Target area vehicle tracking method, device, computer equipment and storage medium

Abstract

The present application relates to the field of video processing, and in particular to a method, device, computer equipment and storage medium for tracking vehicles in a target area, the method comprising: obtaining first tracking information of a first target vehicle in a target area contained in a video to be processed, and determining the residence time of the first target vehicle in the target area based on the first tracking information; when the first tracking information is lost in the target area, and second tracking information of a second target vehicle is obtained in the target area contained in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle; if it is determined that the first target vehicle and the second target vehicle are the same target vehicle, updating the residence time of the first target vehicle in the target area based on the second tracking information. The present invention can more accurately obtain the residence time of the target vehicle in the target area.

Description

Technical Field

[0001] The present application relates to the field of video processing, and in particular to a method, device, computer equipment and storage medium for tracking vehicles in a target area. Background Art

[0002] In the prior art, a target vehicle in a target area is tracked and detected through video surveillance, for example, a target vehicle in a target fire passage is tracked and detected to obtain the residence time of the target vehicle in the target fire passage. In the process of tracking and detecting the target vehicle, the tracking of the target vehicle may be lost due to occlusion. When the target vehicle is detected again, it is regarded as a different target vehicle from the last detected target vehicle, which may lead to inaccurate judgment of the residence time of the target vehicle in the target area. Summary of the invention

[0003] Based on this, it is necessary to provide a target area vehicle tracking method, device, computer equipment and storage medium to address the above technical problems.

[0004] In a first aspect, an embodiment of the present invention provides a target area vehicle tracking method, the method comprising:

[0005] Acquire first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information;

[0006] When the first tracking information is lost in the target area, and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle;

[0007] If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information.

[0008] In one embodiment, the target area is an area of ​​a preset vehicle passage containing a preset type of vehicle, and the first target vehicle and the second target vehicle are vehicles other than the preset type of vehicle; the method further comprises:

[0009] Based on the magnitude relationship between the updated dwell time and the preset time threshold, the traffic status of the preset vehicle channel is determined.

[0010] In one embodiment, the preset vehicle type includes a fire truck, and the preset vehicle passage includes a fire passage.

[0011] In one embodiment, determining whether the first target vehicle and the second target vehicle are the same target vehicle comprises:

[0012] Based on the video to be processed, extracting features of the first target vehicle to obtain first feature information;

[0013] Based on the video to be processed, extracting the features of the second target vehicle to obtain second feature information;

[0014] Based on the matching relationship between the first feature information and the second feature information, it is determined whether the first target vehicle and the second target vehicle are the same target vehicle.

[0015] In one embodiment, extracting the feature of the first target vehicle based on the video to be processed to obtain the first feature information includes:

[0016] Performing frame processing on the video to be processed to obtain video frames;

[0017] Selecting a to-be-processed video frame containing the first target vehicle from each video frame;

[0018] Selecting a video frame to be extracted based on a comparison result between the acquired image parameters of the video frame to be processed and a preset parameter threshold;

[0019] Based on the extracted features of the first target vehicle in the video frame to be extracted, first feature information is obtained using a multi-frame voting method.

[0020] In one embodiment, determining the traffic state of the preset vehicle channel based on the relationship between the updated dwell time and the preset time threshold includes:

[0021] If the updated stay time is greater than the preset time threshold, the traffic status of the preset vehicle channel is determined to be a vehicle illegally parked state.

[0022] In one embodiment, it further includes:

[0023] If the preset vehicle channel is in an illegally parked state, an alarm is issued based on the first feature information extracted from the first target vehicle and the stay time.

[0024] In one embodiment, before obtaining the first tracking information of the first target vehicle in the target area included in the video to be processed, the method further includes:

[0025] Performing frame processing on the video to be processed to obtain video frames;

[0026] Determine the segmentation target in each video frame based on the constructed channel scene semantic segmentation model;

[0027] Based on the segmented target, a target area in each video frame is determined.

[0028] In a second aspect, an embodiment of the present invention provides a target area vehicle tracking device, the device comprising:

[0029] A first determination module is used to obtain first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information;

[0030] A second determination module, configured to determine whether the first target vehicle and the second target vehicle are the same target vehicle when the first tracking information is lost in the target area and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed;

[0031] The third determination module is configured to update the residence time of the first target vehicle in the target area based on the second tracking information if it is determined that the first target vehicle and the second target vehicle are the same target vehicle.

