Environment perception method, apparatus, device, medium and program product for target region

Abstract

The application relates to an environment perception method, device, equipment, medium and program product of a target area. The method comprises the following steps: acquiring sensing data of a target road; acquiring an initial perception result according to the sensing data; processing the initial perception result by using the relative spatial relationship of a plurality of traffic participants in each area on the road to obtain a target perception result of each lane on the target road, wherein the relative spatial relationship of the plurality of traffic participants is confirmed based on a traffic rule. The method can solve the problems of undetectable vehicles or detection errors.

Description

Technical Field

[0001] This application relates to the field of target detection technology, and in particular to a method, apparatus, device, medium, and program product for environmental sensing of a target area. Background Technology

[0002] With the development of technology, object detection has become one of the main research directions in the automotive field. Currently, the object detection process mainly includes: collecting point cloud data through vehicle-mounted radar, and using object detection algorithms to detect objects in the point cloud data.

[0003] However, because vehicles may block each other, it is easy to encounter problems such as vehicles not being detected or detection errors. Summary of the Invention

[0004] Therefore, it is necessary to provide an environmental perception method, device, equipment, medium, and program product for target areas that can solve problems such as failure to detect vehicles or detection errors, in order to address the aforementioned technical issues.

[0005] Firstly, this application provides a method for environmental perception of a target area. The method includes:

[0006] Acquire sensor data for the target road;

[0007] Initial sensing results are obtained based on sensor data;

[0008] The initial perception results are processed by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of multiple traffic participants are confirmed based on traffic rules.

[0009] In one embodiment, the method further includes:

[0010] The target perception results for each lane on the target road are stored. These results are used to confirm the relative spatial relationships of multiple traffic participants in different areas of the road.

[0011] In one embodiment, the above-mentioned processing of the initial perception results using the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception results for each lane on the target road includes:

[0012] If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road.

[0013] In one embodiment, spatial relationship anomalies include missing location information of target traffic participants. The initial perception results are corrected by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain target perception results for each lane on the target road, including:

[0014] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are filled with location information to obtain the target perception results.

[0015] In one embodiment, spatial relationship anomalies include missing location information of target traffic participants. The initial perception results are corrected by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain target perception results for each lane on the target road, including:

[0016] The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results;

[0017] Based on the location information of the target traffic participant before the location information was missing and the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant is determined;

[0018] Based on the missing location information of the target traffic participant, the initial perception results are filled with location information to obtain the target perception results.

[0019] In one embodiment, determining the missing location information of the target traffic participant based on the location information of the target traffic participant before the location information was lost and the fitted movement trajectory of the target traffic participant includes:

[0020] The predicted location of the target traffic participant is determined by matching the location information of the target traffic participant before the location information is missing with the fitted movement trajectory of the target traffic participant.

[0021] Determine the predicted area of ​​the target traffic participants based on their predicted locations;

[0022] The traffic participants are searched in the predicted area of ​​the target traffic participants, and the found traffic participants are identified as the target traffic participants. The location information of the found traffic participants is identified as the missing location information of the target traffic participants.

[0023] In one embodiment, spatial relationship anomalies include errors in the location information of target traffic participants. The initial perception result is corrected by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception result for each lane on the target road, including:

[0024] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are replaced with location information to obtain the target perception results.

[0025] In one embodiment, the method further includes:

[0026] Acquire location information of multiple traffic participants from sensor data;

[0027] Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0028] The relative spatial relationship is determined based on the reference traffic participants and their adjacent traffic participants.

[0029] In one embodiment, determining the adjacent traffic participants of the reference traffic participant based on the location information of multiple traffic participants includes:

[0030] A reference coordinate system is established based on the reference traffic participants; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participants.

[0031] Traffic participants located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold are identified as the preceding adjacent traffic participants of the reference traffic participant.

[0032] In one embodiment, prior to establishing the reference coordinate system based on the reference traffic participant, the method further includes:

[0033] Based on multiple location information of the reference traffic participant, determine the local movement trajectory of the reference traffic participant;

[0034] The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

[0035] In one embodiment, determining the adjacent traffic participants of the reference traffic participant based on the location information of multiple traffic participants includes:

[0036] The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

[0037] Secondly, this application also provides an environmental sensing device for a target area. The device includes:

[0038] The data acquisition module is used to acquire sensor data of the target road.

[0039] The first result acquisition module is used to acquire the initial sensing result based on the sensing data;

[0040] The second result acquisition module is used to process the initial perception results by utilizing the relative spatial relationships of multiple traffic participants in various areas of the road, and to obtain the target perception results of each lane on the target road. The relative spatial relationships of multiple traffic participants are confirmed based on traffic rules.

[0041] Thirdly, this application also provides an electronic device. The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps described in the first aspect.

[0042] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps described in the first aspect.

[0043] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps described in the first aspect.

