Vehicle trajectory identification method, device, electronic device and storage medium

By obtaining and screening vehicle track segments in a multi-camera environment, identifying the inlet and exit areas, and matching the camera connection relationship, the complexity of vehicle track recognition under multiple cameras is solved, and the recognition efficiency and accuracy are improved.

CN113592903BActive Publication Date: 2024-11-12XIAN KAIHUA ELECTRONIC TECH CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202110722017.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-28
Publication Date
2024-11-12
Estimated Expiration
2041-06-28

AI Technical Summary

Technical Problem

In the smart transportation and smart city market scenarios, the target tracking task under multiple cameras is highly complex, and how to efficiently track targets is an urgent problem.

Method used

By obtaining the vehicle track segments monitored by adjacent cameras, querying the intersection setting area, determining the inlet and exit setting area, filtering and matching the track segments according to the connection relationship between the cameras, and splicing the target track of the vehicle.

Benefits of technology

It improves the accuracy and efficiency of vehicle trajectory recognition, reduces the complexity of trajectory segment screening, and enhances the efficiency of multi-objective tracking.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113592903B_ABST
    Figure CN113592903B_ABST
Patent Text Reader

Abstract

The present disclosure provides a vehicle trajectory recognition method, device, electronic device and storage medium, which relate to the field of artificial intelligence, specifically to the field of computer vision and deep learning technology, and are used in intelligent transportation and smart city scenarios. The scheme is: obtain multiple vehicle trajectory fragments monitored by each camera, query multiple intersection setting areas set in the monitoring intersection, determine the entrance setting area and exit setting area passed by each vehicle trajectory fragment, and screen multiple vehicle trajectory fragments according to the connectivity relationship between the multiple intersection setting areas, and the entrance setting area and exit setting area passed by the multiple vehicle trajectory fragments, obtain target trajectory fragments, match and splice the target trajectory fragments to obtain the target trajectory of each vehicle. Based on the connectivity relationship between the set areas of the intersections respectively monitored by two adjacent cameras, the trajectory fragments are screened, the screening efficiency is improved, and thus the efficiency of vehicle trajectory recognition is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, specifically to the field of computer vision and deep learning technology, and can be used in smart transportation and smart city scenarios, and in particular to vehicle trajectory recognition methods, devices, electronic devices and storage media. Background Art

[0002] The use of cameras to monitor and track moving targets is being used in more and more situations, such as smart transportation and smart city scenarios.

[0003] In the target tracking task, target tracking under a single camera is a basic task. Nowadays, the multi-camera multi-target tracking task derived from it is a very challenging problem. Since the angles and lighting of different cameras have a great impact on the tracked targets, the multi-target tracking task is very complex. Therefore, how to efficiently track targets is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present disclosure provides a vehicle trajectory recognition method, device, electronic device and storage medium for improving vehicle trajectory recognition efficiency.

[0005] According to one aspect of the present disclosure, a vehicle trajectory recognition method is provided, comprising:

[0006] Acquire multiple vehicle trajectory segments monitored by each camera of two cameras that are in an adjacent relationship;

[0007] Querying a plurality of intersection setting areas set in the intersections monitored by each of the cameras;

[0008] Determine a target setting area through which each of the vehicle trajectory segments passes from the plurality of intersection setting areas; wherein the target setting area includes an entrance setting area and an exit setting area;

[0009] According to the connectivity relationship between the multiple intersection set areas monitored by the two cameras and the entrance set area and the exit set area through which the multiple vehicle trajectory segments monitored by the two cameras pass, the multiple vehicle trajectory segments monitored by the two cameras are screened to obtain the retained target trajectory segments;

[0010] The target trajectory segments are matched to splice the matched target trajectory segments to obtain the target trajectory of each vehicle.

[0011] According to another aspect of the present disclosure, there is provided a vehicle track identification device, comprising:

[0012] An acquisition module, used for acquiring a plurality of vehicle trajectory segments monitored by each camera of two cameras having an adjacent relationship;

[0013] A query module, used for querying a plurality of intersection setting areas set in the intersections monitored by each of the cameras;

[0014] A determination module, used to determine, from the plurality of intersection setting areas, a target setting area through which each of the vehicle trajectory segments passes; wherein the target setting area includes an entrance setting area and an exit setting area;

[0015] A screening module, configured to screen the multiple vehicle trajectory segments monitored by the two cameras according to the connectivity relationship between the multiple intersection setting areas monitored by the two cameras and the entry setting area and the exit setting area through which the multiple vehicle trajectory segments monitored by the two cameras pass, to obtain the retained target trajectory segments;

[0016] The processing module is used to match the target trajectory segments to splice the matched target trajectory segments to obtain the target trajectory of each vehicle.

