulnerable road users, which includes: obtaining the road type of the road connector corresponding to the road segment in the map, wherein the road type includes expressways and urban expressways; using the road type, determining the theoretical attributes of vulnerable road users for the road connector within a predetermined range; wherein, when the road type is a non-expressway or non-urban expressway, the theoretical attributes of vulnerable road users for the road connector are high; and, when the road type is an expressway or urban expressway, determining the theoretical attributes of vulnerable road users for the road connector corresponding to the road segment based on the lane type and ground objects of the road connector, wherein the lane type includes bicycle lanes and parking lanes, and the ground objects include public transport stops, bicycle lanes within intersections, and pedestrian walkways.

[0006] Optionally, when the road segment is a non-shoulder lane, the corresponding road connectors are traversed to obtain the lane type corresponding to the road connectors; when all lane types are bicycle lanes, the theoretical attribute of the vulnerable road users corresponding to the road segment is high; and when some of the lane types are bicycle lanes, the search area is obtained by extending a predetermined width to both sides based on the position of the bicycle lane road connector, and the theoretical attribute of the vulnerable road users of the road connector is determined based on whether there is a guardrail in the search area.

[0007] Optionally, when the lane type corresponding to the road segment includes a parking lane, the theoretical attribute of the vulnerable road user of the road connector is high.

[0008] Optionally, when the ground object of the road connector corresponding to the road segment contains a public transportation stop, a first road connector consistent with the traffic direction is determined according to the traffic direction of the road segment; the two endpoints of the road connector of the public transportation stop are projected onto the first road connector to obtain two projection points; using the two endpoints and the two projection points, the search area is obtained, and the weak road user attribute of the road connector in the search area is theoretically high.

[0009] Optionally, when the ground object of the road connector corresponding to the road segment includes a pedestrian crossing, a second road connector consistent with the traffic direction is determined according to the traffic direction of the road segment; the road connector of the pedestrian crossing is projected onto the second road connector, and the two projection points farthest apart are obtained; the midpoint of the line connecting the two projection points is used as the reference point, and the theoretical attributes of the vulnerable road users of the road connector are determined using the reference point tracing method.

[0010] Optionally, when the ground object of the road connector corresponding to the road segment is a bicycle lane within the intersection, the road connector of the bicycle lane within the intersection is extended to both sides by a predetermined width to obtain the search area; when there is no road connector for a pedestrian crossing within the search area, a third road connector consistent with the direction of traffic is determined according to the traffic direction of the road segment, and the road connector of the bicycle lane within the intersection is projected onto the third road connector to obtain the two projection points that are furthest apart; the midpoint of the line connecting the two projection points is used as the reference point, and the theoretical attributes of the vulnerable road users of the road connector are determined using the reference point tracing method.

[0011] Optionally, when the ground object of the road connector corresponding to the road segment includes a pedestrian walkway, a fourth road connector consistent with the traffic direction of the road segment is determined; based on the projection positions of the starting and ending points of the pedestrian walkway's road connector on the fourth road connector, the road connectors are interlaced to obtain the road connector interlacing with the longest distance between the starting and ending points; the road connector interlacing is extended to both sides by a predetermined width to obtain the search area; based on whether there are guardrails in the search area, the theoretical attributes of the vulnerable road users of the road connector are determined.

[0012] Optionally, when a guardrail exists in the search area, the guardrail is projected onto the road connector path. Theoretically, the weak road user attributes of road connectors with guardrail projection points are low, and the weak road user attributes of road connectors without guardrail projection points are high.

[0013] The second technical solution adopted in this application is a calculation device for the attributes of vulnerable road users, which includes: an information acquisition module for acquiring the road type of the road connector corresponding to the road segment in the map, wherein the road type includes expressways and urban expressways; a theoretical value calculation module for determining the theoretical attributes of vulnerable road users of the road connector within a predetermined range using the road type; wherein, when the road type is a non-expressway or non-urban expressway, the theoretical attribute of vulnerable road users of the road connector is high; and, when the road type is an expressway or urban expressway, determining the theoretical attributes of vulnerable road users of the road connector corresponding to the road segment based on the lane type and ground objects of the road connector, wherein the lane type includes bicycle lanes and parking lanes, and the ground objects include public transport stops, bicycle lanes within intersections, and pedestrian walkways.

[0014] Optionally, the theoretical value calculation module includes a module for: when the road segment is a non-shoulder lane, traversing the corresponding road connectors to obtain the lane type corresponding to the road connector; when all lane types are bicycle lanes, the theoretical attribute of the vulnerable road user corresponding to the road segment is high; and when some of the lane types are bicycle lanes, extending a predetermined width to both sides based on the position of the road connector of the bicycle lane to obtain a search area, and determining the theoretical attribute of the vulnerable road user of the road connector based on whether there is a guardrail in the search area.

[0015] Optionally, the theoretical value calculation module includes a calculation module for calculating the theoretical attribute of the vulnerable road users of the road connector to be high when the lane type corresponding to the road segment includes a parking lane.

[0016] Optionally, the theoretical value calculation module includes a module for determining a first road connection line consistent with the traffic direction based on the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment contains a public transportation stop; projecting the two endpoints of the road connection line of the public transportation stop onto the first road connection line to obtain two projection points; and using the two endpoints and the two projection points to obtain a search area, wherein the theoretical attribute of the weak road user of the road connection line within the search area is high.

[0017] Optionally, the theoretical value calculation module includes a module for determining a second road connection line consistent with the traffic direction based on the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment contains a pedestrian crossing; projecting the road connection line of the pedestrian crossing onto the second road connection line and obtaining the two projection points that are furthest apart; and using the midpoint of the line connecting the two projection points as a reference point, using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connection line.

[0018] Optionally, the theoretical value calculation module includes a module for: when the ground object of the road connector corresponding to the road segment is a bicycle lane within an intersection, extending the road connector of the bicycle lane within the intersection to both sides by a predetermined width to obtain a search area; when there is no road connector for a pedestrian crossing within the search area, determining a third road connector consistent with the traffic direction of the road segment, and projecting the road connector of the bicycle lane within the intersection onto the third road connector to obtain the two farthest projection points; and using the midpoint of the line connecting the two projection points as a reference point, using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connector.

[0019] Optionally, the theoretical value calculation module includes: a module for determining a fourth road connection line consistent with the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment contains a pedestrian walkway; for connecting the road connection lines according to the projection positions of the starting and ending points of the road connection line on the fourth road connection line, obtaining the road connection line connection with the longest distance between the starting and ending points; for extending the road connection line connection to both sides by a predetermined width to obtain a search area; and for determining the theoretical attributes of the vulnerable road users of the road connection line based on whether there are guardrails in the search area.