[0044] The aforementioned environmental perception methods, devices, equipment, media, and program products for the target area acquire sensor data of the target road; obtain initial perception results based on the sensor data; and process the initial perception results using the relative spatial relationships of multiple traffic participants in various areas of the road to obtain target perception results for each lane on the target road. In this embodiment, the relative spatial relationships of multiple traffic participants are determined during the target detection process. Thus, when vehicles obstruct each other, vehicles can be accurately detected based on the relative spatial relationships of multiple traffic participants, thereby enabling effective vehicle tracking. Attached Figure Description

[0045] Figure 1 This is an application environment diagram of an environmental perception method for a target area in one embodiment;

[0046] Figure 2 This is a flowchart illustrating an environmental perception method for a target area in one embodiment;

[0047] Figure 3 This is a flowchart illustrating the steps for correcting the initial sensing result in one embodiment;

[0048] Figure 4 This is a schematic diagram illustrating the determination of missing location information in one embodiment;

[0049] Figure 5 This is a flowchart illustrating the steps for determining relative spatial relationships in one embodiment;

[0050] Figure 6a This is one of the schematic diagrams for determining adjacent traffic participants in one embodiment;

[0051] Figure 6b This is a second schematic diagram illustrating the determination of adjacent traffic participants in one embodiment;

[0052] Figure 7 This is a flowchart illustrating the environmental perception method for the target area in another embodiment;

[0053] Figure 8 This is a structural block diagram of an environmental sensing device for a target area in one embodiment;

[0054] Figure 9 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The environmental perception method for the target area provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown includes an electronic device 102 and a server 104; the electronic device 102 can communicate with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104 or placed on a cloud or other network server. The electronic device 102 may include, but is not limited to, vehicles, roadside base stations, etc., and multiple sensors can be installed on the electronic device 102, including but not limited to various cameras, LiDAR, etc. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers. In one implementation scenario, the electronic device 102 acquires sensor data through sensors and performs target detection based on the sensor data; in another implementation scenario, the server 104 acquires sensor data from the electronic device 102 and performs target detection based on the sensor data. This application embodiment does not limit the implementation scenario.

[0057] In one embodiment, such as Figure 2 As shown, an environmental perception method for a target area is provided, which is then applied to... Figure 1 Taking an electronic device as an example, the explanation includes the following steps:

[0058] Step 201: Obtain sensor data for the target road.

[0059] The electronic device is equipped with multiple sensors, including cameras, lidar, etc. The electronic device can acquire image data of the target road through the camera, or point cloud data of the target road through the lidar. This application does not limit the types of sensors or the sensing data.

[0060] Step 202: Obtain the initial sensing results based on the sensing data.

[0061] The initial perception results include the initial location information of multiple traffic participants on the target road. Traffic participants can include various motor vehicles and non-motor vehicles; however, this embodiment does not limit the types of traffic participants.

[0062] Electronic devices can obtain a perception model from a server in advance. After obtaining the sensing data, they can input the sensing data into the perception model to obtain the initial perception results.

[0063] For example, electronic devices input image data into a perception model to obtain the initial position information of multiple vehicles on the target road; or, electronic devices input point cloud data into a perception model to obtain the initial position information of multiple vehicles on the target road.

[0064] The aforementioned perception model can be a neural network model, and this application does not limit this.

[0065] Step 203: Process the initial perception results using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road.

[0066] The relative spatial relationships among multiple traffic participants are determined based on traffic rules.

[0067] Electronic devices can determine the relative spatial relationships of multiple traffic participants based on sensor data and traffic rules over historical periods. For example, they can determine that vehicle A is in front of vehicle B on a target road, and vehicle C is in the adjacent lane of vehicle A.

[0068] The initial perception results obtained by electronic devices may be incomplete, erroneous, or abnormal. Therefore, electronic devices can obtain more complete and accurate target perception results based on the relative spatial relationships of multiple traffic participants and the initial perception results.

[0069] For example, the initial perception results include the initial position information of vehicle B and vehicle C. Based on the previously determined relative spatial relationships of multiple traffic participants, the target position information of vehicle A, vehicle B, and vehicle C can be obtained separately.

[0070] In one embodiment, the electronic device is a vehicle, and the target perception results can assist the vehicle in autonomous driving and improve the safety of vehicle driving.

[0071] In the aforementioned environmental perception method for the target area, sensor data of the target road is acquired; initial perception results are obtained based on the sensor data; and the initial perception results are processed using the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception results for each lane on the target road. In this embodiment, the relative spatial relationships of multiple traffic participants are determined during the target detection process. Thus, when vehicles obstruct each other, vehicles can be accurately detected based on the relative spatial relationships of multiple traffic participants, thereby enabling effective vehicle tracking.

[0072] In one embodiment, the present application may further include: storing target perception results for each lane on the target road, wherein the target perception results are used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road.

[0073] After obtaining the target perception results for each lane, the electronic device stores these results. Then, when the electronic device acquires the initial perception results again, it can determine the relative spatial relationships of multiple traffic participants in different areas of the road based on the stored target perception results, and then process the initial perception results according to these relative spatial relationships.

