Vehicle tracking threshold updating method, device, electronic device and storage medium

Abstract

The present invention provides a vehicle tracking threshold update method, device, electronic device, and storage medium, relating to the field of image processing technology. The method comprises: first acquiring a to-be-processed image of a vehicle on a monitored road; determining the position information of a tracking target in the image based on a pre-trained detection model; updating an IoU threshold based on this position information; and tracking the tracking target based on the updated IoU threshold. This method, combining position information monitoring with IoU threshold updating, can address the ID jump problem of "nonlinear geometric scaling" data association tracking. Compared with existing Kalman filtering methods, it reduces the error rate of data association and improves the practical application of target tracking.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a vehicle tracking threshold updating method, device, electronic device and storage medium. Background Art

[0002] The visual tracking system can automatically detect and track selected targets from the original video captured by the camera. This system is one of the basic technologies in the field of computer vision and is widely used in vehicle monitoring, unmanned driving, robotics, security monitoring, etc.

[0003] In intelligent road traffic systems, tracking and locating vehicle traffic is a key technology in intelligent traffic management research. Current vehicle tracking technologies rely heavily on GPS tracking systems, 3D LiDAR, and AI-based camera-based target detection and tracking. This has significantly advanced the development of intelligent non-site highway law enforcement. In practice, relevant departments have deployed a large number of surveillance cameras at intersections, highway entrances and exits, and key road sections, enabling comprehensive monitoring of urban roads.

[0004] However, when it is necessary to track a target vehicle from a traffic video stream, traditional manual monitoring methods are not only time-consuming and labor-intensive, but also prone to missing key video information and low efficiency. Furthermore, in the case of a single camera, there are disadvantages such as a small monitoring range and insufficient information. While the multi-camera approach can compensate for the shortcomings of a single camera, existing "cross-camera" tracking technology is not very mature, with frequent tracking ID jumps and poor stability. In most practical applications, it still relies on manual clicks to switch videos, making it less applicable. While multi-camera panoramic camera stitching can also provide a wide field of view, the stitching imaging process introduces nonlinear spherical distortion at close range, resulting in "nonlinear scale changes" of vehicle targets, significantly affecting the continuous tracking of variable-range targets. Summary of the Invention

[0005] The purpose of the present invention is to provide a vehicle threshold updating method, device, electronic device and storage medium to reduce the error rate of data association and improve the practical application effect of target tracking.

[0006] Obtaining a vehicle image to be processed;

[0007] Determining the position information of the tracking target in the image to be processed according to a pre-trained detection model;

[0008] An IoU threshold is updated according to the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold; wherein the IoU threshold corresponding to a closer tracking target is smaller than the IoU threshold corresponding to a farther tracking target, and the distance between the closer tracking target and a camera that captures the image to be processed is smaller than the distance between the farther tracking target and the camera.

[0009] Furthermore, the step of determining the position information of the tracking target in the image to be processed according to the pre-trained detection model includes:

[0010] Inputting the image to be processed into the detection model to obtain a plurality of initial targets, and the confidence and position information of each of the initial targets;

[0011] According to the confidence level of each of the initial targets, a tracking target is screened out from the multiple initial targets.

[0012] Furthermore, the step of selecting a tracking target from the plurality of initial targets according to the confidence level of each initial target includes:

[0013] An initial target whose confidence level is greater than or equal to a preset confidence threshold among the multiple initial targets is determined as a tracking target.

[0014] Furthermore, the position information of the tracking target includes the vehicle type of the tracking target and the coordinate value of the tracking target in its moving direction; and the step of updating the intersection-over-union ratio threshold value according to the position information of the tracking target includes:

[0015] Determining target update parameters corresponding to the vehicle type of the tracking target according to a preset correspondence between vehicle types and update parameters;

[0016] An intersection-over-union threshold is updated according to the coordinate value of the tracking target in its moving direction and the target update parameter.

[0017] Furthermore, the step of updating the intersection-over-union threshold according to the coordinate value of the tracking target in its motion direction and the target update parameter includes:

[0018] The updated intersection-over-union threshold IOU is calculated by the following formula threshold :

[0019]

[0020] Wherein, x is the coordinate value of the tracking target in its moving direction, the target update parameters include r, μ, σ and b, r is the shape factor, μ is the sample mean, σ is the sample variance factor, and b is the deviation degree factor.

