A vehicle tracking method and system based on multi-camera cooperation

Abstract

The application provides a vehicle tracking method and system based on multi-camera cooperation. The application utilizes the cooperation among cameras, identifies feature points such as the time, geographic coordinates, vehicle features and motion direction of vehicles passing through different cameras, automatically generates the vehicle trajectory among the cameras, and draws it on a map to form a vehicle tracking system based on camera cooperation.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent security ports, and in particular to a vehicle tracking method and system based on multi-camera collaboration. Background Art

[0002] Container ports face numerous challenges in traffic management due to the frequent traffic. Especially within the port area, due to the high volume of vehicles, high speeds, and complex traffic conditions, vehicles often violate traffic regulations and drive in violation of traffic rules, which places enormous pressure on traffic management and poses safety risks.

[0003] Traditional traffic monitoring systems typically use cameras installed on roads to monitor and record traffic conditions. However, due to the limited placement and field of view of the cameras, they often fail to fully cover all traffic sections within the port area, resulting in blind spots in some areas and the risk of missing important traffic violations. After an accident, managers often need to manually query footage from multiple cameras to identify the vehicle's trajectory, then piece together and analyze the footage to determine the cause and responsibility. This approach is not only inefficient but also prone to information omissions and misjudgments, making it difficult to respond to traffic incidents in a timely and effective manner.

[0004] Therefore, there is an urgent need for an intelligent traffic monitoring system that can monitor and track the driving conditions of vehicles in the port in real time and automatically generate vehicle driving trajectories to facilitate management personnel to fully understand the traffic conditions in the port area, promptly discover and deal with traffic violations, and improve traffic safety and management efficiency. Summary of the Invention

[0005] In order to at least solve the technical problems existing in the above-mentioned background technology, the present invention provides a vehicle tracking method, system, electronic device, storage medium and computer program product based on multi-camera collaboration.

[0006] The present invention provides a vehicle tracking method based on multi-camera collaboration, comprising the following steps:

[0007] installing a plurality of PTZ cameras at different locations inside the container port, the PTZ cameras including a first PTZ camera and a second PTZ camera;

[0008] The first PTZ camera identifies a target vehicle based on a first surveillance image captured in real time, and actively tracks the target vehicle;

[0009] During active tracking, the first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, adjusts the tracking posture of the first PTZ camera according to the estimation result, and determines the second PTZ camera to be followed according to the estimation result;

[0010] The second PTZ camera identifies the target vehicle based on the third monitoring image captured in real time, and continues to actively track the target vehicle;

[0011] The first PTZ camera and the second PTZ camera upload their respective active tracking record information to a server, and the server is configured to generate a trajectory of the target vehicle according to the active tracking record information and display the trajectory on a map.

[0012] Optionally, the first PTZ camera identifies a target vehicle based on the first surveillance image captured in real time, and actively tracks the target vehicle, including:

[0013] The first PTZ camera searches and locates the target vehicle in the first surveillance image after foreground detection and segmentation based on the first vehicle target feature. After finding the target vehicle, the first PTZ camera enters an active tracking state for the target vehicle and extracts a second vehicle target feature of the target vehicle.

[0014] The first PTZ camera also learns the features of the target vehicle during the active tracking process, and feeds back the feature learning results for use in updating the target features of the second vehicle.

[0015] Optionally, the first vehicle target feature is determined by:

[0016] The user inputs the first vehicle target feature through the interactive device, or directly selects the target vehicle on the interactive device, and the first vehicle target feature is extracted from the image of the target vehicle.

[0017] Optionally, the second PTZ camera further receives the first vehicle target feature or the second vehicle target feature sent by the server or the first PTZ camera.

[0018] Optionally, the first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, and determines the second PTZ camera to be connected according to the estimation result, including:

[0019] The first PTZ camera extracts the background of the target vehicle from a plurality of second surveillance images captured in real time to obtain background features, and compares the background features with a plurality of associated template background features. If the comparison is successful, it is determined that the vehicle has reached the limit area of ​​the field of view of the first PTZ camera; wherein the template background features are background features extracted from surveillance images captured corresponding to the postures of the first PTZ camera when the camera is located at each limit area of ​​the field of view;

[0020] The second PTZ camera to be connected is determined based on the position information corresponding to the successfully matched template background feature and the moving direction of the target vehicle.

