Vehicle cross-camera tracking method, navigation method, system, equipment and medium

Abstract

The invention discloses a vehicle cross-camera tracking method, a navigation method, a system, equipment and a medium. The method comprises the steps that first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to a target vehicle are acquired respectively, and whether the target vehicle completes cross-camera matching in the current camera or not is judged according to the first vehicle information and the second vehicle information; if yes, a matching result is generated, first vehicle information of the target vehicle is updated according to the matching result, first updated vehicle information is obtained, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system; and if not, judging whether the current camera recognizes the first license plate information of the target vehicle, if so, updating the first vehicle information of the target vehicle according to the first license plate information to obtain second updated vehicle information, and uploading the second updated vehicle information to the vehicle cross-camera navigation system. Through cross-camera tracking of the vehicle, the accuracy of vehicle navigation in the parking lot is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent video surveillance technology, and in particular to a vehicle cross-camera tracking method, a navigation method, a system, a device and a medium. Background Art

[0002] Currently, although vehicle identification devices are widely used at the entrances and exits of various parking lots and inside, they still face challenges in achieving accurate vehicle guidance throughout the entire parking lot. Especially when the owner is driving at high speeds, existing systems often have difficulty providing timely and effective navigation information, which reduces the overall user satisfaction. In addition, the complexity of the internal environment of the parking lot, including poor mobile phone network caused by signal shielding, especially in underground parking lots, further exacerbates the problem of navigation accuracy. When trying to track vehicles in real time through cross-camera technology, the failure or abnormality of some linked cameras may have an adverse effect on the stability and accuracy of the navigation system, which puts more stringent requirements on the robustness of the navigation system.

[0003] Therefore, how to improve the accuracy of vehicle navigation in parking lots has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the technical problems of low accuracy, adaptability and stability of vehicle navigation in existing parking lots, the present application provides a vehicle cross-camera tracking method, navigation method, system, device and medium.

[0005] The present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present disclosure provides a vehicle cross-camera tracking method, which is applied to a vehicle cross-camera tracking system. The method includes:

[0007] Respectively obtain first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to the target vehicle, and determine whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information;

[0008] If the target vehicle completes cross-camera matching in the current camera, a matching result is generated, and first vehicle information of the target vehicle is updated according to the matching result to obtain first updated vehicle information, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system;

[0009] If the target vehicle has not completed cross-camera matching in the current camera, it is determined whether the current camera recognizes the first license plate information of the target vehicle. If the first license plate information is recognized, the first vehicle information of the target vehicle is updated according to the first license plate information to obtain the second vehicle information, and the second updated vehicle information is uploaded to the vehicle cross-camera navigation system.

[0010] Optionally, the first vehicle information and the second vehicle information both include a vehicle position, and judging whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information includes:

[0011] Acquire a first high-precision map and first calibration information within the field of view of the current camera, and acquire a second high-precision map and second calibration information within the field of view of the adjacent camera;

[0012] Converting the vehicle position in the first vehicle information into a first real physical coordinate by using the first high-precision map and the first calibration information, and converting the vehicle position in the second vehicle information into a second real physical coordinate by using the second high-precision map and the second calibration information;

[0013] Comparing the first real physical coordinate with the second real physical coordinate to obtain a similarity, and determining whether the similarity is greater than a preset similarity threshold;

[0014] If the similarity is greater than the preset similarity threshold, it is determined that the target vehicle has completed cross-camera matching in the current camera; if the similarity is less than or equal to the preset similarity threshold, it is determined that the target vehicle has not completed cross-camera matching in the current camera.

[0015] Optionally, updating the first vehicle information of the target vehicle according to the first license plate information includes:

[0016] Acquire the second license plate information within a preset time threshold uploaded by the adjacent camera, and determine whether the first license plate information is consistent with the second license plate information;

[0017] If the first license plate information is consistent with the second license plate information, updating the first vehicle information of the target vehicle according to the first license plate information, and marking the target vehicle as a matched vehicle;

[0018] If the first license plate information is inconsistent with the second license plate information, obtaining the first real position of the target vehicle in the current camera, and obtaining the second real position of the target vehicle uploaded by the adjacent camera;

[0019] Calculating a real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than a preset distance threshold is 1;

[0020] If the number of vehicles whose actual distance is less than the preset distance threshold is 1, updating the first vehicle information of the target vehicle according to the second license plate information, and marking the target vehicle as a matched vehicle;

[0021] If the number of vehicles whose actual distance is less than the preset distance threshold is not 1, the first vehicle information of the target vehicle is updated according to the first license plate information, and the target vehicle is marked as an unmatched vehicle.

[0022] Optionally, after determining whether the current camera recognizes the first license plate information of the target vehicle, the method further includes:

[0023] If the first license plate information is not recognized, obtaining a first real position of the target vehicle in the current camera, and obtaining a second real position of the target vehicle uploaded by the adjacent camera;

[0024] Calculating a real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than the preset distance threshold is 1;

[0025] If the number of vehicles whose actual distance is less than the preset distance threshold is 1, the first vehicle information of the target vehicle is updated, the updated third updated vehicle information is uploaded to the vehicle cross-camera navigation system, and the target vehicle is marked as a matched vehicle.