[0020] Optionally, the theoretical value calculation module includes a module for projecting guardrails onto road connectors when guardrails exist in the search area. The theoretical attribute of the weak road users of road connectors with guardrail projection points in the road connectors is low, and the theoretical attribute of the weak road users of road connectors without guardrail projection points in the road connectors is high.

[0021] The third technical solution adopted in this application is an automatic detection and correction method for vulnerable road user attributes, which includes: obtaining the road type, lane type, and ground objects of the road connectors corresponding to road segments in the map, wherein the road type includes expressways and urban expressways, the lane type includes bicycle lanes and parking lanes, and the ground objects include public transport stops, bicycle lanes within intersections, and pedestrian walkways; using the road type, lane type, and ground objects, determining the theoretical attributes of vulnerable road users for the road connectors within a predetermined range; obtaining the actual attributes of vulnerable road users corresponding to the road connectors in the map based on the unique identification code of the road connectors; comparing and differentiating the theoretical attributes of vulnerable road users with the corresponding actual attributes of vulnerable road users, and correcting the actual attributes of vulnerable road users for the road connectors based on the comparison results.

[0022] Another technical solution adopted in this application is: providing a computer-readable storage medium storing a computer program / instruction, which is operated to execute the calculation method of vulnerable road user attributes in Scheme 1 or the automatic detection and correction method of vulnerable road user attributes in Scheme 3.

[0023] Another technical solution adopted in this application is: providing an electronic device, characterized in that it includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program / instruction executable by the at least one processor, and the at least one processor operates the computer program / instruction to execute the calculation method for vulnerable road user attributes in Scheme 1 or the automatic detection and correction method for vulnerable road user attributes in Scheme 3.

[0024] Another technical solution adopted in this application is: providing a computer program product, including a computer program / instruction, characterized in that, when the computer program / instruction is executed by a processor, it implements the calculation method for the weak road user attributes in Solution 1 or the automatic detection and correction method for the weak road user attributes in Solution 3.

[0025] The beneficial effects of the technical solution of this application are as follows: By combining the analysis of vulnerable road user scenarios and high-precision map product specifications, this application realizes the automatic identification and judgment of vulnerable road user areas, lays the foundation for automatically verifying the difference between theoretical data and real data, and automatically verifying the accuracy and freshness of data production, which can improve the quality of map data, further enhance the auxiliary information provided by the map obtained by autonomous vehicles, improve various detection indicators in the autonomous driving process, strengthen the detection power, improve the detection degree and accuracy of vulnerable road users, and more accurately and quickly predict risk areas. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of a specific implementation of a method for calculating the attributes of vulnerable road users according to this application;

[0028] Figure 2 This is a schematic diagram of a specific embodiment of a method for calculating the attributes of vulnerable road users according to this application;

[0029] Figure 3 This is a schematic diagram of a method for determining the attributes of vulnerable road users in a bicycle lane connecting line, which is a calculation method for the attributes of vulnerable road users according to this application.

[0030] Figure 4 This is a schematic diagram of a method for determining the weak road user attributes of a parking lane road connector, which is a method for calculating the attributes of weak road users according to this application.

[0031] Figure 5 This is a schematic diagram of a method for determining the attributes of vulnerable road users in a public transport stop road connector, which is a method for calculating the attributes of vulnerable road users according to the present application.

[0032] Figure 6 This is a schematic diagram of a method for determining pedestrian crossing reference points, which is a method for calculating the attributes of vulnerable road users according to this application.

[0033] Figure 7 This is a schematic diagram of a method for calculating the attributes of vulnerable road users and a method for determining the attributes of vulnerable road users in pedestrian crossing road connectors, which is a method proposed in this application.

[0034] Figure 8 This is a schematic diagram of a method for determining the weak road user attributes of a pedestrian walkway connector, which is a method for calculating the attributes of weak road users according to this application.

[0035] Figure 9 This is a schematic diagram of a specific embodiment of a calculation device for the attributes of vulnerable road users according to this application;

[0036] Figure 10 This is a schematic diagram of a specific implementation of a method for automatically detecting and correcting the attributes of vulnerable road users according to this application.

[0037] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0038] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0039] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0040] The method provided in this application is applicable to scenarios such as identification and detection of vulnerable road user attributes in high-precision maps and automatic correction of data errors.

[0041] The inventive concept of this application is to automatically verify and correct the discrepancies between Vulnerable Road Users (VRUs) attributes in product data and the real world during the production process by analyzing the scene characteristics of VRUs and their corresponding application scenarios in high-precision maps for autonomous driving. In VRU attribute identification, based on scene characteristics and autonomous driving use cases, methods such as projection, benchmark tracing, and traversal query are employed. VRUs are identified and their theoretical values ​​are recorded using road connectors in high-precision map data as basic units. The theoretical VRU values ​​and actual VRU values ​​in the data are uniquely associated and consistent based on the unique identification code of the road connector. If discrepancies occur, the actual VRU values ​​are automatically corrected to their theoretical values ​​to match the actual situation, improving data accuracy and timeliness.

[0042] Definitions: 1. Vulnerable Road User (VRU): refers to road traffic participants who lack safety protection, such as pedestrians and non-motorized vehicle drivers.

[0043] 2. Definition of high-precision map products: refers to the attributes assigned to the road connectors that make up the map when creating a high-precision map. These attributes are determined by the actual use of the road connectors or by their classification.

[0044] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other to form new embodiments. The same or similar ideas or processes described in one embodiment may not be repeated in other embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0045] Figure 1 This paper illustrates one implementation of a method for calculating the attributes of vulnerable road users according to this application.

[0046] Figure 1 The method for calculating the attributes of vulnerable road users shown includes: step S101, obtaining the road type of the road connecting line corresponding to the road segment in the map, wherein the road type includes expressways and urban expressways;

[0047] Step S102 involves determining the theoretical attributes of vulnerable road users for road connectors within a predetermined range using road type. Specifically, when the road type is a non-expressway or non-urban expressway, the theoretical attribute of vulnerable road users for the road connector is high. Furthermore, when the road type is an expressway or urban expressway, the theoretical attributes of vulnerable road users for the corresponding road connector are determined based on the lane type and ground objects. Lane types include bicycle lanes and parking lanes, and ground objects include public transport stops, bicycle lanes within intersections, and pedestrian walkways. This specific embodiment accurately calculates the theoretical attributes of vulnerable road users using information such as the usage attributes of road connectors, avoiding manual intervention in the calculation process, reducing labor costs, and improving data quality and calculation efficiency.