[0074] For example, the target perception result includes the target location information of vehicle A, vehicle B, and vehicle C. Based on the target location information of vehicle A, vehicle B, and vehicle C, the relative spatial relationship of the three vehicles can be determined, including vehicle A being in front of vehicle B and vehicle C being in the adjacent lane of vehicle A. The electronic device stores this relative spatial relationship.

[0075] In one embodiment, the relative spatial relationships of multiple traffic participants can be updated according to the target perception results at preset time intervals.

[0076] In the above embodiments, the target perception results of each lane on the target road are stored. These target perception results can be used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road, providing a basis for subsequent vehicle detection.

[0077] In one embodiment, the step of processing the initial perception result using the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception result of each lane on the target road may include: if there are abnormal spatial relationships and / or abnormal numbers in the initial perception result, then the initial perception result is corrected using the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception result of each lane on the target road.

[0078] Once the electronic device obtains the initial perception results, if there are abnormalities in the spatial relationships or quantities of local areas, the initial perception results are corrected based on the previously determined relative spatial relationships of multiple traffic participants.

[0079] For example, the initial perception result includes the initial position information of vehicle A, vehicle B, and vehicle C. Based on the initial position information of the three vehicles, their current relative spatial relationship can be determined. If vehicle occlusion occurs, the current relative spatial relationship may not correspond to the previously determined relative spatial relationship, or the current number of vehicles may not correspond to the previously determined number of vehicles. In this case, the positions of vehicles with incorrect positions in the initial perception result can be corrected based on the previously determined relative spatial relationship, or the positions of each vehicle in the initial perception result can be corrected to obtain the target perception result.

[0080] In one embodiment, the initial perception result may also include the vehicle type, and in the event of a vehicle type error, the vehicle type may be corrected based on the relative spatial relationship.

[0081] In the above embodiments, if there are abnormalities in the spatial relationships and / or the number of objects in the initial perception results, the initial perception results are corrected by utilizing the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road. Through the embodiments of this application, the problem of vehicles not being detected or being detected incorrectly due to vehicle obstruction can be avoided, and vehicles can be accurately detected, thereby achieving vehicle tracking.

[0082] Based on the specific circumstances of an abnormal initial sensing result, the embodiments of this application can adopt the following correction methods:

[0083] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant. The correction process may include: filling the initial perception result with location information based on the location information of the target traffic participant in the relative spatial relationship to obtain the target perception result.

[0084] For example, if vehicle A is the target traffic participant, and vehicle A is obscured, the initial perception result obtained by the electronic device does not include the location information of vehicle A. That is, the initial perception result has a missing location information of the target traffic participant.

[0085] In this scenario, the electronic device can determine the location information of the target traffic participant based on the previously determined relative spatial relationship, and then fill in the initial perception result with location information based on the location information of the target traffic participant to obtain the target perception result.

[0086] For example, the initial perception result includes the initial position information of vehicle B and vehicle C. The previously determined relative spatial relationship includes vehicle A in front of vehicle B and vehicle C in the adjacent lane of vehicle A. Based on the initial position information of vehicle B and vehicle C and the relative spatial relationship of the three vehicles, the position information of vehicle A can be determined. Then, the position information of vehicle A is used to fill in the initial perception result to obtain the target position information of the three vehicles, that is, the target perception result.

[0087] In one embodiment, the location information may further include the identifier of the traffic participant, which is filled in during the filling process.

[0088] In the above embodiments, the initial perception results are filled with location information based on the location information of the target traffic participant in the relative spatial relationship to obtain the target perception result. This application embodiment uses a filling process to obtain a complete target perception result, which can solve the problem of missing location information of the target traffic participant in the initial perception result.

[0089] In one implementation, spatial relationship anomalies include missing location information of the target traffic participants, such as... Figure 3 As shown, the correction process may include the following steps:

[0090] Step 301: Determine the fitted movement trajectory of the target traffic participant based on multiple initial perception results.

[0091] When the location information of the target traffic participant is missing in an initial perception result, the trajectory of the target traffic participant can be fitted based on multiple initial perception results to obtain the fitted movement trajectory of the target traffic participant.

[0092] For example, if the target traffic participant is vehicle A, and the electronic device acquires 5 frames of point cloud data, obtaining an initial perception result for each frame, then after acquiring the 6th frame, the initial perception result based on this frame shows a missing location information for vehicle A. The electronic device can then perform trajectory fitting based on the location information of vehicle A from the first 5 frames of point cloud data to obtain a fitted movement trajectory for vehicle A.

[0093] Step 302: Determine the missing location information of the target traffic participant based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant.

[0094] After determining the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant can be determined based on the location information of the target traffic participant before the location information was lost and the fitted movement trajectory.

[0095] For example, based on the point cloud data of frame 5 and the fitted movement trajectory of vehicle A, the electronic device can obtain the position information of vehicle A in the point cloud data of frame 6.