[0021] Optionally, the second PTZ camera receives the vehicle target feature, including:

[0022] The first PTZ camera analyzes the number of other vehicles in the second surveillance image that are moving in the same direction as the target vehicle, and determines, based on the number, a timing for sending a connection request instruction, wherein the connection request instruction is used to trigger the second PTZ camera to change to a posture corresponding to a field of view limit area of ​​the first PTZ camera;

[0023] The larger the number is, the closer the sending timing is to the moment when the first PTZ camera reaches the limit area of ​​its visual field, and vice versa.

[0024] The present invention also provides a vehicle tracking system based on multi-camera collaboration, comprising a plurality of PTZ cameras installed at different locations inside a container port, a processing module, and a storage module, wherein the processing module is connected to each of the PTZ cameras and the storage module respectively; wherein,

[0025] The storage module is used to store executable computer program code;

[0026] The PTZ camera is used to capture a surveillance image containing a target vehicle and transmit the image to the processing module;

[0027] The processing module is configured to execute the method as described in any of the preceding items by calling the executable computer program code in the storage module.

[0028] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute any of the methods described above.

[0029] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0030] The present invention also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program implements any of the above methods when executed by a processor.

[0031] The present invention utilizes the collaboration between cameras. By identifying characteristic points such as the time, geographic coordinates, vehicle characteristics and running direction when a vehicle passes through different cameras, it automatically generates vehicle trajectories between cameras and plots them on a map, forming a camera-coordinated vehicle tracking system. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] 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 therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 This is a schematic diagram of a vehicle tracking method based on multi-camera collaboration disclosed in an embodiment of the present invention.

[0034] Figure 2 This is a flow chart of a vehicle tracking method based on multi-camera collaboration disclosed in an embodiment of the present invention.

[0035] Figure 3 This is a structural diagram of a vehicle tracking system based on multi-camera collaboration disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0037] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0038] In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the invention is usually placed when in use. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the system or component referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0039] The terms "first," "second," "third," and "fourth" in the specification and claims of the present invention are used to distinguish different objects rather than to describe a specific order of objects. For example, the terms "first input," "second input," "third input," and "fourth input" are used to distinguish different inputs rather than to describe a specific order of inputs.

[0040] In the embodiments of the present invention, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0041] In the description of the embodiments of the present invention, unless otherwise specified, “multiple” means two or more than two. For example, multiple processing units means two or more processing units; multiple elements means two or more elements, etc.

[0042] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0043] In response to the technical problems mentioned in the background technology, the present invention installs multiple PTZ cameras at different locations inside the container port. These cameras can seamlessly exchange data and share information, so that through the cooperation between multiple cameras, the traffic conditions in the monitored port area can be jointly monitored.

[0044] like Figure 1 As shown, a vehicle tracking method based on multi-camera collaboration according to an embodiment of the present invention includes the following steps:

[0045] installing a plurality of PTZ cameras at different locations inside the container port, the PTZ cameras including a first PTZ camera and a second PTZ camera;

[0046] The first PTZ camera identifies a target vehicle based on a first surveillance image captured in real time, and actively tracks the target vehicle;

[0047] During active tracking, the first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, adjusts the tracking posture of the first PTZ camera according to the estimation result, and determines the second PTZ camera to be followed according to the estimation result;

[0048] The second PTZ camera identifies the target vehicle based on the third monitoring image captured in real time, and continues to actively track the target vehicle;

[0049] The first PTZ camera and the second PTZ camera upload their respective active tracking record information to a server, and the server is configured to generate a trajectory of the target vehicle according to the active tracking record information and display the trajectory on a map.