[0032] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquire first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information;

[0034] When the first tracking information is lost in the target area, and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle;

[0035] If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the processor executes the computer program, the following steps are implemented:

[0037] Acquire first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information;

[0038] When the first tracking information is lost in the target area, and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle;

[0039] If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information.

[0040] The above method, apparatus, computer equipment and storage medium obtain the first tracking information of the first target vehicle in the target area included in the video to be processed, and determine the residence time of the first target vehicle in the target area based on the first tracking information; when the first tracking information is lost in the target area, and the second tracking information of the second target vehicle is obtained in the target area included in the video to be processed, determine whether the first target vehicle and the second target vehicle are the same target vehicle; if it is determined that the first target vehicle and the second target vehicle are the same target vehicle, update the residence time of the first target vehicle in the target area based on the second tracking information. The present invention aims at the situation where the first tracking information is lost in the target area. When the second tracking information of the second target vehicle is re-acquired, the residence time is determined by judging whether the first target vehicle and the second target vehicle are the same target vehicle, so that the residence time of the target vehicle in the target area can be obtained more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A diagram showing an application environment of a target area vehicle tracking method in an embodiment;

[0042] Figure 2 A schematic diagram of a flow chart of a target area vehicle tracking method in one embodiment;

[0043] Figure 3 A schematic diagram of a flow chart of a method for determining a target vehicle in one embodiment;

[0044] Figure 4 is a schematic flow chart of a first feature information extraction method in an embodiment;

[0045] Figure 5 is a schematic flow chart of a method for determining a target area in one embodiment;

[0046] Figure 6 A schematic diagram of the overall process of a target area vehicle tracking method in one embodiment;

[0047] Figure 7 A schematic diagram of the structure of a target area vehicle tracking device in one embodiment;

[0048] Figure 8 The figure is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The target area vehicle tracking method provided by this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The terminal 102 first obtains the first tracking information of the first target vehicle in the target area included in the video to be processed, and determines the residence time of the first target vehicle in the target area based on the first tracking information. When the first tracking information is lost in the target area, and the second tracking information of the second target vehicle is obtained in the target area included in the video to be processed, it is determined whether the first target vehicle and the second target vehicle are the same target vehicle. If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information, and the terminal 102 sends the residence time to the server 104. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0051] In one embodiment, if Figure 2 As shown, a target area vehicle tracking method is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0052] S202: Acquire first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information.

[0053] The video to be processed is acquired through a monitoring device in the target area, and the monitoring device monitors the entire target area.

[0054] In this embodiment, the video to be processed is processed into frames to obtain each video frame, and then the vehicle recognition model is used to identify the first target vehicle in the target area of ​​the video to be processed, and then the target detection frame is used to follow the first target vehicle. The first tracking information includes information such as the detection frame of the first target vehicle.

[0055] The first video frame in which the first target vehicle appears can be determined according to the first tracking information. Each video frame has a corresponding time, so the residence time of the first target vehicle in the target area can be obtained according to the first tracking information.

[0056] S204: When the first tracking information is lost in the target area and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle.

[0057] It is understandable that the first tracking information may be lost in the target area due to reasons such as the first target vehicle being blocked. One case is that the first target vehicle is still in the target area, and the other case is that the first target vehicle is blocked and then drives out of the target area. Therefore, when the second tracking information of the second target vehicle is re-acquired in the target area included in the video to be processed, it cannot be determined that the second target vehicle is the first target vehicle, so it is necessary to determine whether the first target vehicle and the second target vehicle are the same target vehicle.

[0058] When the first tracking information is lost outside the target area, it is determined that the first target vehicle has driven out of the target area.

[0059] The method for acquiring the second target vehicle and the second tracking information is the same as the method for acquiring the first target vehicle and the first tracking information, and thus will not be described in detail.

[0060] S206: If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, updating the residence time of the first target vehicle in the target area based on the second tracking information.

[0061] If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information to obtain the total residence time of the first target vehicle in the target area. If it is determined that the first target vehicle and the second target vehicle are different target vehicles, the residence time of the second target vehicle in the target area is obtained.

[0062] In this embodiment, in the case where the first tracking information is lost in the target area, when the second tracking information of the second target vehicle is reacquired next time, the residence time is determined by judging whether the first target vehicle and the second target vehicle are the same target vehicle, thereby being able to more accurately obtain the residence time of the target vehicle in the target area.