[0096] In one embodiment, the process of determining the missing location information of the target traffic participant may include: determining the predicted location of the target traffic participant based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant; determining the predicted area of ​​the target traffic participant based on the predicted location of the target traffic participant; searching for traffic participants in the predicted area of ​​the target traffic participant, and determining the found traffic participants as the target traffic participant, and determining the location information of the found traffic participants as the missing location information of the target traffic participant.

[0097] like Figure 4 As shown, the position information of vehicle A before the location information is missing is (x0, y0). Based on this position information and the fitted movement trajectory of vehicle A, the predicted position of vehicle A is determined to be (x1, y1). A prediction area for vehicle A is determined with (x1, y1) as the center and a preset length R as the radius. The vehicle is searched within the prediction area, and the found vehicle is identified as vehicle A. The position information of the found vehicle is then determined as the missing location information for vehicle A. It should be noted that other methods can also be used to determine the prediction area. For example, a square with side length R can be defined as the prediction area for vehicle A, centered on its predicted position. The method for determining the prediction area in this embodiment is not limited and can be set according to actual conditions.

[0098] Step 303: Based on the missing location information of the target traffic participant, fill in the location information of the initial perception result to obtain the target perception result.

[0099] After determining the missing location information of the target traffic participant, the location information is filled into the initial perception result to obtain the target perception result.

[0100] For example, if the location information of a vehicle found in the prediction area is (x2, y2), then this location information is used to fill in the initial perception result to obtain the target location information of vehicle A, vehicle B and vehicle C.

[0101] In the above embodiments, the fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results; the missing location information of the target traffic participant is determined based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant; and the missing location information of the target traffic participant is used to fill in the location information of the initial perception results to obtain the target perception result. This embodiment of the application determines the missing location information of the target traffic participant through trajectory fitting, which can solve the problem of missing location information of the target traffic participant in the initial perception results.

[0102] In one embodiment, spatial relationship anomalies include errors in the location information of the target traffic participant. The correction process may include: replacing the location information of the initial perception result with the location information of the target traffic participant in the relative spatial relationship to obtain the target perception result.

[0103] In actual detection, there may be cases where the location of the target traffic participant is incorrect. To address this, the location information of the target traffic participant can be retrieved from the previously determined relative spatial relationships. This retrieved location information can then replace the erroneous location information in the initial perception result, thus obtaining the target perception result.

[0104] In one embodiment, the location information may further include the identifier of the traffic participant, which is replaced during the replacement process.

[0105] In the above embodiments, the initial perception result is replaced with location information based on the location information of the target traffic participant in the relative spatial relationship to obtain the target perception result. This embodiment of the application determines the target perception result through replacement processing, which can solve the problem of incorrect location information of the target traffic participant in the initial perception result.

[0106] In one embodiment, such as Figure 5 As shown, embodiments of this disclosure may further include a process for determining relative spatial relationships:

[0107] Step 401: Obtain the location information of multiple traffic participants from the sensor data.

[0108] After acquiring the sensor data, the electronic device identifies the location information of multiple traffic participants from the sensor data. For example, image data or point cloud data is input into a target detection model, and the target detection model outputs the location information of multiple traffic participants. The target detection model described above can be a neural network model, and this application embodiment does not limit it to this.

[0109] Step 402: Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0110] The electronic device uses one of the traffic participants as a reference traffic participant, and then determines the adjacent traffic participants in front of, behind, to the left and right of the reference traffic participant based on the location information of multiple traffic participants and lane lines.

[0111] For example, if vehicle B is the reference traffic participant, based on the location information of vehicle A, vehicle B, and vehicle C, as well as the lane lines, it can be determined that vehicle A in front of vehicle B is the adjacent traffic participant of vehicle B.

[0112] In practical applications, there are several ways to determine adjacent traffic participants:

[0113] In one embodiment, the process of determining adjacent traffic participants may include: establishing a reference coordinate system based on a reference traffic participant, wherein the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participant; and determining the traffic participant located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold as the preceding adjacent traffic participant of the reference traffic participant.

[0114] like Figure 6a As shown, a reference coordinate system is established based on vehicle B, where the y-axis represents the driving direction of vehicle B. Vehicles in front of vehicle B whose angle with the y-axis is within a preset angle threshold are identified as the preceding adjacent vehicles of vehicle B. Assuming the preset angle threshold is 20°, if vehicle A is in front of vehicle B and its angle α with the y-axis is within 20°, then vehicle A is the preceding adjacent vehicle of vehicle B. However, although vehicle C is in front of vehicle B, its angle β with the y-axis is greater than 20°, therefore vehicle C is not the preceding adjacent vehicle of vehicle B.

[0115] In one embodiment, before establishing the reference coordinate system, the method may further include: determining the local movement trajectory of the reference traffic participant based on multiple location information of the reference traffic participant; correcting the navigation angle of the reference traffic participant based on the local movement trajectory; and determining the driving direction of the reference traffic participant based on the corrected navigation angle.