[0050] In an embodiment of the present invention, multiple PTZ cameras are installed at different locations within a container port. These PTZ cameras include a first PTZ camera and a second PTZ camera. The first and second PTZ cameras are used solely to distinguish the order in which a target vehicle is identified, and are not intended to be limiting. The first PTZ camera initially identifies a target vehicle based on a first surveillance image captured in real time and actively tracks it. During the tracking process, it further performs background estimation on the target vehicle. This estimation result is used to adjust the first PTZ camera's tracking posture, continuously adjusting its posture angle to ensure the target vehicle remains within its field of view. Furthermore, this estimation result is used to determine whether the target vehicle's current position has reached the limit of its field of view. If so, a target handover between cameras is required. The second PTZ camera then continues tracking in the same manner. During the tracking process, each PTZ camera involved in tracking the target vehicle uploads its active tracking record information to a server, which generates the target vehicle's trajectory and displays it on a map. This allows management personnel to intuitively visualize the vehicle's travel path and trajectory, quickly understanding traffic conditions within the port area.

[0051] For identified target vehicles, each PTZ camera records the active tracking information detected, primarily including the subsequent secondary vehicle target features. Based on this information, the server applies a trajectory generation algorithm to automatically calculate the vehicle's trajectory within the port. These trajectories include the vehicle's movement path and driving trajectory within the monitoring range of different cameras. The generated vehicle trajectory data is also transmitted to the map display interface and presented graphically on the map. This allows managers to intuitively view the vehicle's driving path and trajectory, quickly understanding traffic conditions within the port area. Through the map interface, managers can select specific time periods, vehicles, or areas for viewing and analysis, facilitating real-time monitoring and management.

[0052] In addition, if the server determines that the target vehicle is beyond the monitoring range of the entire system, it will give the user a prompt to end automatic tracking.

[0053] Optionally, the first PTZ camera identifies a target vehicle based on the first surveillance image captured in real time, and actively tracks the target vehicle, including:

[0054] The first PTZ camera searches and locates the target vehicle in the first surveillance image after foreground detection and segmentation based on the first vehicle target feature. After finding the target vehicle, the first PTZ camera enters an active tracking state for the target vehicle and extracts a second vehicle target feature of the target vehicle.

[0055] The first PTZ camera also learns the features of the target vehicle during the active tracking process, and feeds back the feature learning results for use in updating the target features of the second vehicle.

[0056] In an embodiment of the present invention, the first PTZ camera can receive first vehicle target features, such as license plate numbers, vehicle appearance features, etc., and perform foreground segmentation in the first surveillance image based on these vehicle target features, thereby realizing search and positioning of the target vehicle and continuously and actively tracking it.

[0057] At the same time, some features of the target vehicle may change during its motion. For example, the color, texture, and pattern on different sides of the vehicle may be different. After the vehicle turns around, the vehicle target features identified by the first PTZ camera will change significantly. If the original vehicle target features are still used for tracking, it is easy to lose the target vehicle. To address this issue, the present invention configures the first PTZ camera to learn the target vehicle's features during active tracking. That is, when the target vehicle's features change, it identifies and maintains a lock on the target vehicle based on the previous tracking points, and simultaneously updates the target vehicle's target features to the new second vehicle target features after the changes. In this way, continuous active tracking of the target vehicle can be achieved based on the new second vehicle target features.

[0058] Optionally, the first vehicle target feature is determined by:

[0059] The user inputs the first vehicle target feature through the interactive device, or directly selects the target vehicle on the interactive device, and the first vehicle target feature is extracted from the image of the target vehicle.

[0060] In an embodiment of the present invention, the solution of the present invention also includes an interactive device, which is equipped with a mouse, a keyboard, a display, etc. The user can directly input the first vehicle target feature through the interactive device, such as inputting the license plate number, vehicle appearance features, etc. of the target vehicle to be monitored through the keyboard; the user can also use the mouse on the interactive device or select the vehicle on the touch screen to select the target vehicle, and then the image recognition software extracts the first vehicle target feature from the image of the target vehicle.

[0061] Optionally, the second PTZ camera further receives the first vehicle target feature or the second vehicle target feature sent by the server or the first PTZ camera.

[0062] In an embodiment of the present invention, each PTZ camera is interconnected with the server and with each other. Therefore, when a first PTZ camera identifies a target vehicle, it can transmit the target vehicle's second target feature to the server, which then forwards it to a second PTZ camera for follow-up tracking. Alternatively, the first PTZ camera can directly transmit the target vehicle's second target feature to the second PTZ camera for follow-up tracking. In this way, the second PTZ camera obtains the second target feature, allowing it to identify the target vehicle within its own field of view and actively track it.