[0048] Specifically, in practical applications, when the vulnerable road user attribute of a certain road segment is high, it means that vulnerable road users are likely to appear on this road segment, the driving risk is relatively high, and caution should be exercised, and emergency avoidance should be carried out if necessary; when the vulnerable road user attribute of a certain road segment is low, it means that the probability of vulnerable road users appearing on this road segment is low.

[0049] Based on the definition of high-precision map products, this application calculates the theoretical attributes of vulnerable road users in high-precision map data. It further compares and determines the correctness of the actual attributes of vulnerable road users in existing high-precision map data by differential analysis. When the actual attributes of vulnerable road users in high-precision map data are incorrect, the actual attributes of vulnerable road users in high-precision map data are updated according to the calculated theoretical attributes of vulnerable road users. This ensures the authenticity and accuracy of the information obtained by autonomous vehicles, thereby ensuring the safety and reliability of autonomous driving. Here, the definition of high-precision map products refers to the ground objects of road type and lane type of road connectors.

[0050] When calculating the theoretical attributes of vulnerable road users corresponding to a road segment, this application determines the road type, lane type, and ground objects of the road connectors included in the road segment. Based on the different road types, lane types, and ground objects, different calculation methods are used to obtain the theoretical attributes of vulnerable road users of the road connectors in the road segment. Specifically, this application calculates the theoretical attributes of vulnerable road users of the road connectors based on the road segment. That is, when the road connectors are not completely within a certain road segment, only the theoretical attributes of vulnerable road users of the road connectors in the segment are calculated.

[0051] exist Figure 1 In the illustrated embodiment, the method for calculating the vulnerable road user attributes includes step S101, which involves obtaining the road type of the road connecting lines corresponding to the road segment in the map. The road type includes expressways and urban expressways. This step, by obtaining the map product definition, lays the foundation for more accurate calculation of the vulnerable road user attributes of the road segment and achieves automatic acquisition and calculation of these attributes, avoiding errors caused by manual calculation.

[0052] Specifically, by using high-precision maps, the road type, lane type, and ground objects of the road connectors in the road segment can be obtained, so as to automatically identify and calculate the theoretical attributes of the vulnerable road users corresponding to the road segment based on the characteristics of the road connectors, thereby reducing the manual cost in the calculation process.

[0053] exist Figure 1In the specific embodiment shown, the method for calculating the vulnerable road user attribute further includes step S102, which uses the road type to determine the theoretical vulnerable road user attribute of the road connector within a predetermined range. Specifically, when the road type is a non-expressway or non-urban expressway, the theoretical vulnerable road user attribute of the road connector is high. And, when the road type is an expressway or urban expressway, the theoretical vulnerable road user attribute of the corresponding road connector is determined based on the lane type and ground objects of the road connector. The lane type includes bicycle lanes and parking lanes, and the ground objects include public transport stops and sidewalks. This specific embodiment accurately calculates the theoretical vulnerable road user attribute using information such as the usage attributes of the road connector, avoiding manual intervention in the calculation process, reducing labor costs, and improving data quality and calculation efficiency.

[0054] For example, such as Figure 2 Based on the road type of the road connector, the theoretical attributes of the vulnerable road users in the road segment are calculated. When the road type is a non-expressway or non-urban expressway, the theoretical attributes of the vulnerable road users in the road segment are high. When the road type is an expressway or urban expressway, the theoretical attributes of the vulnerable road users for the corresponding road connector are determined based on the lane type and ground object of the road connector. The calculation methods for the theoretical attributes of the vulnerable road users for road segments corresponding to road connectors with different lane types and ground objects are different. Specific calculation methods are as follows: Figure 2 ,in Figure 2 The calculation order of the theoretical attributes of vulnerable road users for each lane type and road connection line of the ground object is only illustrative, and the specific calculation order is not limited in this application.

[0055] In one specific embodiment of this application, step S102 includes: when the road segment is a non-shoulder lane, traversing the road connectors corresponding to the road segment to obtain the lane type corresponding to the road connectors; when all lane types are bicycle lanes, the theoretical attribute of the vulnerable road user corresponding to the road segment is high; and when some of the lane types are bicycle lanes, using the position of the road connector of the bicycle lane as a reference, extending a predetermined width to both sides to obtain a search area, and determining the theoretical attribute of the vulnerable road user of the road connector based on whether there is a guardrail in the search area.

[0056] Specifically, when the road connector corresponding to a road segment is a non-shoulder lane, the lane type of the road connector corresponding to the road segment is obtained through traversal query. When the lane type of the road connector corresponding to a certain road segment is all bicycle lane, the VRU attribute of the road connector in the current road segment is high. When the lane type of the road connector corresponding to a certain road segment contains other lane types or other ground objects, the VRU attribute of the road connector in the road segment is calculated in different ways according to the relative position between the bicycle lane and other lanes. Here, the bicycle lane is not restricted to lanes that can only be used for bicycles. Lanes that allow other non-motorized vehicles can also use this technique to calculate the corresponding VRU attribute.

[0057] When the bicycle lane is outside other lanes, that is, when both lanes on both sides of the bicycle lane are non-bicycle lanes, all points on the road connector of the bicycle lane in the road segment are projected onto the non-bicycle lane road connector on both sides. Then, the VRU attribute of the projected part of the non-bicycle lane road connector is high, and the VRU attribute of the unprojected part is low.

[0058] When the bike lane is outside other lanes, the search area is defined by widening the shared lane boundary line between the bike lane and other lanes by 0.5 meters to the left and right. If there is no guardrail within the search area, the VRU attribute of the road connector corresponding to the current road segment should be high; if... Figure 3 If a guardrail object exists within the search area, the shape points corresponding to the guardrail are projected onto the road connection line using the projection method. The VRU attribute of the part of the road connection line with the projected point is low, and the VRU attribute of the part without the projected point should be high.

[0059] In one specific embodiment of this application, step S102 includes the following: when the lane type corresponding to the road segment includes a parking lane, the theoretical attribute of the vulnerable road user of the road connector is high.

[0060] Specifically, such as Figure 4 The system iterates through the lane types of the road connectors corresponding to the road segments to obtain the lane types. When a parking lane exists in the lane type corresponding to a certain road segment, the VRU attribute of the road connector in the current road segment should be high.

[0061] In one specific embodiment of this application, step S102 includes: when the ground object of the road connection line corresponding to the road segment contains a public transportation stop, determining a first road connection line consistent with the traffic direction according to the traffic direction of the road segment; projecting the two endpoints of the road connection line of the public transportation stop onto the first road connection line to obtain two projection points; using the two endpoints and the two projection points to obtain a search area, in which the weak road user theoretical attribute of the road connection line within the search area is high.