[0026] According to a second aspect of the present application, an embodiment provides a vehicle cross-camera navigation method, which is applied to a vehicle cross-camera navigation system, and the method includes:

[0027] Receiving first updated vehicle information or second updated vehicle information uploaded by the vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method according to the first aspect;

[0028] determining whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval;

[0029] If the first updated vehicle information or the second updated vehicle information is received within the continuous preset time interval, planning a navigation route according to the most recently received first updated vehicle information or second updated vehicle information;

[0030] If the first updated vehicle information or the second updated vehicle information is not received within the continuous preset time interval, the inertial sensor data uploaded by the target vehicle is obtained, the vehicle position and vehicle speed of the target vehicle at the current moment are calculated according to the inertial sensor data, and the navigation path is planned according to the vehicle position and vehicle speed at the current moment.

[0031] Optionally, the method further comprises:

[0032] Determining whether a vehicle speed in the first updated vehicle information or the second updated vehicle information is less than a preset speed threshold;

[0033] If the vehicle speed in the first updated vehicle information or the second updated vehicle information is less than the preset speed threshold, Bluetooth beacon data is obtained, the first updated vehicle information or the second updated vehicle information is corrected according to the Bluetooth beacon data to obtain corrected vehicle information, and the navigation path is planned according to the corrected vehicle information.

[0034] According to a third aspect of the present application, an embodiment provides a vehicle cross-camera tracking system, the system comprising:

[0035] An acquisition module, used to respectively acquire first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to a target vehicle, and determine whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information;

[0036] A first updating module, configured to generate a matching result if the target vehicle completes cross-camera matching in the current camera, and update first vehicle information of the target vehicle according to the matching result to obtain first updated vehicle information, and upload the first updated vehicle information to the vehicle cross-camera navigation system;

[0037] The second updating module is used to determine whether the current camera recognizes the first license plate information of the target vehicle if the target vehicle has not completed cross-camera matching in the current camera; if the first license plate information is recognized, update the first vehicle information of the target vehicle according to the first license plate information to obtain second updated vehicle information, and upload the second updated vehicle information to the vehicle cross-camera navigation system.

[0038] According to a fourth aspect of the present application, an embodiment provides a vehicle cross-camera navigation system, the system comprising:

[0039] A receiving module, configured to receive first updated vehicle information or second updated vehicle information uploaded by the vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method according to the first aspect;

[0040] A determination module, configured to determine whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval;

[0041] A first planning module, configured to plan a navigation path according to the most recently received first updated vehicle information or second updated vehicle information if the first updated vehicle information or the second updated vehicle information is received within the continuous preset time interval;

[0042] The second planning module is used to obtain the inertial sensor data uploaded by the target vehicle if the first updated vehicle information or the second updated vehicle information is not received within the continuous preset time interval, calculate the vehicle position and vehicle speed of the target vehicle at the current moment according to the inertial sensor data, and plan the navigation path according to the vehicle position and vehicle speed at the current moment.

[0043] According to the fifth aspect of the present application, a computer device is provided in one embodiment, wherein the computer device includes a memory for storing programs; and a processor for executing the programs stored in the memory to implement the vehicle cross-camera tracking method as described in the first aspect or the vehicle cross-camera navigation method as described in the second aspect.

[0044] According to the sixth aspect of the present application, in one embodiment, a computer-readable storage medium is provided, comprising a program, which can be executed by a processor to implement the vehicle cross-camera tracking method as described in the first aspect or the vehicle cross-camera navigation method as described in the second aspect.

[0045] Beneficial effects of this application:

[0046] The vehicle cross-camera tracking method provided in the embodiment of the present application obtains the first vehicle information and the second vehicle information collected by the current camera and the adjacent camera corresponding to the target vehicle respectively, and judges whether the target vehicle has completed the cross-camera matching in the current camera according to the first vehicle information and the second vehicle information; if the target vehicle has completed the cross-camera matching in the current camera, a matching result is generated, and the first vehicle information of the target vehicle is updated according to the matching result to obtain the first updated vehicle information, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system; if the target vehicle has not completed the cross-camera matching in the current camera, it is judged whether the current camera recognizes the first license plate information of the target vehicle, and if the first license plate information is recognized, the first vehicle information of the target vehicle is updated according to the first license plate information to obtain the second updated vehicle information, and the second updated vehicle information is uploaded to the vehicle cross-camera navigation system. The above method improves the accuracy of vehicle navigation in the parking lot by tracking the vehicle across cameras.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work. In each of the drawings, similar components are numbered similarly.