[0063] Among them, the second vehicle target feature can include the license plate number, vehicle appearance features, etc. in the first vehicle target feature. In addition, it also includes the time, geographic coordinates and other key features (such as the updated first vehicle target feature) when the target vehicle passes through each camera, the direction of movement, and even the number of other vehicles in the subsequent surveillance images with the same direction of movement as the target vehicle.

[0064] Optionally, the first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, and determines the second PTZ camera to be connected according to the estimation result, including:

[0065] The first PTZ camera extracts the background of the target vehicle from a plurality of second surveillance images captured in real time to obtain background features, and compares the background features with a plurality of associated template background features. If the comparison is successful, it is determined that the vehicle has reached the limit area of ​​the field of view of the first PTZ camera; wherein the template background features are background features extracted from surveillance images captured corresponding to the postures of the first PTZ camera when the camera is located at each limit area of ​​the field of view;

[0066] The second PTZ camera to be connected is determined based on the position information corresponding to the successfully matched template background feature and the moving direction of the target vehicle.

[0067] In an embodiment of the present invention, when the first PTZ camera is about to reach the limit of its field of view, it can no longer track the target vehicle by changing its camera posture. It is necessary to initiate a search for the second PTZ camera to continue tracking the target vehicle. Existing methods use the detection angle of the PTZ camera's posture angle sensor to determine whether it has reached the attitude angle limit. If so, it is determined that the PTZ camera is about to reach the field of view limit. However, PTZ cameras are susceptible to vibration, human or accidental damage, and other factors that may cause their posture to change. If this judgment is still based on the detection angle of the posture angle sensor, it is obviously easy to misjudge.

[0068] To address this issue, the present invention pre-controls each PTZ camera to assume a posture at the extremes of its field of view, captures surveillance images in this posture, and extracts background features from these postures as template background features. Thus, while the PTZ camera is actively tracking a target vehicle, it extracts background features from the target vehicle's area using the captured secondary surveillance images. A determination is made as to whether these features correspond to one of multiple preset template background features. If so, the target vehicle reaches the extremes of its field of view. Because each template background feature corresponds to positional information, which is the actual positional information (calculated from the PTZ camera's position) corresponding to the aforementioned surveillance images (images captured by the PTZ camera in the extremes of its field of view), the optimal secondary PTZ camera for continued tracking can be determined based on this positional information and the target vehicle's direction of motion.

[0069] Optionally, the second PTZ camera receives the vehicle target feature, including:

[0070] The first PTZ camera analyzes the number of other vehicles in the second surveillance image that are moving in the same direction as the target vehicle, and determines, based on the number, a timing for sending a connection request instruction, wherein the connection request instruction is used to trigger the second PTZ camera to change to a posture corresponding to a field of view limit area of ​​the first PTZ camera;

[0071] The larger the number is, the closer the sending timing is to the moment when the first PTZ camera reaches the limit area of ​​its visual field, and vice versa.

[0072] In this embodiment of the present invention, the second PTZ camera must first identify the target vehicle before actively tracking it. However, identifying the target vehicle requires considering the accuracy of the predicted location of the target vehicle's first appearance and the number of other vehicles present at the same time. Specifically, the greater the number of other vehicles present at the same time, the longer it takes for the second PTZ camera to accurately identify the target vehicle. Accordingly, the first PTZ camera must send a follow-up request containing vehicle target features (in addition to the aforementioned license plate number and vehicle appearance features, this should also include at least the location and direction of movement of the template vehicle) sooner after determining that the first PTZ camera has reached the limit of its field of view, thereby preparing for identification and tracking.

[0073] like Figure 2 As shown, the present invention also discloses a vehicle tracking system based on multi-camera collaboration, comprising a plurality of PTZ cameras installed at different locations inside a container port, a processing module, and a storage module, wherein the processing module is connected to each of the PTZ cameras and the storage module respectively; wherein,

[0074] The storage module is used to store executable computer program code;

[0075] The PTZ camera is used to capture a surveillance image containing a target vehicle and transmit the image to the processing module;

[0076] The processing module is configured to execute the method as described in any of the preceding items by calling the executable computer program code in the storage module.