[0062] Specifically, based on the travel direction of the road connector line in the segment where the public transport stop is located, the endpoints of the public transport stop's road connector line are projected onto the road connector line of the public transport stop in the travel direction using a projection method. The VRU attribute within the range of the two farthest projection points on the road connector line in the travel direction should be high, while the VRU attribute of the road connector line outside the projection range within the segment should be low. For example... Figure 5 The endpoints of the road connectors DB and AC at the public transport stops are projected onto the road connectors in the direction of travel as a, b, c, and d, respectively. The distance between projection points a and d is the greatest. Therefore, the VRU attribute within the range of the road connector ad corresponding to this road segment should be high, and the VRU attribute of the road connector outside the projection range of ad should be low.

[0063] In one specific embodiment of this application, step S102 includes: when the ground object of the road connection line corresponding to the road segment contains a pedestrian crossing, determining a second road connection line consistent with the traffic direction according to the traffic direction of the road segment; projecting the road connection line of the pedestrian crossing onto the second road connection line and obtaining the two projection points that are furthest apart; taking the midpoint of the line connecting the two projection points as a reference point, and using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connection line.

[0064] Specifically, such as Figure 6 When determining the reference point, since pedestrian crossings in actual sites and map operations are mostly irregular polygons, the pedestrian crossing can be vertically projected onto the road connection line corresponding to different traffic directions. Specifically, the two outermost intersections of the road connection line with the pedestrian crossing are taken as the two farthest projection points. The coordinates of the center point corresponding to these two farthest projection points are then calculated, and this center point is used as the reference point. The reference point coordinates (X...) are... 基准点 Y 基准点 The calculation method for ) is as follows: The above X a1 and X a2 These are the x-coordinates and y-coordinates of the two farthest projection points, respectively. a1 and Y a2 These are the ordinates of the two projection points that are furthest apart.

[0065] Starting from the reference point, the road segments are traced along both the direction of travel and the opposite direction of travel, and the length of the trace is calculated. When the traced length is the predetermined length, the tracing stops and the position coordinates (X, Y, X) of the current tracing point are recorded. 追溯点 Y 追溯点 ), where the string length is (X 基准点 Y 基准点 ) and (X追溯点 Y 追溯点 The length of the curve segment between the reference point and the trace point. The VRU attribute is high for the crossover portion between the reference point and the trace point, and low for the crossover portion outside the crossover portion between the reference point and the trace point. Preferably, the predetermined length is 200 meters.

[0066] For example, such as Figure 7 For the second road connector, i.e., road connector a (LINK a), the two projection points farthest apart among the projection points of the various shapes of the pedestrian crossing onto LINK a are a1 and a2. Based on the positions of a1 and a2, the midpoint a on LINK a is calculated, and point a is the reference point for tracing. According to the traffic direction of LINK a and the opposite direction of LINK a, the road connectors within a 200m range are traced forward and backward from point a. The VRU attribute corresponding to the road connectors within this range is high, meaning the curve length from point a to any point on LINK a, LINK b, LINK c, LINK d, LINK k, LINK l, and LINK f is less than 200 meters. Therefore, the VRU attribute of LINK a, LINK b, LINK c, LINK d, LINK k, LINK l, and LINK f should be high.

[0067] In one specific embodiment of this application, step S102 includes: when the ground object of the road connector corresponding to the road segment is a bicycle lane within an intersection, extending the road connector of the bicycle lane within the intersection to both sides by a predetermined width to obtain a search area; when there is no road connector for a pedestrian crossing within the search area, determining a third road connector consistent with the direction of travel of the road segment, and projecting the road connector of the bicycle lane within the intersection onto the third road connector to obtain the two projection points that are furthest apart; using the midpoint of the line connecting the two projection points as a reference point, and using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connector.

[0068] Specifically, when a road segment includes a bicycle lane within an intersection, the midpoint between the two projection points with the furthest distance between them on the road connection line corresponding to the traffic direction of the road segment is used as the reference point, and the road connection line within a range of 50m is traced back.

[0069] If a pedestrian crossing exists within a 50m radius of the road connector, the VRU information related to the bicycle lane at that intersection will not be calculated again, because the VRU information for the road connector at that intersection has already been calculated during the pedestrian crossing calculation. However, when the calculation of the bicycle lane at the intersection is performed before the calculation of the pedestrian crossing, the calculation method described above for when a pedestrian crossing exists will be used. Preferably, the calculation of intersections containing pedestrian crossings is performed before those containing bicycle lanes, in order to reduce the amount of calculation.

[0070] If there is no pedestrian crossing within a 50m range, the benchmark point tracing method is used to calculate the road connector within a 50m range of the benchmark point to determine the theoretical attributes of the vulnerable road users of the road connector. The specific calculation method is the same as the calculation method of the benchmark point and tracing point when the road segment includes a pedestrian crossing.

[0071] In one specific embodiment of this application, step S102 includes: when the ground object of the road connection line corresponding to the road segment includes a pedestrian walkway, determining a fourth road connection line consistent with the travel direction of the road segment; according to the projection positions of the starting point and ending point of the road connection line on the fourth road connection line, connecting the road connection lines to obtain the road connection line connection with the longest distance between the starting point and the ending point; extending the road connection line connection to both sides by a predetermined width to obtain a search area; and determining the theoretical attributes of the vulnerable road users of the road connection line based on whether there are guardrails in the search area.

[0072] Furthermore, when a guardrail exists in the search area, the guardrail is projected onto the road connector path. Theoretically, the weak road user attributes of road connectors with guardrail projection points are low, while the weak road user attributes of road connectors without guardrail projection points are high.

[0073] Specifically, when the ground object of the road connector line corresponding to the road segment includes a pedestrian walkway, the starting and ending points of the pedestrian walkway's road skeleton line are projected onto the corresponding starting and ending points of the road skeleton line in the travel direction of the road segment. By interlacing the road skeleton lines in the travel direction of the road segment, the two projection points of the pedestrian walkway's starting and ending points on the interlacing line are obtained. Using the road connector line connecting these two projection points as a baseline, a predetermined width is extended to both sides to obtain the search area; preferably, the predetermined width is 1 meter. Furthermore, when there are no guardrail objects in the search area, the VRU attribute of the road connector line connecting these two projection points should be high; if there are guardrail objects in the search area, the points corresponding to the guardrail objects are projected onto the road skeleton line in the travel direction. The VRU attribute of the road connector line containing the projection points in the interlacing line is low, while the VRU attribute of the road connector line without projections and within the two farthest projection points mentioned above should be high.