[0049] Figure 1 One of the flow charts of the vehicle cross-camera tracking method provided by an embodiment of the present application is shown;

[0050] Figure 2 The second flowchart of the vehicle cross-camera tracking method provided by the embodiment of the present application is shown;

[0051] Figure 3 One of the distribution diagrams of camera directions provided in an embodiment of the present application is shown;

[0052] Figure 4 The second distribution diagram of the camera direction provided in the embodiment of the present application is shown;

[0053] Figure 5 The third flowchart of the vehicle cross-camera tracking method provided by the embodiment of the present application is shown;

[0054] Figure 6A fourth flowchart of the vehicle cross-camera tracking method provided in an embodiment of the present application is shown;

[0055] Figure 7 One of the flow charts of the vehicle cross-camera navigation method provided by an embodiment of the present application is shown;

[0056] Figure 8 The second flowchart of the vehicle cross-camera navigation method provided by the embodiment of the present application is shown;

[0057] Fig. 9 A schematic diagram of the structure of a vehicle cross-camera tracking system provided by an embodiment of the present application is shown;

[0058] Fig.10 A schematic structural diagram of a vehicle cross-camera navigation system provided by an embodiment of the present application is shown;

[0059] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0060] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0061] Example 1

[0062] like Figure 1 FIG. 1 is a flow chart of a vehicle cross-camera tracking method in an embodiment of the present application. The vehicle cross-camera tracking method provided in an embodiment of the present application is applied to a vehicle cross-camera tracking system. The method specifically includes the following steps:

[0063] Step S110, respectively obtaining first vehicle information and second vehicle information collected by the current camera and the adjacent camera corresponding to the target vehicle, and determining whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information.

[0064] In an optional embodiment, if Figure 2 As shown, step S110 also includes:

[0065] Step S111, obtaining a first high-precision map and first calibration information within the field of view of the current camera, and obtaining a second high-precision map and second calibration information within the field of view of an adjacent camera;

[0066] Step S112, converting the vehicle position in the first vehicle information into a first real physical coordinate through the first high-precision map and the first calibration information, and converting the vehicle position in the second vehicle information into a second real physical coordinate through the second high-precision map and the second calibration information;

[0067] Step S113, comparing the first real physical coordinate with the second real physical coordinate to obtain a similarity, and determining whether the similarity is greater than a preset similarity threshold;

[0068] Step S114: if the similarity is greater than a preset similarity threshold, it is determined that the target vehicle has completed cross-camera matching in the current camera; if the similarity is less than or equal to the preset similarity threshold, it is determined that the target vehicle has not completed cross-camera matching in the current camera.

[0069] It should be noted that the specific situation of adjacent cameras is as follows Figure 3 and Figure 4 As shown, Figure 3 The two location cameras are located adjacent to each other. Figure 4 The two location cameras are distributed adjacent to each other in the same direction. As long as the cameras are adjacent in physical position, they need to be able to transmit information to each other. The lane area refers to the lane area generated according to the parking space that can effectively identify the license plate. The tracking area refers to the area extending a certain distance (for example, 8 meters) away from the lane area. The vehicle can be tracked in the overlapping part of the picture taken by the camera (that is, the tracking area). When the pictures taken by the cameras do not overlap, the vehicle needs to enter the lane area camera to track it.

[0070] In this embodiment, firstly, the first vehicle information of the target vehicle collected by the current camera and the second vehicle information of the target vehicle collected by the adjacent camera are obtained, and the first vehicle information and the second vehicle information each include at least one of the vehicle position, vehicle speed and time data. Then, the first high-precision map and the first calibration information, the second high-precision map and the second calibration information corresponding to the respective field of view of the current camera and the adjacent camera are obtained, and the respective corresponding vehicle positions are converted into the first real physical coordinates and the second real physical coordinates through the above two high-precision maps and the two calibration information.

[0071] It should be noted that this embodiment does not involve camera calibration related content. The default camera has been calibrated and can convert the vehicle position in the image pixel content into real physical coordinates. The real physical coordinates can be longitude and latitude coordinates, or the coordinate system established by the navigation system, based on the coordinate format of the transmitted high-precision map, and this embodiment of the application does not limit this.

[0072] It can be understood that, in this embodiment, information can be transmitted between adjacent cameras, but information cannot be transmitted between non-adjacent cameras.

[0073] Optionally, the first real physical coordinate detected by the current camera is compared with the second real physical coordinate detected by the adjacent camera, and a similarity measurement method (such as cosine similarity, Euclidean distance, etc.) is used to obtain the similarity between the two vehicle positions. If the similarity exceeds a preset similarity threshold (such as 95%), it is determined that the target vehicle has completed cross-camera matching in the current camera, otherwise it is determined that the target vehicle has not completed cross-camera matching in the current camera.

[0074] The above method can ensure the continuous tracking of the target vehicle between multiple cameras and more accurately identify the vehicle information of the target vehicle by judging whether the current camera and the adjacent camera have completed cross-camera matching.

[0075] Step S120: If the target vehicle completes cross-camera matching in the current camera, a matching result is generated, and the first vehicle information of the target vehicle is updated according to the matching result to obtain first updated vehicle information, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system.