[0077] The present invention also discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0078] The present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is run by a processor, any of the above methods is executed.

[0079] The present invention further discloses a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program implements any of the above methods when executed by a processor.

[0080] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can 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.

[0081] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0082] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] 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).

[0084] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer having 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 back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0085] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0086] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0087] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A vehicle tracking method based on multi-camera collaboration, characterized by: The steps include: installing a plurality of PTZ cameras at different locations inside the container port, the PTZ cameras including a first PTZ camera and a second PTZ camera; The first PTZ camera identifies a target vehicle based on a first surveillance image captured in real time, and actively tracks the target vehicle; During active tracking, the first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, adjusts the tracking posture of the first PTZ camera according to the estimation result, and determines the second PTZ camera to be followed according to the estimation result; The second PTZ camera identifies the target vehicle based on the third monitoring image captured in real time, and continues to actively track the target vehicle; The first PTZ camera and the second PTZ camera upload their respective active tracking record information to a server, and the server is configured to generate a trajectory of the target vehicle based on the active tracking record information and display it on a map; The first PTZ camera estimates the background of the target vehicle based on a plurality of second surveillance images captured in real time, and determines a second PTZ camera to be connected according to the estimation result, including: The first PTZ camera extracts the background of the target vehicle from a plurality of second surveillance images captured in real time to obtain background features, and compares the background features with a plurality of associated template background features. If the comparison is successful, it is determined that the vehicle has reached the limit area of ​​the field of view of the first PTZ camera; wherein the template background features are background features extracted from surveillance images captured corresponding to the postures of the first PTZ camera when the camera is located at each limit area of ​​the field of view; The second PTZ camera to be connected is determined based on the position information corresponding to the successfully matched template background feature and the moving direction of the target vehicle.

2. The vehicle tracking method based on multi-camera collaboration according to claim 1, characterized in that: The first PTZ camera identifies a target vehicle based on a first surveillance image captured in real time, and actively tracks the target vehicle, including: The first PTZ camera searches and locates the target vehicle in the first surveillance image after foreground detection and segmentation based on the first vehicle target feature. After finding the target vehicle, the first PTZ camera enters an active tracking state for the target vehicle and extracts a second vehicle target feature of the target vehicle. The first PTZ camera also learns the features of the target vehicle during the active tracking process, and feeds back the feature learning results for use in updating the target features of the second vehicle.

3. The vehicle tracking method based on multi-camera collaboration according to claim 2, characterized in that: The first vehicle target feature is determined by: The user inputs the first vehicle target feature through the interactive device, or directly selects the target vehicle on the interactive device, and the first vehicle target feature is extracted from the image of the target vehicle.

4. The vehicle tracking method based on multi-camera collaboration according to claim 3, characterized in that: The second PTZ camera further receives the first vehicle target feature or the second vehicle target feature sent by the server or the first PTZ camera.

5. The vehicle tracking method based on multi-camera collaboration according to claim 1, characterized in that: The second PTZ camera receives the vehicle target feature, including: The first PTZ camera analyzes the number of other vehicles in the second surveillance image that are moving in the same direction as the target vehicle, and determines, based on the number, a timing for sending a connection request instruction, wherein the connection request instruction is used to trigger the second PTZ camera to change to a posture corresponding to a field of view limit area of ​​the first PTZ camera; The larger the number is, the closer the sending timing is to the moment when the first PTZ camera reaches the limit area of ​​its visual field, and vice versa.

6. A vehicle tracking system based on multi-camera collaboration, comprising a plurality of PTZ cameras installed at different locations within a container port, a processing module, and a storage module, wherein the processing module is connected to each of the PTZ cameras and the storage module; wherein: The storage module is used to store executable computer program code; The PTZ camera is used to capture a surveillance image containing a target vehicle and transmit the image to the processing module; It is characterized in that: the processing module is used to execute the method according to any one of claims 1 to 5 by calling the executable computer program code in the storage module.

7. An electronic device comprising: a memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-5.

8. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

9. A computer program product comprising a computer program stored on a non-transitory computer-readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images