[0116] During the movement of a reference traffic participant, the navigation angle may deviate from its direction of travel. For example, if vehicle B is traveling due north, but adjusts its direction of travel east to avoid a vehicle on its left, then vehicle B's navigation angle will not be due north, and will deviate from its direction of travel. To avoid this, a local trajectory of vehicle B can be determined based on multiple positional information. The navigation angle can then be corrected based on this local trajectory, and the corrected navigation angle will be used to determine vehicle B's direction of travel. Understandably, using a local trajectory for navigation angle correction allows for accurate determination of the reference traffic participant's direction of travel, thereby accurately establishing a reference coordinate system and accurately identifying adjacent traffic participants.

[0117] In another implementation, the process of determining adjacent traffic participants may include: determining an adjacent area centered on a reference traffic participant, and determining traffic participants located within the adjacent area in adjacent lanes as the side adjacent traffic participants of the reference traffic participant.

[0118] like Figure 6b As shown, the reference traffic participant is vehicle A. With vehicle A as the center, a rectangular area of ​​a preset size is defined as the adjacent area. Vehicle C, which is located in the adjacent area in the lane to the left of vehicle A, is defined as the side adjacent vehicle of vehicle A.

[0119] Step 403: Determine the relative spatial relationship based on the reference traffic participant and its adjacent traffic participants.

[0120] After identifying the reference traffic participants and adjacent traffic participants, the relative spatial relationships between them are determined. For example, if vehicle A is determined to be the preceding adjacent vehicle of vehicle B, and vehicle C is the lateral adjacent vehicle of vehicle A, then the relative spatial relationships of the three vehicles can be determined.

[0121] In the above embodiments, the location information of multiple traffic participants in the sensor data is acquired; any one of the multiple traffic participants is used as a reference traffic participant, and the adjacent traffic participants of the reference traffic participant are determined based on the location information of the multiple traffic participants; the relative spatial relationship is determined based on the reference traffic participant and its adjacent traffic participants. This embodiment determines the relative spatial relationship by identifying adjacent vehicles, which is not only fast but also highly accurate.

[0122] In one embodiment, such as Figure 7 As shown, an environmental perception method for a target area is provided, which is then applied to... Figure 1 Taking an electronic device as an example, the explanation includes the following steps:

[0123] Step 501: Obtain sensor data of the target road.

[0124] Step 502: Obtain the location information of multiple traffic participants from the sensor data.

[0125] Step 503: Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0126] In one implementation, the local movement trajectory of the reference traffic participant is determined based on multiple location information of the reference traffic participant; the navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle; a reference coordinate system is established based on the reference traffic participant; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participant; and the traffic participant located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold is determined as the preceding adjacent traffic participant of the reference traffic participant.

[0127] In one embodiment, an adjacent area is determined with the reference traffic participant as the center, and traffic participants located in the adjacent area in the adjacent lane are determined as the side adjacent traffic participants of the reference traffic participant.

[0128] Step 504: Determine the relative spatial relationship based on the reference traffic participant and its adjacent traffic participants.

[0129] Step 505: Obtain the initial sensing results based on the sensing data.

[0130] Step 506: If there are abnormal spatial relationships and / or abnormal numbers in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road.

[0131] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant. Based on the location information of the target traffic participant in the relative spatial relationship, the initial perception result is filled with location information to obtain the target perception result.

[0132] In one embodiment, the spatial relationship anomaly includes the missing location information of the target traffic participant. The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results. The missing location information of the target traffic participant is determined based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant. The missing location information of the target traffic participant is used to fill in the location information of the initial perception results to obtain the target perception result.

[0133] In one embodiment, spatial relationship anomalies include errors in the location information of the target traffic participant. Based on the location information of the target traffic participant in the relative spatial relationship, the initial perception result is replaced with location information to obtain the target perception result.

[0134] Step 507: Store the target perception results for each lane on the target road. The target perception results are used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road.

[0135] In the above embodiments, sensor data of the target road is acquired; position information of multiple traffic participants in the sensor data is acquired; then, reference traffic participants and adjacent traffic participants are determined based on the position information of the multiple traffic participants, and the relative spatial relationship between the multiple traffic participants is determined based on the reference traffic participants and adjacent traffic participants. Afterwards, an initial perception result is obtained based on the sensor data; if there are abnormal spatial relationships and / or abnormal numbers in the initial perception result, the initial perception result is corrected using the relative spatial relationship of the multiple traffic participants to obtain the target perception result for each lane on the target road, and the target perception result for each lane on the target road is stored. This embodiment of the application determines the relative spatial relationship of multiple traffic participants during the target detection process. Thus, when vehicles obstruct each other, vehicles can be accurately detected based on the relative spatial relationship of the multiple traffic participants, avoiding failure to detect vehicles or detection errors, and therefore enabling effective vehicle tracking.

[0136] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0137] Based on the same inventive concept, this application also provides an environmental sensing device for implementing the environmental sensing method for the target area described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of the one or more environmental sensing device embodiments for the target area provided below can be found in the limitations of the environmental sensing method for the target area described above, and will not be repeated here.