[0076] In one embodiment, if the target vehicle completes cross-camera matching in the current camera, a matching result is generated, including identity (such as a unique identifier such as a license plate number or a vehicle feature code), position (relative position or absolute coordinates in the current camera), and possible changes in driving trajectory, and further updates the first vehicle information related to the target vehicle in the current camera based on the matching result to obtain the first updated vehicle information, and reports the first updated vehicle information to the adjacent camera and uploads it to the vehicle cross-camera navigation system.

[0077] The above method ensures the real-time nature of vehicle information by updating vehicle information, and can more accurately track the driving trajectory and status of the target vehicle. The updated vehicle information is uploaded to the vehicle cross-camera navigation system, which enables the vehicle cross-camera navigation system to more accurately understand the current position and driving status of the target vehicle, so that the path planning can be dynamically adjusted, providing more accurate navigation services and improving navigation efficiency and safety.

[0078] Step S130, if the target vehicle has not completed cross-camera matching in the current camera, determine whether the current camera recognizes the first license plate information of the target vehicle. If the first license plate information is recognized, update the first vehicle information of the target vehicle according to the first license plate information to obtain the second updated vehicle information, and upload the second updated vehicle information to the vehicle cross-camera navigation system.

[0079] In another embodiment, if the target vehicle has not completed cross-camera matching in the current camera, it is determined whether the current camera has recognized the first license plate information of the target vehicle. If the first license plate information is recognized, Figure 5 As shown, perform the following steps:

[0080] Step S131, obtaining the second license plate information within a preset time threshold uploaded by the adjacent camera, and determining whether the first license plate information is consistent with the second license plate information;

[0081] Step S132, if the first license plate information is consistent with the second license plate information, updating the first vehicle information of the target vehicle according to the first license plate information, and marking the target vehicle as a matched vehicle;

[0082] Step S133, if the first license plate information is inconsistent with the second license plate information, obtaining the first real position of the target vehicle in the current camera, and obtaining the second real position of the target vehicle uploaded by the adjacent camera;

[0083] Step S134, calculating the real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than a preset distance threshold is 1;

[0084] Step S135, if the number of vehicles whose actual distance is less than the preset distance threshold is 1, then updating the first vehicle information of the target vehicle according to the second license plate information, and marking the target vehicle as a matched vehicle;

[0085] Step S136: If the number of vehicles whose actual distance is less than the preset distance threshold is not 1, the first vehicle information of the target vehicle is updated according to the first license plate information, and the target vehicle is marked as an unmatched vehicle.

[0086] It can be understood that if the current camera recognizes the first license plate information, it obtains the second license plate information within a preset time threshold (such as 60 seconds) uploaded by the adjacent camera, and then determines whether the first license plate information is consistent with the second license plate information. If the first license plate information is consistent with the second license plate information, the first vehicle information of the target vehicle is updated according to the first license plate information or the second license plate information, and the target vehicle is marked as a matched vehicle, which means that the target vehicle has completed cross-camera matching at this time.

[0087] It can be understood that when the first license plate information is inconsistent with the second license plate information, the first real position of the target vehicle in the current camera is obtained, the second real position of the target vehicle uploaded by the adjacent camera is obtained (the latest vehicle position of the same target vehicle in the last second is taken), the real distance between the first real position and the second real position is calculated, and it is determined whether the number of vehicles whose real distance is less than a preset distance threshold (such as 12 meters) is 1.

[0088] If the number of vehicles whose actual distance is less than the preset distance threshold is 1, it proves that only the target vehicle has passed between the two cameras. At this time, the second license plate information uploaded by the adjacent camera is inherited (the three license plate data with the highest license plate confidence are retained), and the first vehicle information of the target vehicle is updated according to the second license plate information, the target vehicle is marked as a matched vehicle, and the updated fourth updated vehicle information is reported to the adjacent camera and uploaded to the vehicle cross-camera navigation system.

[0089] If the number of vehicles whose actual distance is less than the preset distance threshold is not 1, it proves that not only the target vehicle has passed between the two cameras, but also other vehicles have passed. At this time, only the first vehicle information of the target vehicle needs to be updated according to the first license plate information recognized by the current camera, and the target vehicle is marked as an unmatched vehicle. The updated fifth updated vehicle information is reported to the adjacent camera and uploaded to the vehicle cross-camera navigation system.

[0090] In an optional implementation, after determining whether the current camera recognizes the first license plate information of the target vehicle, if the first license plate information is not recognized, Figure 6 As shown, perform the following steps:

[0091] Step S137, if the first license plate information is not recognized, obtaining the first real position of the target vehicle in the current camera, and obtaining the second real position of the target vehicle uploaded by the adjacent camera;

[0092] Step S138, calculating the real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than a preset distance threshold is 1;

[0093] Step S139, if the number of vehicles whose actual distance is less than the preset distance threshold is 1, the first vehicle information of the target vehicle is updated, the updated third updated vehicle information is uploaded to the vehicle cross-camera navigation system, and the target vehicle is marked as a matched vehicle.