[0074] The specific projection calculation method is as follows: Project the pedestrian walkway connecting line perpendicularly onto the corresponding traffic direction connecting line of the road segment, and obtain the coordinates of the projection points corresponding to the two endpoints of the pedestrian walkway connecting line. Using the coordinates of the endpoint projection points, calculate the distances between all endpoint projection points, and sort the calculated distances. That is, when the endpoint projection points are 1, 2, 3, and 4, calculate the distances between 1 and 2, 1 and 3, and 1 and 4 respectively. Based on the farthest projection distance, obtain the coordinates (X, Y) of the two projection points furthest apart on the path. m Y m ), (X n Y n Based on the unique identifier of the road connection point corresponding to the two farthest projection points, the lane boundary of the outermost lane corresponding to this road segment is obtained, that is, the lane boundary with the largest boundary number of the connecting road line of the road segment connected to the current road segment; using the outermost lane boundary as the baseline, the search area is obtained by extending 1 meter in a direction perpendicular to the outermost lane line. Guardrails are searched within the search area. If a guardrail exists within the search area, the point corresponding to the guardrail object is vertically projected onto the connecting road line of the current road segment's traffic direction, and the coordinates (X) of the farthest projection point corresponding to the guardrail are obtained. p Y p ) and (X q Y q ), projection point (X) p Y p ) and (X q Y q The road connecting lines between the two points represent the maximum range of the guardrail projection within the search area.

[0075] When a guardrail exists within the search area, the attributes of the VRU corresponding to the road segment are obtained by differencing the coordinates of the pedestrian walkway's projection onto the connecting line in the travel direction with the coordinates of the guardrail's projection within the search area. Specifically, the attributes of the VRU corresponding to the road segment are obtained by differencing the projection ranges of the pedestrian walkway and guardrail onto the connecting line in the travel direction corresponding to the road segment. This means that the VRU's attributes are determined when the connecting line is the point where the two projection points (X, Y, X) of the pedestrian walkway on the connecting line in the travel direction are the farthest apart. m Y m ) and (X n Y n The coordinates of the projection point (X) between and farthest from the guardrail. p Y p ) and (X q Y q If it is not a high VRU, then its corresponding VRU attribute is high.

[0076] For example, such as Figure 8If there is no guardrail object within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of projection point a to projection point N1 on LINK1, then the VRU attribute of the road connection line within the range of point a to point N1 in LINK1 should be high. If there is no guardrail object projection within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of point N1 to point c on LINK2, then the VRU attribute of the road connection line within the range of point N1 to point c in LINK2 should be high. If there is a guardrail object projection within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of point c to point d in LINK2, then the VRU attribute of the road connection line within the range of point c to point d in LINK2 should be low.

[0077] In one specific embodiment of this application, the method for calculating the vulnerable road user attribute further includes comparing and differentiating the theoretical value of the vulnerable road user attribute with the corresponding actual value of the vulnerable road user, and correcting the actual value of the vulnerable road user for the road connector based on the comparison result. This specific embodiment, by automatically verifying the difference between high-precision map data and real-world theoretical values, and automatically determining and correcting the correctness of the actual vulnerable road user attribute in the data according to product specifications, lays the foundation for efficient and accurate identification and judgment of vulnerable road user attributes during autonomous driving, ensuring the accuracy and freshness of the data acquired by autonomous vehicles, and guaranteeing the safety and performance of autonomous driving.

[0078] In a specific instance of this application, during practical application, errors in preliminary work, changes in related elements, or alterations in road information can lead to mismatches in VRU attributes. This can result in erroneous data acquired by autonomous vehicles, thereby affecting the safety of autonomous driving. Therefore, accurate and timely Vulnerable Road User (VRU) attributes are essential for autonomous driving technology. This application calculates and records the theoretical attributes of Vulnerable Road Users (VRUs) on a high-precision map based on the unique identification code of road connectors, and compares the calculated theoretical attributes with the actual attributes of VRUs stored in the map data. When the theoretical attributes and actual attributes of VRUs differ, the theoretical attributes are assigned to the actual attributes of the VRUs, becoming the actual attributes of the VRUs for the road connectors.

[0079] For example, as shown in Table 1, the theoretical value and actual value of VRU are correlated and differentiated according to LINK_ID. When the theoretical value and actual value of VRU corresponding to a LINK_ID are inconsistent, the actual value attribute of VRU is corrected and assigned.

[0080] Table 1

[0081] LINK_ID VRU Theoretical Value VRU_actual value Does it need to be corrected? VRU_Correction Result LINK a HIGH HIGH no LINK b HIGH LOW yes HIGH LINK c LOW LOW no LINK d LOW HIGH yes LOW

[0082] Figure 9 This application illustrates a specific embodiment of a computing device for calculating the attributes of vulnerable road users.

[0083] exist Figure 9 In the specific implementation shown, the calculation device for the attributes of vulnerable road users mainly includes: an information acquisition module 901, used to acquire the road type of the road connecting line corresponding to the road segment in the map, wherein the road type includes expressways and urban expressways;

[0084] The theoretical value calculation module 902 uses the road type to determine the theoretical attributes of vulnerable road users for road connectors within a predetermined range. Specifically, when the road type is a non-expressway or non-urban expressway, the theoretical attributes of vulnerable road users for the road connector are high. When the road type is an expressway or urban expressway, the theoretical attributes of vulnerable road users for the corresponding road connector are determined based on the lane type and ground objects of the road connector. The lane type includes bicycle lanes and parking lanes, and the ground objects include public transport stops, bicycle lanes within intersections, and pedestrian walkways.

[0085] In one specific embodiment of this application, the theoretical value calculation module includes: when the road segment is a non-shoulder lane, traversing the road connectors corresponding to the road segment to obtain the lane type corresponding to the road connector; when all lane types are bicycle lanes, the theoretical attribute of the vulnerable road user corresponding to the road segment is high; and when some of the lane types are bicycle lanes, using the position of the road connector of the bicycle lane as a reference, extending a predetermined width to both sides to obtain a search area, and determining the theoretical attribute of the vulnerable road user of the road connector based on whether there is a guardrail in the search area.

[0086] Specifically, the module works as follows: When the road connector corresponding to a road segment is a non-shoulder lane, the module iterates through the road connectors to obtain their lane types. If all lane types of the road connectors for a given road segment are bicycle lanes, the VRU attribute of the road connectors in that segment is high. If other lane types or other ground objects exist for the road connectors for a given road segment, the VRU attribute of the road connectors in that segment is calculated using different methods based on the relative positions of the bicycle lane and other lanes. Note that the bicycle lanes here are not limited to bicycles; lanes allowing other non-motorized vehicles can also have their VRU attributes calculated using this technique. When the bicycle lane is outside other lanes (i.e., both sides of the bicycle lane are non-bicycle lanes), all points on the road connector of the bicycle lane within the segment are projected onto the non-bicycle lane road connectors on both sides. The projected portion of the non-bicycle lane road connector has a high VRU attribute, while the unprojected portion has a low VRU attribute. When the bike lane is outside other lanes, the search area is defined by widening the shared lane boundary line between the bike lane and other lanes by 0.5 meters to the left and right. If there is no guardrail within the search area, the VRU attribute of the road connector corresponding to the current road segment should be high; if... Figure 3 If a guardrail object exists within the search area, the shape points corresponding to the guardrail are projected onto the road connection line using the projection method. The VRU attribute of the part of the road connection line with the projected point is low, and the VRU attribute of the part without the projected point should be high.