[0021] In a second aspect, an embodiment of the present invention further provides a vehicle tracking threshold updating device, the device comprising:

[0022] An acquisition module, used for acquiring the image to be processed of the vehicle;

[0023] A determination module, configured to determine the position information of the tracking target in the image to be processed based on a pre-trained detection model;

[0024] and an updating module, configured to update an IoU threshold value based on the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold value; wherein the IoU threshold value corresponding to a closer tracking target is smaller than the IoU threshold value corresponding to a farther tracking target, and the distance between the closer tracking target and a camera that captures the image to be processed is smaller than the distance between the farther tracking target and the camera.

[0025] Furthermore, the position information of the tracking target includes the vehicle type of the tracking target and the coordinate value of the tracking target in its moving direction; the updating module is specifically configured to:

[0026] Determining target update parameters corresponding to the vehicle type of the tracking target according to a preset correspondence between vehicle types and update parameters;

[0027] An intersection-over-union threshold is updated according to the coordinate value of the tracking target in its moving direction and the target update parameter.

[0028] Furthermore, the update module is further configured to:

[0029] The updated intersection-over-union threshold IOU is calculated by the following formula threshold :

[0030]

[0031] Wherein, x is the coordinate value of the tracking target in its moving direction, the target update parameters include r, μ, σ and b, r is the shape factor, μ is the sample mean, σ is the sample variance factor, and b is the deviation degree factor.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the method described in the first aspect when executing the computer program.

[0033] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the method described in the first aspect is executed.

[0034] The vehicle threshold update method, device, electronic device and storage medium provided by the embodiments of the present invention obtain a to-be-processed image of a vehicle, determine the position information of the tracking target in the to-be-processed image based on a pre-trained detection model, and update the intersection-in-union (IoU) threshold based on the position information of the tracking target to track the tracking target based on the updated IoU threshold, wherein the IoU threshold corresponding to the closer tracking target is smaller than the IoU threshold corresponding to the farther tracking target, and the distance between the closer tracking target and the camera that captured the to-be-processed image is smaller than the distance between the farther tracking target and the camera. This update method that combines position information monitoring and IoU threshold can solve the problem of ID jumps in "non-linear geometric scale" data association tracking. Compared with the existing Kalman filtering method, it reduces the error rate of data association and improves the practical application effect of target tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A schematic diagram of a scenario of a vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0037] Figure 2 A schematic flow chart of a vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0038] Figure 3 A diagram illustrating a calculation method for a vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0039] Figure 4 A statistical result diagram of a vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0040] Figure 5 A graph showing statistical results of another vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0041] Figure 6 A fitting curve diagram of another vehicle tracking threshold updating method provided by an embodiment of the present invention;

[0042] Figure 7 A schematic structural diagram of a vehicle tracking threshold updating device provided by an embodiment of the present invention;

[0043] Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] In intelligent road traffic systems, tracking and locating road vehicle driving information is a key technology in intelligent traffic management research. However, when it is necessary to track a target vehicle from a traffic video stream, the traditional manual monitoring method is not only time-consuming and labor-intensive, but also prone to missing key video information and low efficiency. Moreover, in the scenario of a single camera, there are disadvantages such as a small monitoring range and insufficient information. Although the multi-camera method can make up for the shortcomings of a single camera, the existing "cross-camera" tracking technology is not mature enough, the tracking ID jumps frequently, and the stability is poor. In most practical applications, it still relies on manual clicks on video switching, and its applicability is not high. Based on this, the embodiment of the present invention provides a vehicle tracking threshold update method, device, electronic device and storage medium, which combines position information monitoring and the update method of the intersection-and-union ratio threshold, can reduce the error rate of data association and improve the practical application effect of target tracking.

[0046] To facilitate understanding of this embodiment, a vehicle tracking threshold updating method disclosed in an embodiment of the present invention is first introduced in detail.

[0047] The embodiment of the present invention provides a method for updating a vehicle tracking threshold value. The method can be executed by an electronic device with image processing capabilities and is applicable to road monitoring in traffic law enforcement. Figure 1 Schematic diagram of a scenario of a vehicle tracking threshold update method shown in FIG:

[0048] The multi-view panoramic camera tracks the vehicles on the monitored road and generates a tracking video. When the vehicle reaches the intermediate distance, the type of the target vehicle is detected, and a detection frame of the target vehicle is generated and uploaded to the detection model.