[0138] In one embodiment, such as Figure 8 As shown, an environmental sensing device for a target area is provided, comprising:

[0139] The data acquisition module 601 is used to acquire sensor data of the target road;

[0140] The first result acquisition module 602 is used to acquire the initial sensing result based on the sensing data;

[0141] The second result acquisition module 603 is used to process the initial perception result by utilizing the relative spatial relationship of multiple traffic participants in various areas of the road to obtain the target perception result of each lane on the target road. The relative spatial relationship of multiple traffic participants is confirmed based on traffic rules.

[0142] In one embodiment, the device further includes:

[0143] The storage module is used to store the target perception results for each lane on the target road. The target perception results are used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road.

[0144] In one embodiment, the second result acquisition module 603 is specifically used to correct the initial perception result by utilizing the relative spatial relationships of multiple traffic participants in each area of ​​the road if there are abnormalities in the spatial relationships and / or the number of participants in the initial perception result. This corrects the initial perception result and obtains the target perception result for each lane on the target road.

[0145] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant. The second result acquisition module 603 is specifically used to fill in the location information of the initial perception result based on the location information of the target traffic participant in the relative spatial relationship, so as to obtain the target perception result.

[0146] In one embodiment, the spatial relationship anomaly includes the missing location information of the target traffic participant. The second result acquisition module 603 is specifically used to determine the fitted movement trajectory of the target traffic participant based on multiple initial perception results; determine the missing location information of the target traffic participant based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant; and fill in the location information of the initial perception results based on the missing location information of the target traffic participant to obtain the target perception result.

[0147] In one embodiment, the second result acquisition module 603 is specifically used to determine the predicted position of the target traffic participant based on the position information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant; determine the predicted area of ​​the target traffic participant based on the predicted position of the target traffic participant; search for traffic participants in the predicted area of ​​the target traffic participant, and determine the found traffic participants as the target traffic participant, and determine the location information of the found traffic participants as the missing location information of the target traffic participant.

[0148] In one embodiment, spatial relationship anomalies include errors in the location information of the target traffic participant. The second result acquisition module 603 is specifically used to replace the location information of the initial perception result based on the location information of the target traffic participant in the relative spatial relationship, so as to obtain the target perception result.

[0149] In one embodiment, the device further includes:

[0150] The location acquisition module is used to acquire the location information of multiple traffic participants from the sensor data;

[0151] The adjacency determination module is used to take any one of the multiple traffic participants as a reference traffic participant and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0152] The spatial relationship determination module is used to determine the relative spatial relationship based on the reference traffic participant and its adjacent traffic participants.

[0153] In one embodiment, the adjacent determination module is specifically used to establish a reference coordinate system based on a reference traffic participant; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participant; and the traffic participant located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold is determined as the previous adjacent traffic participant of the reference traffic participant.

[0154] In one embodiment, the device further includes:

[0155] The trajectory determination module is used to determine the local movement trajectory of the reference traffic participant based on multiple location information of the reference traffic participant.

[0156] The direction determination module is used to correct the navigation angle of the reference traffic participant based on the local movement trajectory, and to determine the driving direction of the reference traffic participant based on the corrected navigation angle.

[0157] In one embodiment, the adjacency determination module is specifically used to determine the adjacent area with the reference traffic participant as the center, and to determine the traffic participants located in the adjacent area in the adjacent lane as the side adjacent traffic participants of the reference traffic participant.

[0158] Each module in the environmental sensing device for the aforementioned target area can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each module.

[0159] In one embodiment, an electronic device is provided, which may be a roadside base station or a vehicle, and its internal structure diagram may be as follows: Figure 9 As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements an environmental awareness method for a target area.

[0160] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0161] In one embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0162] Acquire sensor data for the target road;

[0163] Initial sensing results are obtained based on sensor data;

[0164] The initial perception results are processed by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of multiple traffic participants are confirmed based on traffic rules.

[0165] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0166] The target perception results for each lane on the target road are stored. These results are used to confirm the relative spatial relationships of multiple traffic participants in different areas of the road.

[0167] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0168] If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road.

[0169] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the processor executes the following steps when executing the computer program:

[0170] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are filled with location information to obtain the target perception results.

[0171] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the processor executes the following steps when executing the computer program:

[0172] The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results;

[0173] Based on the location information of the target traffic participant before the location information was missing and the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant is determined;

[0174] Based on the missing location information of the target traffic participant, the initial perception results are filled with location information to obtain the target perception results.

[0175] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0176] The predicted location of the target traffic participant is determined by matching the location information of the target traffic participant before the location information is missing with the fitted movement trajectory of the target traffic participant.

[0177] Determine the predicted area of ​​the target traffic participants based on their predicted locations;

[0178] The traffic participants are searched in the predicted area of ​​the target traffic participants, and the found traffic participants are identified as the target traffic participants. The location information of the found traffic participants is identified as the missing location information of the target traffic participants.

[0179] In one embodiment, spatial relationship anomalies include incorrect location information of the target traffic participant, and the processor executes the following steps when executing the computer program:

[0180] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are replaced with location information to obtain the target perception results.