[0094] It can be understood that if the current camera does not recognize the first license plate information of the target vehicle, the first real position of the target vehicle in the current camera is obtained, the second real position of the target vehicle uploaded by the adjacent camera is obtained (the latest vehicle position of the same target vehicle in the last second is taken), the real distance between the first real position and the second real position is calculated, and it is determined whether the number of vehicles whose real distance is less than a preset distance threshold (such as 12 meters) is 1.

[0095] If the number of vehicles whose actual distance is less than the preset distance threshold is 1, it proves that only the target vehicle has passed between the two cameras. At this time, the first vehicle information of the target vehicle is updated, the target vehicle is marked as a matched vehicle, and the updated third updated vehicle information is reported to the adjacent camera and uploaded to the vehicle cross-camera navigation system.

[0096] If the number of vehicles whose actual distance is less than the preset distance threshold is not one, it proves that not only the target vehicle has passed between the two cameras, but also other vehicles have passed. At this time, the first vehicle information of the target vehicle will not be reported to the adjacent camera, nor uploaded to the vehicle cross-camera navigation system.

[0097] Even if the cross-camera matching is unsuccessful in the above method, the first vehicle information is updated by the first license plate information and then uploaded to the vehicle cross-camera navigation system, so that the vehicle cross-camera navigation system can still provide accurate navigation services based on the latest second updated vehicle information, thereby meeting the user's travel needs and improving the user experience.

[0098] The vehicle cross-camera tracking method provided in the embodiment of the present application obtains the first vehicle information and the second vehicle information collected by the current camera and the adjacent camera corresponding to the target vehicle respectively, and determines whether the target vehicle has completed the cross-camera matching in the current camera according to the first vehicle information and the second vehicle information; if the target vehicle has completed the cross-camera matching in the current camera, a matching result is generated, and the first vehicle information of the target vehicle is updated according to the matching result to obtain the first updated vehicle information, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system; if the target vehicle has not completed the cross-camera matching in the current camera, it is determined whether the current camera recognizes the first license plate information of the target vehicle, and if the first license plate information is recognized, the first vehicle information of the target vehicle is updated according to the first license plate information to obtain the second updated vehicle information, and the second updated vehicle information is uploaded to the vehicle cross-camera navigation system. The above method improves the accuracy of vehicle navigation in the parking lot by tracking the vehicle across cameras.

[0099] Example 2

[0100] like Figure 7 FIG. 1 is a flow chart of a vehicle cross-camera navigation method in an embodiment of the present application. The vehicle cross-camera navigation method provided in the embodiment of the present application is applied to a vehicle cross-camera navigation system. The method specifically includes the following steps:

[0101] Step S210: receiving first updated vehicle information or second updated vehicle information uploaded by the vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method of Example 1.

[0102] Step S220, determining whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval.

[0103] It should be noted that after receiving the first updated vehicle information or the second updated vehicle information uploaded by the vehicle cross-camera tracking system, the vehicle cross-camera navigation system needs to determine whether the first updated vehicle information or the second updated vehicle information uploaded by the vehicle cross-camera tracking system is received again within a continuous preset time interval (such as 1 second).

[0104] The above method performs information reception judgment by setting continuous preset time intervals, so that the system can ensure that the latest vehicle information is obtained in a timely manner, thereby greatly improving the real-time performance and accuracy of vehicle navigation.

[0105] Step S230: If the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval, a navigation route is planned according to the most recently received first updated vehicle information or second updated vehicle information.

[0106] If the first updated vehicle information or the second updated vehicle information is updated within the preset time interval, a navigation path is planned according to the vehicle position in the most recently received first updated vehicle information or second updated vehicle information, and the navigation path is uploaded to the user terminal corresponding to the target vehicle.

[0107] The above method updates the vehicle position information in real time and plans the navigation route accordingly, so that the navigation system can immediately provide the user with the latest driving instructions, ensuring that the user always has the latest navigation information. It also reduces the navigation delay caused by information lag, and improves the response speed and overall efficiency of the navigation system.

[0108] Step S240, if the first updated vehicle information or the second updated vehicle information is not received within a continuous preset time interval, the inertial sensor data uploaded by the target vehicle is obtained, the vehicle position and vehicle speed of the target vehicle at the current moment are calculated based on the inertial sensor data, and the navigation path is planned based on the vehicle position and vehicle speed at the current moment.

[0109] It should be noted that, in this embodiment, the vehicle is equipped with inertial sensors including gyroscopes, accelerometers, etc., which can detect the vehicle and output sensor data (such as position, speed and posture).

[0110] If the first updated vehicle information or the second updated vehicle information is not updated within the preset time interval, the sensor data of the target vehicle uploaded by the inertial sensor is obtained, and the vehicle position and vehicle speed of the target vehicle at the current moment are calculated based on the sensor data. Then, a navigation path is planned based on the vehicle position and vehicle speed at the current moment, and the navigation path is uploaded to the user terminal corresponding to the target vehicle.