[0049] Multi-lens panoramic cameras offer 360-degree coverage, making them suitable for monitoring large spaces. This application uses multi-lens panoramic cameras to provide full 360-degree coverage, while multiple detail domes are used to track targets within a 360-degree range. Targets in different directions can be tracked simultaneously. The vehicle type indicates the size of the vehicle, typically designated as "Truck" or "Car." The detection box is a rectangular box representing the vehicle's position within the image.

[0050] See also Figure 2 FIG. 1 is a flow chart of a method for updating a vehicle tracking threshold value, wherein the method performs the following tracking threshold updating processing shown in steps S101 to S103 on an image of a vehicle to be detected to obtain an IoU threshold value related to the position information of the tracking target:

[0051] Step S101: Acquire a vehicle image to be processed.

[0052] The embodiment of the present application uses a multi-eye panoramic camera to obtain vehicle images from long distances to close distances, and generates a detection frame adapted to the size of the vehicle, and the detection frame is rectangular.

[0053] Step S102: determining the position information of the tracking target in the image to be processed according to the pre-trained detection model.

[0054] The detection model in the embodiment of the present application can use a uniform velocity model and a linear observation model to predict and update the state of the target position and target velocity obtained by detection. The position information of the tracking target includes the type of tracking vehicle and the position of the tracking vehicle in the image to be processed. The position can be determined in a coordinate system.

[0055] In some possible embodiments, the image to be processed is input into a detection model to obtain multiple initial targets, as well as the confidence and position information of each initial target. According to the confidence of each initial target, the tracking target is screened out from the multiple initial targets.

[0056] The confidence interval of a probability sample is an interval estimate of a population parameter of the sample. The confidence interval shows the degree to which the true value of the parameter has a certain probability of falling within the range of the measurement result. The confidence interval provides a range of credibility of the measured value of the measured parameter, that is, the "certain probability" required above. This probability is called the confidence level. The confidence level in the embodiment of the present application is to filter out the tracking target from multiple initial targets, and the confidence level represents the credibility of the tracking target.

[0057] In some possible embodiments, an initial target among the multiple initial targets whose confidence level is greater than or equal to a preset confidence threshold is determined as a tracking target.

[0058] In an embodiment of the present application, the confidence level can be pre-set to 0.25. When the detection target is greater than the pre-set confidence level, it indicates that the detection target exists in the area. When the detection target is less than the pre-set confidence level, it indicates that the detection target does not exist in the area.

[0059] Step S103 : updating the IoU threshold according to the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold.

[0060] The intersection-over-union (IoU) calculation is used to describe the degree of overlap between two bounding boxes. The IoU is equal to the area of ​​the overlapping parts of the two boxes divided by their combined area, that is, the intersection divided by the union. Figure 3 This is the IOU calculation method provided in this application. The initial IOU threshold in this application can be set to 0.9. This threshold is updated based on the target's location information using Deepsort's target tracking method. The vehicle type indicates the size of the vehicle, typically using "Truck" or "Car."

[0061] In some possible embodiments, the position information of the tracking target includes the vehicle type of the tracking target and the coordinate value of the tracking target in the direction of its movement; the step of updating the intersection-in-union ratio threshold value based on the position information of the tracking target includes: determining a target update parameter corresponding to the vehicle type of the tracking target based on a preset correspondence between the vehicle type and the update parameter, and updating the intersection-in-union ratio threshold value based on the coordinate value of the tracking target in the direction of its movement and the target update parameter.

[0062] The purpose of determining the vehicle type is to compare it with the preset vehicle type and obtain the parameters corresponding to the vehicle type. Different detected vehicle types represent different parameters. The position information is the coordinate position of the target in the image. In this embodiment of the application, the direction of movement of the vehicle is set as the x-axis of the image coordinate system to obtain the vehicle target tracking IOU. threshold value, IOU threshold The target value obtained by tracking is combined with the initial IOU threshold. threshold The mapping relationship with the image coordinate x is as follows:

[0063] U threshold =f(x),x∈[0,w]

[0064] Among them, x is the value of the detection target on the x-axis of the image coordinate system, and w is the image width.

[0065] In some optional embodiments, the step of tracking the coordinate value of the target in its moving direction and the target update parameter and updating the intersection-over-union threshold includes:

[0066] The updated intersection-over-union threshold IOU is calculated by the following formula threshold :

[0067]

[0068] Wherein, x is the coordinate value of the tracking target in its moving direction, the target update parameters include r, μ, σ and b, r is the shape factor, μ is the sample mean, σ is the sample variance factor, and b is the deviation degree factor.