[0017] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0021] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.

[0022] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to the first aspect.

[0023] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0024] A plurality of vehicle trajectory segments monitored by each camera of two cameras having an adjacent relationship is obtained, a plurality of intersection setting areas set in the intersection monitored by each camera is queried, and an entrance setting area and an exit setting area passed by each vehicle trajectory segment are determined from the plurality of intersection setting areas, and the plurality of vehicle trajectory segments monitored by the two adjacent cameras are screened according to the connectivity relationship between the plurality of setting areas monitored by the two adjacent cameras and the entrance setting area and the exit setting area passed by the plurality of vehicle trajectory segments monitored by the two adjacent cameras to obtain the retained target trajectory segments, and the target trajectory segments are matched to splice the matched target trajectory segments to obtain the target trajectory of each vehicle, and the trajectory segments of the vehicles monitored by the two cameras are screened by identifying the entrance setting area and the exit setting area passed by the vehicle trajectory segments under a single camera and the connectivity relationship between the setting areas of the intersection respectively monitored by the two cameras having an adjacent relationship, thereby reducing the efficiency of screening the vehicle trajectory segments and improving the accuracy of screening the vehicle trajectory segments, and further obtaining the target trajectory of the vehicle by matching and splicing the target trajectory, thereby improving the accuracy of vehicle trajectory recognition.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0027] Figure 1 A flow chart of a vehicle trajectory recognition method provided by an embodiment of the present disclosure;

[0028] Figure 2 is a schematic diagram of a scenario of an embodiment of the present disclosure;

[0029] Figure 3 A flow chart of another vehicle trajectory recognition method provided by an embodiment of the present disclosure

[0030] Figure 4 A schematic diagram of the structure of a vehicle trajectory identification device provided in an embodiment of the present disclosure;

[0031] Figure 5 FIG. 8 is a schematic block diagram of an exemplary electronic device 800 according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0033] The vehicle trajectory recognition method, device, electronic device and storage medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0034] Figure 1 A flow chart of a vehicle trajectory recognition method provided in an embodiment of the present disclosure.

[0035] like Figure 1 As shown, the method comprises the following steps:

[0036] Step 101 , obtaining a plurality of vehicle trajectory segments monitored by each of two adjacent cameras.

[0037] In this embodiment, two cameras in an adjacent relationship mean that a vehicle can drive from a road section monitored by one of the two cameras to a road section monitored by the other camera. In other words, cameras set in two road sections that have a road topological relationship or a connectivity relationship are called two cameras in an adjacent relationship.

[0038] In this embodiment, the track segment of the vehicle can be generated based on the position information of the vehicle determined in advance by the tracking algorithm. As an implementation method, for each video image sequence captured by each camera, each vehicle in the video image sequence is detected using a target detection algorithm, for example, the target detection algorithm Yolov3, to obtain the position information of the detection frame of each vehicle in each frame image in the video image sequence, determine the position information of each vehicle based on the position information of the detection frame of each vehicle, and generate the track segment of each vehicle under the corresponding camera according to the position information of each vehicle in each frame image.

[0039] As another implementation method, for each video image sequence captured by a camera, a target detection algorithm is used to detect each vehicle in the video image sequence, for example, the target detection algorithm Yolov3, to obtain the position information of the detection frame of each vehicle in the first frame image in the video image sequence, and then based on the multiple object tracking algorithm (Multiple Object Tracking with Tracklet-plane matching, TPM), the track segment corresponding to each vehicle under each camera is determined.

[0040] There is a corresponding relationship between the vehicle track segments and the cameras. For example, vehicle track segment 1 is a vehicle track segment monitored by camera M, and vehicle track segment 2 is a vehicle track segment monitored by camera N.

[0041] Step 102, querying a plurality of intersection setting areas set in the intersections monitored by each camera.