[0111] In the above method, even if some cameras suddenly malfunction, inertial navigation can still be performed. Inertial navigation does not rely on external signals, so it can continue to provide navigation services when vehicle information is not updated, and can cope with various complex situations.

[0112] In an optional embodiment, if Figure 8 As shown, the vehicle cross-camera navigation method of this embodiment also includes:

[0113] Step S250, determining whether the vehicle speed in the first updated vehicle information or the second updated vehicle information is less than a preset speed threshold;

[0114] Step S260, if the vehicle speed in the first updated vehicle information or the second updated vehicle information is less than the preset speed threshold, obtain Bluetooth beacon data, correct the first updated vehicle information or the second updated vehicle information according to the Bluetooth beacon data to obtain corrected vehicle information, and plan a navigation path according to the corrected vehicle information.

[0115] It should be noted that, in one embodiment, a certain number of Bluetooth beacons are laid in the parking lot where the navigation system is located. The Bluetooth beacons should be evenly distributed in the parking lot to ensure that the signal covers the entire navigation area. Each Bluetooth beacon will periodically (such as every 100 milliseconds) broadcast a data packet containing its unique identification and current signal strength to the surrounding area. When the navigation system enters the signal coverage range of the Bluetooth beacon, it will perform a scanning action and receive Bluetooth beacon data from the Bluetooth beacon at intervals.

[0116] Understandably, a preset speed threshold is first used to determine whether the vehicle speed in the first updated vehicle information or the second updated vehicle information is fast or slow. The Bluetooth beacon data provided by the Bluetooth beacon is calibrated but has a delay. However, for a target vehicle with a slower speed, its position changes relatively slowly, so the delay has little effect on the correction result. The system can use the current signal strength of multiple Bluetooth beacon data uploaded by the Bluetooth beacon, combined with advanced positioning algorithms (such as trilateration, fingerprint positioning, etc.) to calculate the precise position of the target vehicle, and correct the first updated vehicle information or the second updated vehicle information according to the calculated precise position to obtain more accurate corrected vehicle information.

[0117] For target vehicles with faster speeds, the system does not rely on Bluetooth beacons for correction, but directly uses the first updated vehicle information or the second updated vehicle information uploaded by the vehicle cross-camera tracking system to plan the navigation path. This can avoid correction errors caused by Bluetooth beacon delays.

[0118] The above method can continue to connect through Bluetooth beacons after other cameras have abnormalities, achieving cross-camera navigation with higher accuracy, faster speed and stronger robustness, greatly improving the navigation experience of car owners, especially for vehicles with faster speeds.

[0119] The vehicle cross-camera navigation method provided in the embodiment of the present application receives the first updated vehicle information or the second updated vehicle information uploaded by the vehicle cross-camera tracking system; determines whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval; if the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval, then the navigation path is planned according to the latest received first updated vehicle information or second updated vehicle information; if the first updated vehicle information or the second updated vehicle information is not received within a continuous preset time interval, then the inertial sensor data uploaded by the target vehicle is obtained, the vehicle position and vehicle speed of the target vehicle at the current moment are calculated according to the inertial sensor data, and the navigation path is planned according to the vehicle position and vehicle speed at the current moment. The above method can obtain the latest position and status of the target vehicle in real time by receiving the latest vehicle information uploaded by the cross-camera tracking system, thereby ensuring that the planned navigation path is the most accurate and up-to-date, which helps to reduce navigation errors caused by information lag and improve the reliability of navigation.

[0120] Example 3

[0121] like Fig. 9 FIG. 1 is a schematic diagram of a vehicle cross-camera tracking system 900 in an embodiment of the present application, wherein the system includes:

[0122] An acquisition module 910 is used to respectively acquire first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to the target vehicle, and determine whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information;

[0123] A first updating module 920 is used to generate a matching result if the target vehicle completes cross-camera matching in the current camera, and to update the first vehicle information of the target vehicle according to the matching result to obtain first updated vehicle information, and to upload the first updated vehicle information to the vehicle cross-camera navigation system;

[0124] The second update module 930 is used to determine whether the current camera recognizes the first license plate information of the target vehicle if the target vehicle has not completed cross-camera matching in the current camera. If the first license plate information is recognized, the first vehicle information of the target vehicle is updated according to the first license plate information to obtain the second updated vehicle information, and the second updated vehicle information is uploaded to the vehicle cross-camera navigation system.

[0125] The vehicle cross-camera tracking system provided in the embodiment of the present application improves the accuracy of vehicle navigation in a parking lot by tracking the vehicle across cameras.