[0063] In one embodiment, if Figure 3 As shown, determining whether the first target vehicle and the second target vehicle are the same target vehicle includes the following steps:

[0064] S302: extracting features of the first target vehicle based on the video to be processed to obtain first feature information;

[0065] S304: extracting features of the second target vehicle based on the video to be processed to obtain second feature information;

[0066] S306: Based on the matching relationship between the first feature information and the second feature information, determine whether the first target vehicle and the second target vehicle are the same target vehicle.

[0067] In this embodiment, if the first feature information and the second feature information match, it is determined that the first target vehicle and the second target vehicle are the same target vehicle; if the first feature information and the second feature information do not match, it is determined that the first target vehicle and the second target vehicle are different target vehicles.

[0068] In one embodiment, the first characteristic information and the second characteristic information include vehicle location information, license plate information, vehicle attribute information, etc. The vehicle attribute information refers to whether the vehicle is a fire truck.

[0069] The position of the target vehicle in the actual target area is determined according to the position of the target vehicle in the target area in the video frame, thereby obtaining the vehicle position information.

[0070] Based on the video to be processed, the trained model is used to extract the license plate features of the target vehicle to obtain the license plate information.

[0071] Based on the video to be processed, the trained model is used to extract the vehicle attribute features of the target vehicle, thereby obtaining the vehicle attribute information.

[0072] When any one of the first characteristic information matches any one of the second characteristic information, it can be determined that the first target vehicle and the second target vehicle are the same target vehicle.

[0073] In one embodiment, if Figure 4 As shown, based on the video to be processed, extracting the features of the first target vehicle and obtaining the first feature information includes the following steps:

[0074] S402: performing frame processing on the video to be processed to obtain video frames;

[0075] S404: Selecting a to-be-processed video frame including the first target vehicle from each video frame;

[0076] S406: Selecting a video frame to be extracted based on a comparison result between the acquired image parameters of the video frame to be processed and a preset parameter threshold;

[0077] S408: Based on the extracted features of the first target vehicle in the video frame to be extracted, first feature information is obtained using a multi-frame voting method.

[0078] Considering that not all video frames can clearly record the features of the first target vehicle, in this embodiment, by comparing the image parameters of the acquired video frame to be processed with the preset parameter threshold, a sufficiently clear video frame to be extracted is selected, thereby improving the accuracy of the first feature information, thereby improving the accuracy of the state judgment of the target fire escape passage. Among them, the image parameters include parameters such as clarity and angle.

[0079] Each frame of the video to be extracted is input into the established feature extraction model respectively, and the feature with the highest confidence is obtained as the first feature information using a multi-frame voting method.

[0080] It can be understood that the method for extracting the second feature information is the same as the method for extracting the first feature information, and thus will not be described in detail.

[0081] In one embodiment, the target area is an area of ​​a preset vehicle passage containing a preset type of vehicle, and the first target vehicle and the second target vehicle are vehicles other than the preset type of vehicle; the method further comprises the following steps:

[0082] S208: Determine the traffic status of the preset vehicle channel based on the relationship between the updated residence time and the preset time threshold.

[0083] The preset vehicle channel status includes the vehicle illegal parking status and the normal status. If the updated stay time is greater than the preset time threshold, it is determined that the target fire channel is in the illegal parking status, otherwise, it is in the normal status.

[0084] In this embodiment, because the residence time of the target vehicle in the preset vehicle channel can be obtained more accurately, the state of the preset vehicle channel can be judged more accurately.

[0085] It is understandable that the preset vehicle channel may be a fire channel, and the traffic status of the fire channel is determined based on the relationship between the updated residence time of the target vehicle and the preset time threshold.

[0086] It is understandable that the preset vehicle lane may also be other vehicle lanes, such as a bus lane, and the traffic status of the bus lane is determined based on the relationship between the updated target vehicle's stay time and the preset time threshold.

[0087] In one embodiment, after determining the residence time of the first target vehicle in the target area based on the first tracking information, the method further includes the following steps:

[0088] S203: Compare the residence time of the first target vehicle in the preset vehicle channel with a preset time threshold to determine the traffic status of the preset vehicle channel.

[0089] Before the first tracking information is lost in the preset vehicle channel, the residence time of the first target vehicle in the preset vehicle channel is compared with a preset time threshold to determine the state in the preset vehicle channel.