[0042] In this embodiment, each camera has a corresponding monitored intersection, and a predefined area, ie, a set area, is pre-set in each monitored intersection. The set area is used to identify each intersection.

[0043] like Figure 2 As shown, taking the intersection monitored by camera A as an example, the areas marked by the boxes numbered L1-1, L1-2, L1-3, L1-4, L1-5, and L1-6 are the set areas of each intersection monitored by camera A.

[0044] It should be noted that the intersection setting area may also be a circular area, an elliptical area, etc., and the shape of the setting area is not limited in this embodiment.

[0045] Step 103 , determining a target setting area through which each vehicle trajectory segment passes from a plurality of intersection setting areas, wherein the target setting area includes an entrance setting area and an exit setting area.

[0046] In this embodiment, based on the position information carried in the vehicle trajectory fragments of each vehicle and the position information corresponding to the intersection setting area of ​​the intersection monitored by each camera, the setting area passed by each vehicle trajectory fragment is determined, and the setting area passed by the vehicle trajectory fragment is used as the target setting area, wherein the target setting area includes the entrance setting area and the exit setting area, that is, it can be determined that the vehicle's trajectory fragment passes through the entrance setting area and the exit setting area under the corresponding camera, that is, it can be determined from which setting area the vehicle enters and from which setting area the vehicle exits.

[0047] Step 104, based on the connectivity relationship between the multiple intersection set areas monitored by the two adjacent cameras and the entrance set areas and exit set areas through which the multiple vehicle trajectory segments monitored by the two adjacent cameras pass, the multiple vehicle trajectory segments monitored by the two adjacent cameras are screened to obtain the retained target trajectory segments.

[0048] In this embodiment, based on the connectivity relationship between multiple intersection setting areas monitored by two cameras that are in an adjacent relationship, that is, based on the connectivity relationship between multiple intersection setting areas monitored by one camera that are in an adjacent relationship and multiple intersection setting areas monitored by another camera, it can be determined whether multiple vehicles monitored by one camera can drive from the corresponding intersection setting area monitored by the camera to each intersection setting area monitored by another camera, for example, whether vehicle A monitored by camera A can drive from intersection 1 to one of the intersections monitored by camera B. The vehicle's trajectory fragment records the vehicle's position information in each video frame, so that according to the entrance setting area and exit setting area passed by the vehicle's trajectory fragment monitored by a single camera, it can be determined whether the vehicle can reach the monitoring area of ​​another camera from the monitoring area of ​​the current surveillance camera. Therefore, according to the entrance setting area and exit setting area passed by multiple vehicle trajectory fragments monitored by two cameras, and according to the connectivity relationship between the multiple intersection setting areas monitored by the two cameras, the trajectory fragments of vehicles that cannot drive from the multiple intersection setting areas monitored by one camera to the multiple intersection setting areas monitored by another camera can be screened out and deleted to obtain the retained target trajectory fragments, wherein the retained target trajectory fragments belong to the multiple vehicle trajectory fragments monitored by two cameras that are in an adjacent relationship, thereby realizing the retention of the trajectory fragments of vehicles traveling between the intersections monitored by the two cameras, thereby improving the efficiency of subsequent matching and splicing of the vehicle's trajectory fragments.

[0049] Step 105 , matching the target trajectory segments to splice the matched target trajectory segments to obtain the target trajectory of each vehicle.

[0050] In this embodiment, the target trajectory segments monitored by the two cameras are matched. As an implementation method, the vehicle features of the vehicles to which the target trajectory segments monitored by the two cameras belong are obtained, and the matching target trajectory segments are determined based on the vehicle features through the Hungarian matching algorithm, and the matching target trajectory segments are spliced ​​to obtain the target trajectory of each vehicle.

[0051] Among them, the matched target trajectory segments are trajectory segments monitored by two cameras, thereby realizing multi-target tracking under multiple cameras and improving the tracking efficiency.