[0126] Example 4

[0127] like Fig.10 FIG. 1 is a schematic diagram of the structure of a vehicle cross-camera navigation system 1000 in an embodiment of the present application, wherein the system includes:

[0128] A receiving module 1010 is used to receive first updated vehicle information or second updated vehicle information uploaded by the vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method of embodiment 1;

[0129] The determination module 1020 is used to determine whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval;

[0130] A first planning module 1030 is configured to plan a navigation path according to the most recently received first updated vehicle information or second updated vehicle information if the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval;

[0131] The second planning module 1040 is used to obtain the inertial sensor data uploaded by the target vehicle if the first updated vehicle information or the second updated vehicle information is not received within a continuous preset time interval, calculate the vehicle position and vehicle speed of the target vehicle at the current moment according to the inertial sensor data, and plan a navigation path according to the vehicle position and vehicle speed at the current moment.

[0132] The vehicle cross-camera navigation system provided in the embodiment of the present application can obtain the latest position and status of the target vehicle in real time by receiving the latest vehicle information uploaded by the cross-camera tracking system, thereby ensuring that the planned navigation path is the most accurate and up-to-date, helping to reduce navigation errors caused by information lag and improving navigation reliability.

[0133] Example 5

[0134] The present application also provides a computer device. Fig.11 , Fig.11 This is a basic structural block diagram of the computer device in this embodiment.

[0135] The computer device 11 includes a memory 111 and a processor 112 which are connected to each other through a system bus. It should be noted that the figure only shows a computer device 11 having a memory 111 and a processor 112, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0136] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0137] The memory 111 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D slot compatibility test memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 111 can be an internal storage unit of the computer device 11, such as a hard disk or memory of the computer device 11. In other embodiments, the memory 111 can also be an external storage device of the computer device 11, such as a plug-in hard disk equipped on the computer device 11, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 111 can also include both the internal storage unit of the computer device 11 and its external storage device. In this embodiment, the memory 111 is generally used to store the operating system and various application software installed on the computer device 11, such as computer-readable instructions of the slot compatibility test method, etc. In addition, the memory 111 can also be used to temporarily store various types of data that have been output or are to be output.

[0138] The processor 112 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other vehicle cross-camera tracking navigation chip in some embodiments. The processor 112 is generally used to control the overall operation of the computer device 11. In this embodiment, the processor 112 is used to run computer-readable instructions stored in the memory 111 or process data, such as computer-readable instructions for running a slot compatibility test method.

[0139] The computer device provided in this embodiment can execute the above-mentioned vehicle cross-camera tracking method and vehicle cross-camera navigation method. Here, the vehicle cross-camera tracking and navigation method and vehicle cross-camera navigation method can be the vehicle cross-camera tracking method and vehicle cross-camera navigation method of each of the above-mentioned embodiments.

[0140] Example 6

[0141] The present embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the vehicle cross-camera navigation method and the steps of the vehicle cross-camera navigation method in the embodiment are implemented.

[0142] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, referred to as SMC), a secure digital (Secure Digital, referred to as SD) card, a flash card, etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0143] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0144] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0145] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or partly contributed to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0146] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A vehicle cross-camera tracking method, characterized in that: Applied to a vehicle cross-camera tracking system, the method comprises: Respectively obtain first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to the target vehicle, and determine whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information; If the target vehicle completes cross-camera matching in the current camera, a matching result is generated, and first vehicle information of the target vehicle is updated according to the matching result to obtain first updated vehicle information, and the first updated vehicle information is uploaded to the vehicle cross-camera navigation system; If the target vehicle has not completed cross-camera matching in the current camera, it is determined whether the current camera recognizes the first license plate information of the target vehicle. If the first license plate information is recognized, the first vehicle information of the target vehicle is updated according to the first license plate information to obtain second updated vehicle information, and the second updated vehicle information is uploaded to the vehicle cross-camera navigation system.

2. The vehicle cross-camera tracking method according to claim 1, characterized in that: The first vehicle information and the second vehicle information both include vehicle positions, and judging whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information includes: Acquire a first high-precision map and first calibration information within the field of view of the current camera, and acquire a second high-precision map and second calibration information within the field of view of the adjacent camera; Converting the vehicle position in the first vehicle information into a first real physical coordinate by using the first high-precision map and the first calibration information, and converting the vehicle position in the second vehicle information into a second real physical coordinate by using the second high-precision map and the second calibration information; Comparing the first real physical coordinate with the second real physical coordinate to obtain a similarity, and determining whether the similarity is greater than a preset similarity threshold; If the similarity is greater than the preset similarity threshold, it is determined that the target vehicle has completed cross-camera matching in the current camera; if the similarity is less than or equal to the preset similarity threshold, it is determined that the target vehicle has not completed cross-camera matching in the current camera.