[0181] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0182] Acquire location information of multiple traffic participants from sensor data;

[0183] Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0184] The relative spatial relationship is determined based on the reference traffic participants and their adjacent traffic participants.

[0185] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0186] A reference coordinate system is established based on the reference traffic participants; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participants.

[0187] Traffic participants located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold are identified as the preceding adjacent traffic participants of the reference traffic participant.

[0188] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0189] Based on multiple location information of the reference traffic participant, determine the local movement trajectory of the reference traffic participant;

[0190] The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

[0191] In one embodiment, when a processor executes a computer program, it performs the following steps:

[0192] The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

[0193] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0194] Acquire sensor data for the target road;

[0195] Initial sensing results are obtained based on sensor data;

[0196] The initial perception results are processed by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of multiple traffic participants are confirmed based on traffic rules.

[0197] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0198] The target perception results for each lane on the target road are stored. These results are used to confirm the relative spatial relationships of multiple traffic participants in different areas of the road.

[0199] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0200] If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road.

[0201] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0202] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are filled with location information to obtain the target perception results.

[0203] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0204] The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results;

[0205] Based on the location information of the target traffic participant before the location information was missing and the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant is determined;

[0206] Based on the missing location information of the target traffic participant, the initial perception results are filled with location information to obtain the target perception results.

[0207] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0208] The predicted location of the target traffic participant is determined by matching the location information of the target traffic participant before the location information is missing with the fitted movement trajectory of the target traffic participant.

[0209] Determine the predicted area of ​​the target traffic participants based on their predicted locations;

[0210] The traffic participants are searched in the predicted area of ​​the target traffic participants, and the found traffic participants are identified as the target traffic participants. The location information of the found traffic participants is identified as the missing location information of the target traffic participants.

[0211] In one embodiment, spatial relationship anomalies include incorrect location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0212] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are replaced with location information to obtain the target perception results.

[0213] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0214] Acquire location information of multiple traffic participants from sensor data;

[0215] Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0216] The relative spatial relationship is determined based on the reference traffic participants and their adjacent traffic participants.

[0217] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0218] A reference coordinate system is established based on the reference traffic participants; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participants.

[0219] Traffic participants located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold are identified as the preceding adjacent traffic participants of the reference traffic participant.

[0220] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0221] Based on multiple location information of the reference traffic participant, determine the local movement trajectory of the reference traffic participant;

[0222] The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

[0223] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0224] The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

[0225] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0226] Acquire sensor data for the target road;

[0227] Initial sensing results are obtained based on sensor data;

[0228] The initial perception results are processed by utilizing the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of multiple traffic participants are confirmed based on traffic rules.

[0229] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0230] The target perception results for each lane on the target road are stored. These results are used to confirm the relative spatial relationships of multiple traffic participants in different areas of the road.

[0231] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0232] If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road.

[0233] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0234] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are filled with location information to obtain the target perception results.

[0235] In one embodiment, spatial relationship anomalies include missing location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0236] The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results;

[0237] Based on the location information of the target traffic participant before the location information was missing and the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant is determined;

[0238] Based on the missing location information of the target traffic participant, the initial perception results are filled with location information to obtain the target perception results.

[0239] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0240] The predicted location of the target traffic participant is determined by matching the location information of the target traffic participant before the location information is missing with the fitted movement trajectory of the target traffic participant.

[0241] Determine the predicted area of ​​the target traffic participants based on their predicted locations;

[0242] The traffic participants are searched in the predicted area of ​​the target traffic participants, and the found traffic participants are identified as the target traffic participants. The location information of the found traffic participants is identified as the missing location information of the target traffic participants.

[0243] In one embodiment, spatial relationship anomalies include incorrect location information of the target traffic participant, and the computer program, when executed by a processor, further performs the following steps:

[0244] Based on the location information of the target traffic participants in the relative spatial relationship, the initial perception results are replaced with location information to obtain the target perception results.

[0245] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0246] Acquire location information of multiple traffic participants from sensor data;

[0247] Take any one of the multiple traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the multiple traffic participants.

[0248] The relative spatial relationship is determined based on the reference traffic participants and their adjacent traffic participants.

[0249] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0250] A reference coordinate system is established based on the reference traffic participants; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participants.

[0251] Traffic participants located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold are identified as the preceding adjacent traffic participants of the reference traffic participant.

[0252] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0253] Based on multiple location information of the reference traffic participant, determine the local movement trajectory of the reference traffic participant;

[0254] The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

[0255] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0256] The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

[0257] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0258] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0259] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for environmental perception of a target area, characterized in that, The method includes: Acquire sensor data for the target road; The initial sensing result is obtained based on the sensor data; The initial perception results are processed using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of the multiple traffic participants are determined based on traffic rules. The target perception results for each lane on the target road are stored, and the target perception results are used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road. The step of processing the initial perception results using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road includes: If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road. The spatial relationship anomaly includes missing location information of the target traffic participants. The step of correcting the initial perception result by utilizing the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception result for each lane on the target road includes: Based on the location information of the target traffic participant in the relative spatial relationship, the initial perception result is filled with location information to obtain the target perception result.