[0052] In the vehicle trajectory recognition method of the present embodiment, a plurality of vehicle trajectory segments monitored by each of two adjacent cameras are obtained, a plurality of intersection setting areas set in the intersection monitored by each camera are queried, and an entry setting area and an exit setting area passed by each vehicle trajectory segment are determined from the plurality of intersection setting areas. According to the connectivity relationship between the plurality of setting areas monitored by the two adjacent cameras and the entry setting area and the exit setting area passed by the plurality of vehicle trajectory segments monitored by the two adjacent cameras, the plurality of vehicle trajectory segments monitored by the two adjacent cameras are screened to obtain the retained target trajectory segments, and the target trajectory segments are matched to splice the matched target trajectory segments to obtain the target trajectory of each vehicle. By identifying the entry setting area and the exit setting area passed by the trajectory segments of the vehicle under a single camera and the connectivity relationship between the setting areas of the intersection respectively monitored by the two adjacent cameras, the trajectory segments of the vehicle monitored under the two cameras are screened, thereby improving the screening efficiency. Furthermore, the target trajectory of the vehicle is obtained by matching and splicing the target trajectory, thereby improving the efficiency of vehicle trajectory recognition.

[0053] Based on the above embodiment, this embodiment provides another possible implementation of the vehicle trajectory recognition method, such as Figure 3 As shown, the method comprises the following steps:

[0054] Step 301: Acquire a plurality of vehicle trajectory segments monitored by each camera of two cameras that are in an adjacent relationship.

[0055] Step 302, querying a plurality of intersection setting areas set in the intersections monitored by each camera.

[0056] like Figure 2 As shown, the areas marked by the rectangular boxes numbered L1-1, L1-2, L1-3, L1-4, L1-5, and L1-6 are the set areas of each intersection monitored by camera A, and the areas marked by the rectangular boxes numbered L2-1, L2-2, L2-3, L2-4, L2-5, and L2-6 are the set areas of each intersection monitored by camera B.

[0057] Among them, step 301 and step 302 can refer to the explanations in the aforementioned steps 101 and 102, and the principles are the same, so they will not be repeated in this embodiment.

[0058] Step 303, for each camera, the position information of each vehicle contained in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera to determine the entry setting area and the exit setting area passed by each vehicle trajectory segment.

[0059] In this embodiment, for each camera, based on the position information, the entry set area and the exit set area passed by each vehicle trajectory segment monitored by the corresponding camera are determined, thereby realizing the determination of the vehicle entry and exit intersections in the monitoring area of ​​a single camera, facilitating the subsequent screening of the vehicle entry and exit intersections in the monitoring area of ​​each single camera, thereby improving the efficiency and accuracy of the screening.

[0060] Accurately determining the entry setting area and exit setting area that each vehicle trajectory segment passes through can improve the accuracy of subsequent screening. Therefore, this embodiment provides an implementation method for identifying the entry setting area and exit setting area that the vehicle trajectory segment passes through based on the position information of the detection frame of the vehicle contained in the vehicle trajectory segment. Specifically, for each camera, each vehicle trajectory segment monitored by the camera contains the position information of the vehicle in each frame of the image, so that the position information of the detection frame of the vehicle contained in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the same camera, and the vehicle trajectory segment contains The initial position information of the detection frame of the vehicle is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera. When determining the entrance setting area, when the vehicle appears in the video, the first intersection setting area that matches the initial position information of the vehicle detection frame is used as the entrance setting area through which the vehicle track segment passes; and the intersection setting area that matches the end position information of the detection frame is used as the exit setting area through which the vehicle track segment passes. That is to say, when determining the exit setting area, when the vehicle disappears in the video collected by the camera, the intersection setting area that matches the end position information corresponding to when the vehicle detection frame disappears is used as the exit setting area through which the vehicle track segment passes. This embodiment identifies the entrance setting area and the exit setting area through which the vehicle track segment passes based on the relationship between the change in the position information of the detection frame of the vehicle contained in the vehicle track segment and the position information of each setting area, and the recognition efficiency is high and the accuracy is also high.

[0061] It should be understood that the end position information of the vehicle detection frame is the position information of the vehicle detection frame in the last frame image in the video image sequence corresponding to the vehicle's trajectory segment.

[0062] Furthermore, in an implementation of the present embodiment, in order to improve the accuracy of the entrance setting area matching, the first setting area in each intersection setting area that completely contains the initial position information of the detection box of the vehicle contained in the vehicle trajectory fragment is used as the entrance setting area, thereby reducing the misrecognition rate and improving the recognition efficiency.

[0063] The position information of the detection frame includes the position of the detection frame and the size of the detection frame, and is used to indicate the area information where the vehicle is located in the image. The area information includes the size of the area and the position of the area.