3. The vehicle cross-camera tracking method according to claim 1, characterized in that: The updating of the first vehicle information of the target vehicle according to the first license plate information includes: Acquire the second license plate information within a preset time threshold uploaded by the adjacent camera, and determine whether the first license plate information is consistent with the second license plate information; If the first license plate information is consistent with the second license plate information, updating the first vehicle information of the target vehicle according to the first license plate information, and marking the target vehicle as a matched vehicle; If the first license plate information is inconsistent with the second license plate information, obtaining the first real position of the target vehicle in the current camera, and obtaining the second real position of the target vehicle uploaded by the adjacent camera; Calculating a real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than a preset distance threshold is 1; If the number of vehicles whose actual distance is less than the preset distance threshold is 1, updating the first vehicle information of the target vehicle according to the second license plate information, and marking the target vehicle as a matched vehicle; If the number of vehicles whose actual distance is less than the preset distance threshold is not 1, the first vehicle information of the target vehicle is updated according to the first license plate information, and the target vehicle is marked as an unmatched vehicle.

4. The vehicle cross-camera tracking method according to claim 3, characterized in that: After determining whether the current camera recognizes the first license plate information of the target vehicle, the method further includes: If the first license plate information is not recognized, obtaining a first real position of the target vehicle in the current camera, and obtaining a second real position of the target vehicle uploaded by the adjacent camera; Calculating a real distance between the first real position and the second real position, and determining whether the number of vehicles whose real distance is less than the preset distance threshold is 1; If the number of vehicles whose actual distance is less than the preset distance threshold is 1, the first vehicle information of the target vehicle is updated, the updated third updated vehicle information is uploaded to the vehicle cross-camera navigation system, and the target vehicle is marked as a matched vehicle.

5. A vehicle cross-camera navigation method, characterized in that: Applied to a vehicle cross-camera navigation system, the method comprises: Receiving first updated vehicle information or second updated vehicle information uploaded by a vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method according to any one of claims 1 to 4; determining whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval; If the first updated vehicle information or the second updated vehicle information is received within the continuous preset time interval, planning a navigation route according to the most recently received first updated vehicle information or second updated vehicle information; If the first updated vehicle information or the second updated vehicle information is not received within the continuous preset time interval, the inertial sensor data uploaded by the target vehicle is obtained, the vehicle position and vehicle speed of the target vehicle at the current moment are calculated according to the inertial sensor data, and the navigation path is planned according to the vehicle position and vehicle speed at the current moment.

6. The vehicle cross-camera navigation method according to claim 5, characterized in that: The method further comprises: Determining whether a vehicle speed in the first updated vehicle information or the second updated vehicle information is less than a preset speed threshold; If the vehicle speed in the first updated vehicle information or the second updated vehicle information is less than the preset speed threshold, Bluetooth beacon data is obtained, the first updated vehicle information or the second updated vehicle information is corrected according to the Bluetooth beacon data to obtain corrected vehicle information, and the navigation path is planned according to the corrected vehicle information.

7. A vehicle cross-camera tracking system, characterized in that: The system comprises: An acquisition module, used to respectively acquire first vehicle information and second vehicle information collected by a current camera and an adjacent camera corresponding to a target vehicle, and determine whether the target vehicle has completed cross-camera matching in the current camera according to the first vehicle information and the second vehicle information; A first updating module, configured to generate a matching result if the target vehicle completes cross-camera matching in the current camera, and update first vehicle information of the target vehicle according to the matching result to obtain first updated vehicle information, and upload the first updated vehicle information to the vehicle cross-camera navigation system; The second updating module is used to determine whether the current camera recognizes the first license plate information of the target vehicle if the target vehicle has not completed cross-camera matching in the current camera; if the first license plate information is recognized, update the first vehicle information of the target vehicle according to the first license plate information to obtain second updated vehicle information, and upload the second updated vehicle information to the vehicle cross-camera navigation system.

8. A vehicle cross-camera navigation system, characterized in that: The system comprises: A receiving module, configured to receive first updated vehicle information or second updated vehicle information uploaded by a vehicle cross-camera tracking system, wherein the first updated vehicle information and the second updated vehicle information are determined by the vehicle cross-camera tracking method according to any one of claims 1 to 4; A determination module, configured to determine whether the first updated vehicle information or the second updated vehicle information is received within a continuous preset time interval; A first planning module, configured to plan a navigation path according to the most recently received first updated vehicle information or second updated vehicle information if the first updated vehicle information or the second updated vehicle information is received within the continuous preset time interval; The second planning module is used to obtain the inertial sensor data uploaded by the target vehicle if the first updated vehicle information or the second updated vehicle information is not received within the continuous preset time interval, calculate the vehicle position and vehicle speed of the target vehicle at the current moment according to the inertial sensor data, and plan the navigation path according to the vehicle position and vehicle speed at the current moment.

9. A computer device, characterized in that: include: Memory, used to store programs; A processor, configured to implement the vehicle cross-camera tracking method according to any one of claims 1 to 4 or the vehicle cross-camera navigation method according to claim 5 or 6 by executing the program stored in the memory.

10. A computer-readable storage medium, characterized in that: The invention comprises a program which can be executed by a processor to implement the vehicle cross-camera tracking method according to any one of claims 1 to 4 or the vehicle cross-camera navigation method according to claim 5 or 6.

Images