2. The method according to claim 1, characterized in that, The spatial relationship anomaly also includes incorrect location information of the target traffic participants. The step of correcting the initial perception result using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception result for each lane on the target road includes: Based on the location information of the target traffic participant in the relative spatial relationship, the initial perception result is replaced with location information to obtain the target perception result.

3. The method according to claim 1, characterized in that, The method further includes: Obtain the location information of multiple traffic participants from the sensor data; Take any one of the plurality of traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants. The relative spatial relationship is determined based on the reference traffic participant and its adjacent traffic participants.

4. The method according to claim 3, characterized in that, The step of determining the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants includes: A reference coordinate system is established based on the reference traffic participant; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participant. The traffic participant located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold is determined as the preceding adjacent traffic participant of the reference traffic participant.

5. The method according to claim 4, characterized in that, Before establishing the reference coordinate system based on the reference traffic participant, the method further includes: Based on multiple location information of the reference traffic participant, the local movement trajectory of the reference traffic participant is determined; The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

6. The method according to claim 3, characterized in that, The step of determining the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants includes: The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

7. A method for environmental perception of a target area, characterized in that, The method includes: Acquire sensor data for the target road; The initial sensing result is obtained based on the sensor data; The initial perception results are processed using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road. The relative spatial relationships of the multiple traffic participants are determined based on traffic rules. The target perception results for each lane on the target road are stored, and the target perception results are used to confirm the relative spatial relationships of multiple traffic participants in each area of ​​the road. The step of processing the initial perception results using the relative spatial relationships of multiple traffic participants in different areas of the road to obtain the target perception results for each lane on the target road includes: If there are local spatial relationship anomalies and / or quantity anomalies in the initial perception results, the initial perception results are corrected by using the relative spatial relationships of multiple traffic participants in each area of ​​the road to obtain the target perception results for each lane on the target road. The spatial relationship anomaly includes missing location information of the target traffic participants. The step of correcting the initial perception result by utilizing the relative spatial relationships of multiple traffic participants in various areas of the road to obtain the target perception result for each lane on the target road further includes: The fitted movement trajectory of the target traffic participant is determined based on multiple initial perception results; Based on the location information of the target traffic participant before the location information was missing and the fitted movement trajectory of the target traffic participant, the missing location information of the target traffic participant is determined; Based on the missing location information of the target traffic participant, the initial perception result is filled with location information to obtain the target perception result; The step of determining the missing location information of the target traffic participant based on the location information of the target traffic participant before the location information was lost and the fitted movement trajectory of the target traffic participant includes: The predicted location of the target traffic participant is determined based on the location information of the target traffic participant before the location information is missing and the fitted movement trajectory of the target traffic participant. The predicted area of ​​the target traffic participant is determined based on the predicted location of the target traffic participant; Traffic participants are searched within the predicted area of ​​the target traffic participant, and the found traffic participants are identified as the target traffic participant. The location information of the found traffic participants is identified as the missing location information of the target traffic participant.

8. The method according to claim 7, characterized in that, The method further includes: Obtain the location information of multiple traffic participants from the sensor data; Take any one of the plurality of traffic participants as a reference traffic participant, and determine the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants. The relative spatial relationship is determined based on the reference traffic participant and its adjacent traffic participants.

9. The method according to claim 8, characterized in that, The step of determining the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants includes: A reference coordinate system is established based on the reference traffic participant; the target coordinate axis of the reference coordinate system is the driving direction of the reference traffic participant. The traffic participant located in front of the reference traffic participant and whose angle with the target coordinate axis is within a preset angle threshold is determined as the preceding adjacent traffic participant of the reference traffic participant.

10. The method according to claim 9, characterized in that, Before establishing the reference coordinate system based on the reference traffic participant, the method further includes: Based on multiple location information of the reference traffic participant, the local movement trajectory of the reference traffic participant is determined; The navigation angle of the reference traffic participant is corrected based on the local movement trajectory, and the driving direction of the reference traffic participant is determined based on the corrected navigation angle.

11. The method according to claim 8, characterized in that, The step of determining the adjacent traffic participants of the reference traffic participant based on the location information of the plurality of traffic participants includes: The adjacent area is determined with the reference traffic participant as the center, and the traffic participants in the adjacent lane that are located in the adjacent area are determined as the side adjacent traffic participants of the reference traffic participant.

12. An environmental sensing device for a target area, characterized in that, The apparatus, applied to the environmental perception method for a target area as described in claim 1 or 7, comprises: The data acquisition module is used to acquire sensor data of the target road. The first result acquisition module is used to acquire the initial sensing result based on the sensing data; The second result acquisition module is used to process the initial perception result by utilizing the relative spatial relationship of multiple traffic participants in various areas of the road to obtain the target perception result of each lane on the target road, wherein the relative spatial relationship of the multiple traffic participants is confirmed based on traffic rules.

13. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.

Images