[0090] In one embodiment, if the preset vehicle channel is in a vehicle illegally parked state, an alarm is issued based on the first characteristic information and the stay time. The alarm information includes the first characteristic information and the stay time, etc.

[0091] When the preset vehicle channel is in the illegal parking state, the alarm information is uploaded. According to the alarm information, the target vehicle in the target fire channel is guided.

[0092] The alarm information includes the first characteristic information and the residence time, so the actual situation of the target vehicle in the target fire channel can be understood more accurately to take targeted actions.

[0093] In one embodiment, before obtaining the first tracking information of the first target vehicle in the target area included in the video to be processed, the method further includes the following steps:

[0094] S201: Based on the video to be processed, determine a target area in the video to be processed.

[0095] Specifically, Figure 5 As shown, the following steps are included:

[0096] S502: performing frame processing on the video to be processed to obtain video frames;

[0097] S504: Determine the segmentation target in each video frame based on the constructed channel scene semantic segmentation model;

[0098] S506: Determine a target area in each of the video frames based on the segmentation target.

[0099] A channel scene semantic segmentation model is constructed by using a lightweight baseline network with atrous convolution and attention mechanism, a spatial pyramid, a detail-preserving network and a feature fusion network to obtain segmentation targets such as the sky, road, and road lines, thereby determining the target area in each video frame. This method can quickly and accurately determine the target area in each video frame.

[0100] It is understandable that different detection methods may also be used to determine the target area in each video frame. In another embodiment, the illegal parking mesh signs in the video frame are detected to determine the target area in each video frame. In another embodiment, a text recognition method is used to identify keywords such as fire escape passages and life passages to determine the target area in each video frame.

[0101] Figure 6 The overall flow chart of the target area vehicle tracking method is as follows: Figure 6 As shown, first determine the target area and the first target vehicle according to the video to be processed, obtain the residence time of the first target vehicle in the target fire passage, and obtain the first characteristic information of the first target vehicle. Determine whether the illegal parking condition is met according to the residence time. If so, issue an illegal parking alarm; if not, determine whether the first target vehicle exits normally. If not, obtain the second characteristic information of the second target vehicle. If the first characteristic information matches the second characteristic information, it is determined to be the same target vehicle, and the illegal parking time is updated.

[0102] It can be understood that when the second tracking information is lost in the target area, the above-mentioned method for determining the same target vehicle is repeated until the target vehicles detected twice are different target vehicles.

[0103] It should be understood that although Figure 1-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0104] In one embodiment, if Figure 7 As shown, the present invention provides a target area vehicle tracking device, the device comprising:

[0105] A first determination module 702 is used to obtain first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information;

[0106] A second determination module 704 is used to determine whether the first target vehicle and the second target vehicle are the same target vehicle when the first tracking information is lost in the target area and the second tracking information of the second target vehicle is acquired in the target area included in the video to be processed;

[0107] The third determination module 706 is configured to update the residence time of the first target vehicle in the target area based on the second tracking information if it is determined that the first target vehicle and the second target vehicle are the same target vehicle.

[0108] In one embodiment, the target area is an area of ​​a preset vehicle passage containing a preset type of vehicle, and the first target vehicle and the second target vehicle are vehicles other than the preset type of vehicle; the device further comprises:

[0109] The fourth determination module is used to determine the traffic status of the preset vehicle channel based on the relationship between the updated residence time and the preset time threshold.

[0110] In one embodiment, the preset vehicle type includes a fire truck, and the preset vehicle passage includes a fire passage.

[0111] In one embodiment, the second determining module includes:

[0112] A first feature extraction module, used to extract the features of the first target vehicle based on the video to be processed to obtain first feature information;

[0113] A second feature extraction module is used to extract the features of the second target vehicle based on the video to be processed to obtain second feature information;

[0114] The second determination submodule is used to determine whether the first target vehicle and the second target vehicle are the same target vehicle based on the matching relationship between the first feature information and the second feature information.

[0115] In one embodiment, the first feature extraction module is specifically used for:

[0116] Performing frame processing on the video to be processed to obtain video frames;

[0117] Selecting a to-be-processed video frame containing the first target vehicle from each video frame;

[0118] Selecting a video frame to be extracted based on a comparison result between the acquired image parameters of the video frame to be processed and a preset parameter threshold;

[0119] Based on the extracted features of the first target vehicle in the video frame to be extracted, first feature information is obtained using a multi-frame voting method.