[0064] For example, in camera A, for the vehicle trajectory segment of the monitored vehicle 1, it is identified that the entrance setting area of ​​the vehicle 1 is L1-1, and the exit setting area is L1-4.

[0065] Step 304, based on the connectivity relationship between the multiple intersection set areas monitored by the two cameras and the entry set areas and exit set areas through which the multiple vehicle trajectory segments monitored by the two cameras pass, the multiple vehicle trajectory segments monitored by the two cameras are screened to obtain the retained target trajectory segments.

[0066] In one implementation of the present embodiment, for any two vehicle trajectory segments belonging to two cameras that are in an adjacent relationship, if there is a connectivity relationship between an exit setting area passed by one vehicle trajectory segment and an entrance setting area passed by another vehicle trajectory segment, or if there is a connectivity relationship between an entrance setting area passed by one vehicle trajectory segment and an exit setting area passed by another vehicle trajectory segment, the two vehicle trajectory segments are taken as retained target trajectory segments.

[0067] For example, Figure 2 As shown, camera A and camera B are two adjacent cameras, that is, the vehicle can drive from the monitoring area of ​​camera A to the monitoring area of ​​camera B, or the vehicle can drive from the monitoring area of ​​camera B to the monitoring area of ​​camera A.

[0068] Among them, the entry setting area and exit setting area passed by each vehicle trajectory segment monitored by camera A are:

[0069] The entry setting area passed by vehicle trajectory segment 1 is L1-1, and the exit setting area is L1-4; the entry setting area passed by vehicle trajectory segment 2 is L1-5, and the exit setting area is L1-4; the entry setting area passed by vehicle trajectory segment 3 is L1-6, and the exit setting area is L1-4; the entry setting area passed by vehicle trajectory segment 4 is L1-1, and the exit setting area is L1-5.

[0070] The entry and exit setting areas of each vehicle trajectory segment monitored by camera B are:

[0071] The entry setting area passed by vehicle trajectory segment 5 is L2-1, and the exit setting area is L2-4; the entry setting area passed by vehicle trajectory segment 6 is L2-1, and the exit setting area is L2-5; the entry setting area passed by vehicle trajectory segment 7 is L2-1, and the exit setting area is L2-6; the entry setting area passed by vehicle trajectory segment 8 is L2-6, and the exit setting area is L2-5.

[0072] Figure 2 In the example, there is a connection relationship between the set area L1-4 monitored by camera A and the set area L2-1 monitored by camera B, that is, when the vehicle exits the set area L1-4 monitored by camera A, it will enter the set area L2-1 monitored by camera B. However, there is no connection relationship between the set area L1-5 monitored by camera A and the set area monitored by camera B, that is, when the vehicle exits the set area L1-5 monitored by camera A, it will not enter any set area monitored by camera B.

[0073] In a scenario of this embodiment, when there is a connectivity relationship between an exit setting area passed by a vehicle trajectory segment and an entrance setting area passed by another vehicle trajectory segment, for example Figure 2 In the example, the vehicle drives from the monitoring area of ​​camera A to the monitoring area of ​​camera B, wherein the exit setting area passed by the trajectory segment 1 monitored by camera A is L1-4. Since there is a connectivity relationship between the setting area L1-4 monitored by camera A and the setting area L2-1 monitored by camera B, there is a connectivity relationship between the exit setting area L1-4 passed by vehicle trajectory segment 1 and the entrance setting area L2-1 passed by vehicle trajectory segment 5; there is a connectivity relationship between the exit setting area L1-4 passed by vehicle trajectory segment 2 and the entrance setting area L2-1 passed by vehicle trajectory segment 6; there is a connectivity relationship between the exit setting area L1-4 passed by vehicle trajectory segment 3 and the entrance setting area L2-1 passed by vehicle trajectory segment 7, so that the vehicle trajectory segments 1, 2 and 3 with the exit setting area L1-4 monitored by camera A are the retained target trajectory segments, and the vehicle trajectory segment 4 is the deleted vehicle trajectory segment. At the same time, in the vehicle trajectory frequency band monitored by camera B, vehicle trajectory segment 5, vehicle trajectory segment 6 and vehicle trajectory segment 7 are retained target trajectory segments, and vehicle trajectory segment 8 is a deleted vehicle trajectory segment.