[0087] In one specific embodiment of this application, the theoretical value calculation module includes a calculation module for calculating the theoretical attribute of the vulnerable road users of the road connector to be high when the lane type corresponding to the road segment includes a parking lane.

[0088] Specifically, the specific working method of this module is as follows: Figure 4 The system iterates through the lane types of the road connectors corresponding to the road segments to obtain the lane types. When a parking lane exists in the lane type corresponding to a certain road segment, the VRU attribute of the road connector in the current road segment should be high.

[0089] In one specific embodiment of this application, the theoretical value calculation module includes a module for determining a first road connection line consistent with the traffic direction based on the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment contains a public transportation stop; projecting the two endpoints of the road connection line of the public transportation stop onto the first road connection line to obtain two projection points; and using the two endpoints and the two projection points to obtain a search area, wherein the theoretical attribute of the weak road user of the road connection line in the search area is high.

[0090] Specifically, the module works as follows: based on the travel direction of the road connector line in the segment where the public transport stop is located, the endpoints of the public transport stop's road connector line are projected onto the road connector line of the public transport stop in the travel direction using a projection method. The VRU attribute within the range of the two farthest projection points on the road connector line in the travel direction should be high, while the VRU attribute of the road connector line outside the projection range within the segment should be low. For example... Figure 5 The endpoints of the road connectors DB and AC at the public transport stops are projected onto the road connectors in the direction of travel as a, b, c, and d, respectively. The distance between projection points a and d is the greatest. Therefore, the VRU attribute within the range of the road connector ad corresponding to this road segment should be high, and the VRU attribute of the road connector outside the projection range of ad should be low.

[0091] In one specific embodiment of this application, the theoretical value calculation module includes a module for determining a second road connection line consistent with the traffic direction based on the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment contains a pedestrian crossing; projecting the road connection line of the pedestrian crossing onto the second road connection line and obtaining the two projection points that are furthest apart; and using the midpoint of the line connecting the two projection points as a reference point, using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connection line.

[0092] Specifically, the specific working method of this module is as follows: Figure 6 When determining the reference point, since pedestrian crossings in actual sites and map operations are mostly irregular polygons, the pedestrian crossing can be vertically projected onto the road connection line corresponding to different traffic directions. Specifically, the two outermost intersections of the road connection line with the pedestrian crossing are taken as the two farthest projection points. The coordinates of the center point corresponding to these two farthest projection points are then calculated, and this center point is used as the reference point. The reference point coordinates (X...) are... 基准点 Y 基准点 The calculation method for ) is as follows: The above X a1 and X a2 These are the x-coordinates and y-coordinates of the two farthest projection points, respectively. a1 and Y a2 These are the ordinates of the two projection points that are furthest apart.

[0093] Starting from the reference point, the road segments are traced along both the direction of travel and the opposite direction of travel, and the length of the trace is calculated. When the traced length is the predetermined length, the tracing stops and the position coordinates (X, Y, X) of the current tracing point are recorded. 追溯点 Y 追溯点 ), where the string length is (X 基准点Y 基准点 ) and (X 追溯点 Y 追溯点 The length of the curve segment between the reference point and the trace point. The VRU attribute is high for the crossover portion between the reference point and the trace point, and low for the crossover portion outside the crossover portion between the reference point and the trace point. Preferably, the predetermined length is 200 meters.

[0094] For example, such as Figure 7 For the second road connector, i.e., road connector a (LINK a), the two projection points farthest apart among the projection points of the various shapes of the pedestrian crossing onto LINK a are a1 and a2. Based on the positions of a1 and a2, the midpoint a on LINK a is calculated, and point a is the reference point for tracing. According to the traffic direction of LINK a and the opposite direction of LINK a, the road connectors within a 200m range are traced forward and backward from point a. The VRU attribute corresponding to the road connectors within this range is high, meaning the curve length from point a to any point on LINK a, LINK b, LINK c, LINK d, LINK k, LINK l, and LINK f is less than 200 meters. Therefore, the VRU attribute of LINK a, LINK b, LINK c, LINK d, LINK k, LINK l, and LINK f should be high.

[0095] In one specific embodiment of this application, the theoretical value calculation module includes a module for: when the ground object of the road connector corresponding to the road segment is a bicycle lane within an intersection, extending the road connector of the bicycle lane within the intersection to both sides by a predetermined width to obtain a search area; when there is no road connector for a pedestrian crossing within the search area, determining a third road connector consistent with the traffic direction of the road segment, and projecting the road connector of the bicycle lane within the intersection onto the third road connector to obtain the two farthest projection points; and using the midpoint of the line connecting the two projection points as a reference point, using the reference point tracing method to determine the theoretical attributes of the vulnerable road users of the road connector.

[0096] Specifically, the module works as follows: when the road segment includes a bicycle lane within an intersection, based on the road connection line corresponding to the traffic direction of the road segment, the midpoint between the two projection points with the farthest projection distance of the bicycle lane on the road connection line is used as the reference point, and the road connection line within a range of 50m is traced back.

[0097] If a pedestrian crossing exists within a 50m radius of the road connector, the VRU information related to the bicycle lane at that intersection will not be calculated again, because the VRU information for the road connector at that intersection has already been calculated during the pedestrian crossing calculation. However, when the calculation of the bicycle lane at the intersection is performed before the calculation of the pedestrian crossing, the calculation method described above for when a pedestrian crossing exists will be used. Preferably, the calculation of intersections containing pedestrian crossings is performed before those containing bicycle lanes, in order to reduce the amount of calculation.

[0098] If there is no pedestrian crossing within a 50m range, the benchmark point tracing method is used to calculate the road connector within a 50m range of the benchmark point to determine the theoretical attributes of the vulnerable road users of the road connector. The specific calculation method is the same as the calculation method of the benchmark point and tracing point when the road segment includes a pedestrian crossing.

[0099] In one specific embodiment of this application, the theoretical value calculation module includes: a module for determining a fourth road connection line consistent with the traffic direction of the road segment when the ground object of the road connection line corresponding to the road segment includes a pedestrian walkway; for connecting the road connection lines according to the projection positions of the starting and ending points of the road connection line on the fourth road connection line, obtaining the road connection line connection with the longest distance between the starting and ending points; for extending the road connection line connection to both sides by a predetermined width to obtain a search area; and for determining the calculation module of the theoretical attributes of the vulnerable road users of the road connection line according to whether there are guardrails in the search area.