[0069] The vehicle threshold update method provided by an embodiment of the present invention obtains a to-be-processed image of a vehicle, determines the position information of the tracking target in the to-be-processed image based on a pre-trained detection model, updates the intersection-in-union (IoU) threshold based on the position information of the tracking target, and tracks the tracking target based on the updated IoU threshold, wherein the IoU threshold corresponding to the closer tracking target is smaller than the IoU threshold corresponding to the farther tracking target, and the distance between the closer tracking target and the camera that captured the to-be-processed image is smaller than the distance between the farther tracking target and the camera. This update method that combines position information monitoring and IoU threshold can solve the problem of ID jumps in "non-linear geometric scale" data association tracking. Compared with the existing Kalman filtering method, it reduces the error rate of data association and improves the practical application effect of target tracking.

[0070] The present invention also provides a data experimental result curve diagram of the above method, which is as follows:

[0071] See also Figure 4 This is the vehicle tracking threshold update method proposed in an embodiment of the present invention, based on the average results of 100 times for different vehicle types, and the IOU statistical result graph of the continuous detection target boxes in the previous and next frames.

[0072] See also Figure 5 The Peaks distribution diagram is obtained by judging the lower peak point (peaks) of the original data IOU value and fitting the regression based on the lower envelope curve of the IOU value.

[0073] The vehicle tracking threshold update method proposed in the present invention is based on the characteristic that the data distribution has larger IOU values ​​at both ends and smaller IOU values ​​in the middle (caused by the central distortion of the multi-camera image), and its distribution is "bell-shaped". Therefore, the present invention is modeled based on a "simulated Gaussian probability density curve", and the function equation formula is shown below.

[0074]

[0075] Wherein, x is the coordinate value of the tracking target in its moving direction, the target update parameters include r, μ, σ and b, r is the shape factor, μ is the sample mean, σ is the sample variance factor, and b is the deviation degree factor.

[0076] The embodiment of the present invention uses the mean-variance minimum parameter iteration to solve the optimal solution, and the optimal solution is u=960; σ=150, r=0.005, b=0.06. Figure 6 This is a curve fitting effect diagram provided by an embodiment of the present invention.

[0077] Corresponding to the above-mentioned vehicle tracking threshold updating method, an embodiment of the present invention further provides a vehicle tracking threshold updating device, which is used to obtain a to-be-processed image of a vehicle, determine the position information of a tracking target in the to-be-processed image based on a pre-trained detection model, and update the intersection-in-union (IoU) threshold based on the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold. Figure 7 FIG. 7 is a schematic diagram of a vehicle tracking threshold updating device 700, the device comprising:

[0078] The acquisition module 710 is used to acquire the image to be processed of the vehicle.

[0079] The determination module 720 is configured to determine the position information of the tracking target in the image to be processed based on a pre-trained detection model.

[0080] An updating module 730 is configured to update an IoU threshold value based on the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold value; wherein the IoU threshold value corresponding to a closer tracking target is smaller than the IoU threshold value corresponding to a farther tracking target, and the distance between the closer tracking target and the camera that captured the image to be processed is smaller than the distance between the farther tracking target and the camera.

[0081] The vehicle threshold updating device provided in an embodiment of the present invention obtains an image of a vehicle to be processed, determines the position information of the tracking target in the image to be processed based on a pre-trained detection model, and updates the intersection-in-union (IoU) threshold based on the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold, wherein the IoU threshold corresponding to the closer tracking target is smaller than the IoU threshold corresponding to the farther tracking target, and the distance between the closer tracking target and the camera that captured the image to be processed is smaller than the distance between the farther tracking target and the camera. This updating method that combines position information monitoring and IoU threshold can solve the problem of ID jump in "nonlinear geometric scale" data association tracking. Compared with the existing Kalman filtering method, it reduces the error rate of data association and improves the practical application effect of target tracking.

[0082] Furthermore, the update module 730 is specifically configured to determine a target update parameter corresponding to the vehicle type of the tracking target according to a preset correspondence between the vehicle type and the update parameter, and update the intersection-over-union threshold according to the coordinate value of the tracking target in its moving direction and the target update parameter.

[0083] Furthermore, the updating module 730 is further configured to calculate the updated intersection-over-union threshold IOU using the following formula: threshold :

[0084]

[0085] Wherein, x is the coordinate value of the tracking target in its moving direction, the target update parameters include r, μ, σ and b, r is the shape factor, μ is the sample mean, σ is the sample variance factor, and b is the deviation degree factor.