[0074] It should be noted that for Figure 2 The method for determining the trajectory segments passing through other set areas is the same and will not be listed one by one in this embodiment.

[0075] It should be understood that in another scenario, when there is a connectivity relationship between the entry setting area passed by one vehicle trajectory segment and the exit setting area passed by another vehicle trajectory segment, for example Figure 2 In the embodiment, the vehicle drives from the monitoring area of ​​camera B to the monitoring area of ​​camera A. The implementation principle is the same as that of the vehicle driving from the monitoring area of ​​camera A to the monitoring area of ​​camera B in the previous scenario, and will not be repeated in this embodiment.

[0076] In this embodiment, for the vehicle trajectory segments belonging to two cameras, the vehicle trajectory segments are screened according to the connectivity relationship between the exit setting area and the entrance setting area passed by any two vehicle trajectory segments. This can accurately remove the vehicle trajectory segments of vehicles that cannot travel in the monitoring area between the two cameras, with fast calculation speed and high accuracy.

[0077] Step 305 , matching the target trajectory segments to splice the matched target trajectory segments to obtain the target trajectory of each vehicle.

[0078] In one implementation of the present embodiment, vehicle features of the vehicles to which each target trajectory segment monitored by each of the two cameras belongs are obtained, wherein the vehicle features may be re-identification (ReID) features of the vehicle, and the target trajectory segments are matched according to the features of each vehicle, and the matched target trajectory segments belonging to the same vehicle are spliced ​​to obtain the target trajectories of each vehicle, and the target trajectory segments belonging to the same vehicle are identified by using the ReID features of the vehicle, so as to splice the target trajectory segments belonging to the same vehicle, so as to obtain the target trajectory of the corresponding vehicle in the two cameras that are in an adjacent relationship, thereby realizing trajectory recognition and tracking of vehicles in multiple cameras, which is simple and efficient.

[0079] In this embodiment, multiple vehicle trajectory segments monitored by each camera of two cameras that are in an adjacent relationship are obtained, and multiple intersection setting areas set in the intersection monitored by each camera are queried. From the multiple intersection setting areas, the entry setting area and the exit setting area passed by each vehicle trajectory segment are determined. According to the connectivity relationship between the multiple setting areas monitored by the two adjacent cameras and the entry setting area and the exit setting area passed by the multiple vehicle trajectory segments monitored by the two adjacent cameras, the multiple vehicle trajectory segments monitored by the two adjacent cameras are screened to obtain the retained target trajectory segments, and the target trajectory segments are matched to splice the matched target trajectory segments to obtain the target trajectory of each vehicle. By identifying the entry setting area and the exit setting area passed by the trajectory segments of the vehicle under a single camera and the connectivity relationship between the setting areas of the intersection respectively monitored by the two adjacent cameras, the trajectory segments of the vehicle monitored under the two cameras are screened, thereby improving the screening efficiency. Furthermore, the target trajectory of the vehicle is obtained by matching and splicing the target trajectory, thereby improving the efficiency of vehicle trajectory recognition.

[0080] Based on the above embodiments, this embodiment provides a vehicle trajectory recognition device.

[0081] Figure 4 A vehicle trajectory recognition device is provided in an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0082] The acquisition module 41 is used to acquire a plurality of vehicle track segments monitored by each camera of two cameras that are in a neighboring relationship.

[0083] The query module 42 is used to query a plurality of intersection setting areas set in the intersections monitored by each of the cameras.

[0084] The determination module 43 is used to determine, from the plurality of intersection setting areas, a target setting area through which each of the vehicle trajectory segments passes; wherein the target setting area includes an entrance setting area and an exit setting area.

[0085] The screening module 44 is used to screen the multiple vehicle trajectory segments monitored by the two cameras according to the connectivity relationship between the multiple intersection setting areas monitored by the two cameras and the entrance setting area and the exit setting area through which the multiple vehicle trajectory segments monitored by the two cameras pass, so as to obtain the retained target trajectory segments.

[0086] The processing module 45 is used to match the target trajectory segments to splice the matched target trajectory segments to obtain the target trajectory of each vehicle.