[0120] In one embodiment, the third determination module is specifically used to:

[0121] If the updated stay time is greater than the preset time threshold, the traffic status of the preset vehicle channel is determined to be a vehicle illegally parked state.

[0122] In one embodiment, it further includes:

[0123] An alarm module is used to issue an alarm based on the first feature information extracted from the first target vehicle and the stay time if the preset vehicle channel is in an illegally parked state.

[0124] In one embodiment, a fifth determining module is further included, and the fifth determining module is specifically configured to:

[0125] Performing frame processing on the video to be processed to obtain video frames;

[0126] Determine the segmentation target in each video frame based on the constructed channel scene semantic segmentation model;

[0127] Based on the segmented target, a target area in each video frame is determined.

[0128] The specific definition of the target area vehicle tracking device can be found in the definition of the target area vehicle tracking method above, which will not be repeated here. Each module in the above-mentioned target area vehicle tracking device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0129] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store motion detection data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in any of the above-mentioned target area vehicle tracking method embodiments are implemented.

[0130] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any of the above-mentioned target area vehicle tracking method embodiments are implemented.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned target area vehicle tracking method embodiments are implemented.

[0133] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0134] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A target area vehicle tracking method, characterized in that: The method comprises: Acquire first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information; When the first tracking information is lost in the target area due to the first target vehicle being blocked, and second tracking information of a second target vehicle is acquired in the target area included in the video to be processed, determining whether the first target vehicle and the second target vehicle are the same target vehicle; If it is determined that the first target vehicle and the second target vehicle are the same target vehicle, the residence time of the first target vehicle in the target area is updated based on the second tracking information.

2. The method according to claim 1, characterized in that The target area is an area of ​​a preset vehicle passage containing vehicles of a preset type, and the first target vehicle and the second target vehicle are vehicles other than the preset type of vehicles; The method further comprises: Based on the magnitude relationship between the updated dwell time and the preset time threshold, the traffic status of the preset vehicle channel is determined.

3. The method according to claim 2, characterized in that The preset vehicle types include fire trucks, and the preset vehicle passages include fire passages.

4. The method according to claim 1, characterized in that: The determining whether the first target vehicle and the second target vehicle are the same target vehicle comprises: Based on the video to be processed, extracting features of the first target vehicle to obtain first feature information; Based on the video to be processed, extracting the features of the second target vehicle to obtain second feature information; Based on the matching relationship between the first feature information and the second feature information, it is determined whether the first target vehicle and the second target vehicle are the same target vehicle.

5. The method according to claim 4, characterized in that The extracting the feature of the first target vehicle based on the video to be processed to obtain the first feature information includes: Performing frame processing on the video to be processed to obtain video frames; Selecting a to-be-processed video frame containing the first target vehicle from each video frame; Selecting a video frame to be extracted based on a comparison result between the acquired image parameters of the video frame to be processed and a preset parameter threshold; Based on the extracted features of the first target vehicle in the video frame to be extracted, first feature information is obtained using a multi-frame voting method.

6. The method according to claim 2, characterized in that The determining the traffic state of the preset vehicle channel based on the relationship between the updated dwell time and the preset time threshold comprises: If the updated stay time is greater than the preset time threshold, the traffic status of the preset vehicle channel is determined to be a vehicle illegally parked state.

7. The method according to claim 6, characterized in that Also includes: If the preset vehicle channel is in an illegally parked state, an alarm is issued based on the first feature information extracted from the first target vehicle and the stay time.

8. The method according to claim 1, characterized in that Before obtaining the first tracking information of the first target vehicle in the target area included in the video to be processed, the method further includes: Performing frame processing on the video to be processed to obtain video frames; Determine the segmentation target in each video frame based on the constructed channel scene semantic segmentation model; Based on the segmented target, a target area in each of the video frames is determined.

9. A target area vehicle tracking device, characterized in that: The device comprises: A first determination module is used to obtain first tracking information of a first target vehicle in a target area included in the video to be processed, and determine a stay time of the first target vehicle in the target area based on the first tracking information; A second determination module is used to determine whether the first target vehicle and the second target vehicle are the same target vehicle when the first tracking information is lost due to the first target vehicle being blocked in the target area and the second tracking information of the second target vehicle is acquired in the target area included in the video to be processed; The third determination module is configured to update the residence time of the first target vehicle in the target area based on the second tracking information if it is determined that the first target vehicle and the second target vehicle are the same target vehicle.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

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

Images