[0086] The device provided in this embodiment has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0087] See also Figure 8 An embodiment of the present invention further provides an electronic device 800, comprising: a processor 802, a memory 804, a bus 803 and a communication interface 801, wherein the processor 802, the communication interface 801 and the memory 804 are connected via the bus 803; the processor 802 is used to execute an executable module stored in the memory 804, such as a computer program.

[0088] The memory 804 may include random access memory (RAM) and non-volatile memory (NVM), such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 801 (which may be wired or wireless), such as the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0089] The bus 803 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0090] Among them, the memory 804 is used to store programs, and the processor 802 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 802 or implemented by the processor 802.

[0091] Processor 802 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 802. The above processor 802 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 804, and processor 802 reads information in memory 804 and, in conjunction with its hardware, completes the steps of the above method.

[0092] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program that, when executed by a processor, executes the seismic image noise suppression method described in the preceding method embodiments. The computer-readable storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), RAM, a magnetic disk, or an optical disk.

[0093] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not limiting, and thus other examples of the exemplary embodiments may have different values.

[0094] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the 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, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that 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 block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0097] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle tracking threshold updating method, characterized in that: include: Obtaining a vehicle image to be processed; Determining the position information of the tracking target in the image to be processed according to a pre-trained detection model; updating an IoU threshold according to the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold; wherein the IoU threshold corresponding to a closer tracking target is smaller than the IoU threshold corresponding to a farther tracking target, and the distance between the closer tracking target and a camera that captures the image to be processed is smaller than the distance between the farther tracking target and the camera; The position information of the tracking target includes the vehicle type of the tracking target and the coordinate value of the tracking target in its moving direction; and the step of updating the intersection-over-union ratio threshold value according to the position information of the tracking target includes: Determining target update parameters corresponding to the vehicle type of the tracking target according to a preset correspondence between vehicle types and update parameters; An intersection-over-union threshold is updated according to the coordinate value of the tracking target in its moving direction and the target update parameter.

2. The vehicle tracking threshold updating method according to claim 1, characterized in that: The step of determining the position information of the tracking target in the image to be processed according to the pre-trained detection model includes: Inputting the image to be processed into the detection model to obtain a plurality of initial targets, and the confidence and position information of each of the initial targets; According to the confidence level of each of the initial targets, a tracking target is screened out from the multiple initial targets.

3. The vehicle tracking threshold updating method according to claim 2, characterized in that: The step of selecting a tracking target from the plurality of initial targets according to the confidence level of each initial target comprises: An initial target whose confidence level is greater than or equal to a preset confidence threshold among the multiple initial targets is determined as a tracking target.

4. The vehicle tracking threshold updating method according to claim 1, characterized in that: The step of updating the intersection-over-union ratio threshold value according to the coordinate value of the tracking target in its motion direction and the target update parameter includes: The updated intersection-over-union threshold is calculated by the following formula : = ， in, is the coordinate value of the tracking target in its moving direction, and the target update parameters include r, μ, σ and b， r is the shape factor, μ is the sample mean, σ is the sample variance factor, b is the deviation factor.

5. A vehicle tracking threshold updating device, characterized in that: include: An acquisition module, used for acquiring the image to be processed of the vehicle; A determination module, configured to determine the position information of the tracking target in the image to be processed based on a pre-trained detection model; an updating module, configured to update an IoU threshold value based on the position information of the tracking target, so as to track the tracking target based on the updated IoU threshold value; wherein the IoU threshold value corresponding to a closer tracking target is smaller than the IoU threshold value corresponding to a farther tracking target, and the distance between the closer tracking target and a camera that captures the image to be processed is smaller than the distance between the farther tracking target and the camera; The position information of the tracking target includes the vehicle type of the tracking target and the coordinate value of the tracking target in its moving direction; the updating module is specifically used to: Determining target update parameters corresponding to the vehicle type of the tracking target according to a preset correspondence between vehicle types and update parameters; An intersection-over-union threshold is updated according to the coordinate value of the tracking target in its moving direction and the target update parameter.

6. The vehicle tracking threshold updating device according to claim 5, characterized in that: The update module is further configured to: The updated intersection-over-union threshold is calculated by the following formula : = ， in, is the coordinate value of the tracking target in its moving direction, and the target update parameters include r, μ, σ and b， r is the shape factor, μ is the sample mean, σ is the sample variance factor, b is the deviation factor.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

8. A computer-readable 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 4 is executed.

Images