[0087] Furthermore, in one implementation of the embodiment of the present application, the screening module 44 is specifically used to:

[0088] For any two vehicle trajectory segments, if there is a connectivity relationship between the exit setting area passed by one vehicle trajectory segment and the entrance setting area passed by another vehicle trajectory segment, or if there is a connectivity relationship between the entrance setting area passed by one vehicle trajectory segment and the exit setting area passed by another vehicle trajectory segment, the two vehicle trajectory segments are taken as retained target trajectory segments, wherein the any two vehicle trajectory segments belong to the two adjacent cameras.

[0089] In one implementation of the embodiment of the present application, the determination module 43 is specifically configured to:

[0090] For each camera, the position information of the vehicles contained in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera to determine the entrance setting area and exit setting area passed by each vehicle trajectory segment.

[0091] In one implementation of the embodiment of the present application, the determination module 43 is further configured to:

[0092] For each vehicle trajectory segment, matching the initial position information of the detection frame of the vehicle contained in the vehicle trajectory segment with the position information of multiple intersection setting areas in the camera-monitored intersection, and taking the first intersection setting area that matches the initial position information of the detection frame as the entrance setting area passed by the vehicle trajectory segment; and

[0093] The intersection setting area that matches the end position information of the detection frame is used as the exit setting area passed by the vehicle trajectory segment.

[0094] In one implementation of the embodiment of the present application, the processing module 45 is specifically configured to:

[0095] Obtaining vehicle features of vehicles to which each target trajectory segment monitored by each of the two cameras belongs;

[0096] The target trajectory segments are matched according to the features of each vehicle, and the matched target trajectory segments belonging to the same vehicle are spliced ​​to obtain the target trajectory of each vehicle.

[0097] It should be noted that the explanations and descriptions of the aforementioned method embodiments are also applicable to the device of this embodiment, and the principles are the same, which will not be repeated in this embodiment.

[0098] In the vehicle trajectory recognition device of the present embodiment, a plurality of vehicle trajectory segments monitored by each camera of two cameras having an adjacent relationship are obtained, a plurality of intersection setting areas set in the intersection monitored by each camera are queried, and an entrance setting area and an exit setting area passed by each vehicle trajectory segment are determined from the plurality of intersection setting areas. According to the connectivity relationship between the plurality of setting areas monitored by the two adjacent cameras and the entrance setting area and the exit setting area passed by the plurality of vehicle trajectory segments monitored by the two adjacent cameras, the plurality of vehicle trajectory segments monitored by the two adjacent cameras are screened to obtain the retained target trajectory segments, and the target trajectory segments are matched to splice the matched target trajectory segments to obtain the target trajectory of each vehicle. By identifying the entrance setting area and the exit setting area passed by the trajectory segments of the vehicle under a single camera and the connectivity relationship between the setting areas of the intersection respectively monitored by the two adjacent cameras, the trajectory segments of the vehicle monitored under the two cameras are screened, thereby improving the screening efficiency. Furthermore, the target trajectory of the vehicle is obtained by matching and splicing the target trajectory, thereby improving the efficiency of vehicle trajectory recognition.

[0099] In order to implement the above embodiment, this embodiment provides an electronic device, including:

[0100] at least one processor; and

[0101] a memory communicatively connected to the at least one processor; wherein,

[0102] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the foregoing method embodiment.

[0103] In order to implement the above embodiment, this embodiment provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in the above method embodiment.

[0104] In order to implement the above embodiment, this embodiment provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in the above method embodiment is implemented.

[0105] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0106] Figure 5Schematic block diagram of an example electronic device 800 of an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0107] like Figure 5 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 802 or a computer program loaded from a storage unit 808 to a RAM (Random Access Memory) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An I / O (Input / Output) interface 805 is also connected to the bus 804.

[0108] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0109] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as a vehicle trajectory recognition method. For example, in some embodiments, the vehicle trajectory recognition method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the vehicle trajectory recognition method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the vehicle trajectory identification method in any other appropriate manner (eg, by means of firmware).