[0100] Furthermore, a calculation module is used to project guardrails onto road connectors when guardrails exist in the search area. Road connectors with guardrail projection points in the road connectors have theoretically low weak road user attributes, while road connectors without guardrail projection points in the road connectors have theoretically high weak road user attributes.

[0101] Specifically, the calculation process of this module is as follows: When the ground object of the road connection line corresponding to the road segment includes a pedestrian walkway, the starting and ending points of the pedestrian walkway road skeleton line are projected onto the corresponding starting and ending points of the road skeleton line in the direction of travel of the road segment. By interlacing the road skeleton lines in the direction of travel of the road segment, the two projection points of the starting and ending points of the pedestrian walkway road skeleton line that are furthest apart on the interlacing line are obtained. Using the road connection line connecting these two projection points as a baseline, a predetermined width is extended to both sides to obtain the search area, preferably 1 meter. Furthermore, when there are no guardrail objects in the search area, the VRU attribute of the road connection line connecting these two projection points should be high; if there are guardrail objects in the search area, the points corresponding to the guardrail objects are projected onto the road skeleton line in the direction of travel. The VRU attribute of the road connection lines in the interlacing line that include the projection points is low, and the VRU attribute of the road connection lines in the interlacing line that do not include projections and are within the two furthest projection points should be high.

[0102] The specific projection calculation method is as follows: Project the pedestrian walkway connecting line perpendicularly onto the corresponding traffic direction connecting line of the road segment, and obtain the coordinates of the projection points corresponding to the two endpoints of the pedestrian walkway connecting line. Using the coordinates of the endpoint projection points, calculate the distances between all endpoint projection points, and sort the calculated distances. That is, when the endpoint projection points are 1, 2, 3, and 4, calculate the distances between 1 and 2, 1 and 3, and 1 and 4 respectively. Based on the farthest projection distance, obtain the coordinates (X, Y) of the two projection points furthest apart on the path. m Y m ), (X n Y n Based on the unique identifier of the road connection point corresponding to the two farthest projection points, the lane boundary of the outermost lane corresponding to this road segment is obtained, that is, the lane boundary with the largest boundary number of the connecting road line of the road segment connected to the current road segment; using the outermost lane boundary as the baseline, the search area is obtained by extending 1 meter in a direction perpendicular to the outermost lane line. Guardrails are searched within the search area. If a guardrail exists within the search area, the point corresponding to the guardrail object is vertically projected onto the connecting road line of the current road segment's traffic direction, and the coordinates (X) of the farthest projection point corresponding to the guardrail are obtained. p Y p ) and (X q Y q ), projection point (X) p Y p ) and (X q Y q The road connecting lines between the two points represent the maximum range of the guardrail projection within the search area.

[0103] When a guardrail exists within the search area, the attributes of the VRU corresponding to the road segment are obtained by differencing the coordinates of the pedestrian walkway's projection onto the connecting line in the travel direction with the coordinates of the guardrail's projection within the search area. Specifically, the attributes of the VRU corresponding to the road segment are obtained by differencing the projection ranges of the pedestrian walkway and guardrail onto the connecting line in the travel direction corresponding to the road segment. This means that the VRU's attributes are determined when the connecting line is the point where the two projection points (X, Y, X) of the pedestrian walkway on the connecting line in the travel direction are the farthest apart. m Y m ) and (X n Y n The coordinates of the projection point (X) between and farthest from the guardrail. p Y p ) and (X q Y q If it is not a high VRU, then its corresponding VRU attribute is high.

[0104] For example, such as Figure 8 If there is no guardrail object within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of projection point a to projection point N1 on LINK1, then the VRU attribute of the road connection line within the range of point a to point N1 in LINK1 should be high. If there is no guardrail object projection within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of point N1 to point c on LINK2, then the VRU attribute of the road connection line within the range of point N1 to point c in LINK2 should be high. If there is a guardrail object projection within the 1m range of the outermost road boundary of the pedestrian walkway within the search range of point c to point d in LINK2, then the VRU attribute of the road connection line within the range of point c to point d in LINK2 should be low.

[0105] In one specific embodiment of this application, the functional modules in the computing device for calculating the attributes of vulnerable road users may be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0106] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0107] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0108] The calculation device for the attributes of vulnerable road users provided in this application can be used to execute the calculation method for the attributes of vulnerable road users described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0109] Figure 10 This paper illustrates a specific implementation of an automatic detection and correction method for the attributes of vulnerable road users according to this application.

[0110] exist Figure 10 In the specific implementation shown, the automatic detection and correction method for vulnerable road user attributes mainly includes: step S1001, obtaining the road type, lane type and ground object of the road connection line corresponding to the road segment in the map, wherein the road type includes expressway and urban expressway, the lane type includes bicycle lane and parking lane, and the ground object includes public transportation stop, bicycle lane in intersection and sidewalk.

[0111] Step S1002: Using road type, lane type, and ground objects, determine the theoretical attributes of vulnerable road users for road connectors within a predetermined range;

[0112] Step S1003: Obtain the actual attributes of vulnerable road users corresponding to the road connectors in the map based on the unique identification code of the road connectors;

[0113] Step S1004: Compare and differentiate the theoretical attributes of vulnerable road users with the corresponding actual attributes of vulnerable road users, and correct the actual attributes of vulnerable road users of the road connector based on the comparison results.

[0114] The automatic detection and correction method for vulnerable road user attributes provided in this application can be used to execute the calculation method for vulnerable road user attributes described in any of the above embodiments. The implementation principle and technical effect are similar, and will not be repeated here.

[0115] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores a computer program / instructions that are operated to perform the method for calculating the attributes of vulnerable road users described in the above embodiments.

[0116] In one specific embodiment of this application, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores program / computer instructions executable by the at least one processor, and the at least one processor operates the program / computer instructions to perform the method for calculating the attributes of vulnerable road users described in the above embodiments.

[0117] In one specific embodiment of this application, a computer program product includes a computer program / instruction, characterized in that, when the computer program / instruction is executed by a processor, it implements the calculation method for the vulnerable road user attribute in Scheme 1 or the automatic detection and correction method for the vulnerable road user attribute in Scheme 3.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of calculating attributes of vulnerable road users, characterized in that, The method comprises: acquiring a road type of a road link corresponding to a road segment in a map, wherein the road type comprises an expressway and an urban expressway; determining a theoretical attribute of a vulnerable road user of the road link within a predetermined range by using the road type; wherein when the road type is a non-expressway or a non-urban expressway, the theoretical attribute of the vulnerable road user of the road link is high; and when the road type is an expressway or an urban expressway, the theoretical attribute of the vulnerable road user of the road link corresponding to the road segment is determined according to a lane type and a ground object of the road link, wherein the lane type comprises a bicycle lane and a parking lane, and the ground object comprises a public transport stop, an in-intersection bicycle lane and a sidewalk.