[0110] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0112] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0115] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0116] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0118] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle trajectory recognition method, It is characterized in that include: Acquire multiple vehicle trajectory segments monitored by each camera of two cameras that are in an adjacent relationship; Querying a plurality of intersection setting areas set in the intersections monitored by each of the cameras; Determine, from the plurality of intersection setting areas, a target setting area through which each of the vehicle trajectory segments passes; wherein the target setting area includes an entrance setting area and an exit setting area; For any two vehicle trajectory segments, if there is a connectivity relationship between the exit setting area passed by one vehicle trajectory segment and the entrance setting area passed by another vehicle trajectory segment, or if there is a connectivity relationship between the entrance setting area passed by one vehicle trajectory segment and the exit setting area passed by another vehicle trajectory segment, the two vehicle trajectory segments are taken as the reserved target trajectory segments, wherein the any two vehicle trajectory segments belong to the two cameras; Obtaining vehicle features of vehicles to which each target trajectory segment monitored by each of the two cameras belongs; The target trajectory segments are matched according to the vehicle features, and the matched target trajectory segments belonging to the same vehicle are spliced ​​to obtain the target trajectory of each vehicle.

2. The method according to claim 1, It is characterized in that The step of determining, from the plurality of intersection setting areas, a target setting area through which each of the vehicle trajectory segments passes comprises: For each camera, the position information of the vehicles contained in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera to determine the entrance setting area and exit setting area passed by each vehicle trajectory segment.

3. The method according to claim 2, It is characterized in that The position information includes the position information of the detection frame of the vehicle, and for each camera, the position information of the vehicle included in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera to determine the entrance setting area and the exit setting area passed by each vehicle trajectory segment, including: For each vehicle trajectory segment, matching the initial position information of the detection frame of the vehicle contained in the vehicle trajectory segment with the position information of multiple intersection setting areas in the camera-monitored intersection, and taking the first intersection setting area that matches the initial position information of the detection frame as the entrance setting area passed by the vehicle trajectory segment; and The intersection setting area that matches the end position information of the detection frame is used as the exit setting area passed by the vehicle trajectory segment.

4. A vehicle trajectory recognition device, It is characterized in that include: An acquisition module, used for acquiring a plurality of vehicle trajectory segments monitored by each camera of two cameras having an adjacent relationship; A query module, used for querying a plurality of intersection setting areas set in the intersections monitored by each of the cameras; A determination module, used to determine, from the plurality of intersection setting areas, a target setting area through which each of the vehicle trajectory segments passes; wherein the target setting area includes an entrance setting area and an exit setting area; a screening module, for any two vehicle trajectory segments, when there is a connectivity relationship between the exit setting area passed by one vehicle trajectory segment and the entrance setting area passed by another vehicle trajectory segment, or when there is a connectivity relationship between the entrance setting area passed by one vehicle trajectory segment and the exit setting area passed by another vehicle trajectory segment, taking the two vehicle trajectory segments as target trajectory segments to be retained, wherein the any two vehicle trajectory segments belong to the two cameras; The processing module is used to obtain vehicle features of the vehicles to which each target trajectory segment monitored by each of the two cameras belongs; match the target trajectory segments according to the vehicle features, and splice the matched target trajectory segments belonging to the same vehicle to obtain the target trajectory of each vehicle.

5. The device as claimed in claim 4, It is characterized in that The determining module is specifically used for: For each camera, the position information of the vehicles contained in each vehicle trajectory segment monitored by the camera is matched with the position information of multiple intersection setting areas in the intersection monitored by the camera to determine the entrance setting area and exit setting area passed by each vehicle trajectory segment.

6. The device as claimed in claim 5, It is characterized in that The determination module is further specifically used for: For each vehicle trajectory segment, the initial position information of the detection frame of the vehicle contained in the vehicle trajectory segment is matched with the position information of multiple intersection setting areas in the camera monitoring intersection, and the first intersection setting area that matches the initial position information of the detection frame is used as the entrance setting area passed by the vehicle trajectory segment; as well as The intersection setting area that matches the end position information of the detection frame is used as the exit setting area passed by the vehicle trajectory segment.

7. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-3.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 3.

Citation Information

Patent Citations

  • Vehicle management method and system based on video stitching

    CN111405196A

  • Drunk driving recognition method and device based on artificial intelligence, equipment and medium

    CN112115890A

  • Entrance and exit position detection method, navigation method, device, equipment and storage medium

    CN112859125A

  • Traffic restriction recognition method and device, electronic equipment and storage medium

    CN113029180A

  • Vehicle track identification in synthetic aperture radar images

    US10032077B1