2. The method of calculating vulnerable road user attributes according to claim 1, wherein, The step of determining the theoretical attribute of the vulnerable road user of the road link according to the lane type and the ground object of the road link when the road type is an expressway or an urban expressway comprises: when the road segment is a non-shoulder lane, the lane type corresponding to the road link of the road segment is obtained by traversing the road link of the road segment; when all the lane types are bicycle lanes, the theoretical attribute of the vulnerable road user of the road segment is high; and when part of the lane types are bicycle lanes, a search area is obtained by extending a predetermined width to both sides based on the position of the road link of the bicycle lane, and the theoretical attribute of the vulnerable road user of the road link is determined according to whether a guardrail exists in the search area.

3. The method of calculating vulnerable road user attributes according to claim 1, wherein, The step of determining the theoretical attribute of the vulnerable road user of the road link according to the lane type and the ground object of the road link when the road type is an expressway or an urban expressway comprises: when the lane type corresponding to the road segment comprises a parking lane, the theoretical attribute of the vulnerable road user of the road link is high; and when the ground object of the road link corresponding to the road segment comprises a public transport stop, a first road link consistent with the traffic direction of the road segment is determined according to the traffic direction of the road segment, two projection points are obtained by projecting two end points of the road link of the public transport stop onto the first road link, and a search area is obtained by using the two end points and the two projection points, wherein the theoretical attribute of the vulnerable road user of the road link in the search area is high.

4. The method of calculating vulnerable road user attributes according to claim 1, wherein, The step of determining the theoretical attribute of the vulnerable road user of the road link according to the lane type and the ground object of the road link when the road type is an expressway or an urban expressway comprises: When the ground object of the road connection line corresponding to the road section contains a pedestrian crossing, a second road connection line consistent with the traffic direction of the road section is determined according to the traffic direction of the road section, the road connection line of the pedestrian crossing is projected onto the second road connection line, and the two farthest projection points are obtained, the midpoint of the line connecting the two projection points is taken as a reference point, and the weak road user theoretical attribute of the road connection line is determined by using the reference point tracing method; When the ground object of the road connection line corresponding to the road section contains an in-intersection bicycle lane, a search area is obtained by extending the road connection line of the in-intersection bicycle lane to both sides by a predetermined width; when there is no road connection line of the pedestrian crossing in the search area, a third road connection line consistent with the traffic direction of the road section is determined according to the traffic direction of the road section, and the road connection line of the in-intersection bicycle lane is projected onto the third road connection line to obtain the two farthest projection points, the midpoint of the line connecting the two projection points is taken as a reference point, and the weak road user theoretical attribute of the road connection line is determined by using the reference point tracing method.

5. The method of calculating attributes of vulnerable road users according to claim 1, wherein, When the road type is a highway or an urban highway, the weak road user theoretical attribute of the road connection line corresponding to the road section is determined according to the lane type and the ground object of the road connection line, including: When the ground object of the road connection line corresponding to the road section contains a pedestrian crossing, a second road connection line consistent with the traffic direction of the road section is determined according to the traffic direction of the road section, the road connection line of the pedestrian crossing is projected onto the second road connection line, and the two farthest projection points are obtained, the midpoint of the line connecting the two projection points is taken as a reference point, and the weak road user theoretical attribute of the road connection line is determined by using the reference point tracing method; When the ground object of the road connection line corresponding to the road section contains a pedestrian crossing, a second road connection line consistent with the traffic direction of the road section is determined according to the traffic direction of the road section, the road connection line of the pedestrian crossing is projected onto the second road connection line, and the two farthest projection points are obtained, the midpoint of the line connecting the two projection points is taken as a reference point, and the weak road user theoretical attribute of the road connection line is determined by using the reference point tracing method; When the ground object of the road connection line corresponding to the road section contains a pedestrian crossing, a second road connection line consistent with the traffic direction of the road section is determined according to the traffic direction of the road section, the road connection line of the pedestrian crossing is projected onto the second road connection line, and the two farthest projection points are obtained, the midpoint of the line connecting the two projection points is taken as a reference point, and the weak road user theoretical attribute of the road connection line is determined by using the reference point tracing method.

6. A method for automatic detection and correction of vulnerable road user attributes, characterized in that, It includes: Obtaining the road type, lane type and ground object of the road connection line corresponding to the road section in the map, wherein the road type includes a highway and an urban highway, the lane type includes a bicycle lane and a parking lane, and the ground object includes a public transportation stop, an in-intersection bicycle lane and a sidewalk; Determining the weak road user theoretical attribute of the road connection line within a predetermined range by using the road type, the lane type and the ground object; According to the unique identification code of the road connection line, the weak road user actual attribute corresponding to the road connection line in the map is obtained. The weak road user theoretical attribute and the corresponding weak road user actual attribute are compared and differentiated, and the weak road user actual attribute of the road link is corrected according to the comparison result.

7. A computing device for vulnerable road user attribute, characterized by, The method comprises the steps of: An information acquisition module is configured to acquire a road type of a road link corresponding to a road segment in a map, wherein the road type comprises an expressway and an urban expressway; A theoretical value calculation module is configured to determine a weak road user theoretical attribute of the road link within a predetermined range by using the road type; When the road type is a non-expressway or a non-urban expressway, the weak road user theoretical attribute of the road link is high; and When the road type is an expressway or an urban expressway, the weak road user theoretical attribute of the road link corresponding to the road segment is determined according to a lane type and a ground object of the road link, wherein the lane type comprises a bicycle lane and a parking lane, and the ground object comprises a public transport stop, an intersection bicycle lane, and a sidewalk.

8. A computer readable storage medium storing computer programs / instructions, characterized in that, The computer program / instruction is operated to perform the weak road user attribute calculation method of any one of claims 1-5 or the weak road user attribute automatic detection and correction method of claim 6.

9. An electronic device, comprising: The method comprises the steps of: At least one processor; And A memory connected in communication with the at least one processor; Wherein the memory stores computer programs / instructions executable by the at least one processor, and the at least one processor operates the computer programs / instructions to perform the weak road user attribute calculation method of any one of claims 1-5 or the weak road user attribute automatic detection and correction method of claim 6.

10. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to realize the weak road user attribute calculation method of any one of claims 1-5 or the weak road user attribute automatic detection and correction method of claim 6.

Images