Target vehicle trajectory tracking method, device and storage medium

Abstract

The present invention relates to the field of image processing technology, and specifically provides a method, device, and storage medium for tracking the trajectory of a target vehicle, aiming to address the technical issues of low accuracy and large errors in existing vehicle trajectory tracking methods. To this end, the target vehicle trajectory tracking method of the present invention includes: obtaining an image to be identified that includes the target vehicle; detecting the image to be identified to obtain attribute information of the target vehicle; and extracting features from the image to be identified to obtain a feature vector of the target vehicle; obtaining at least one matching image that matches the attribute information and the feature vector; and performing clustering based on the image to be identified and the at least one matching image to obtain the vehicle trajectory of the target vehicle. This improves the accuracy of the vehicle trajectory.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and specifically provides a target vehicle trajectory tracking method, device and storage medium. Background Art

[0002] Currently, in vehicle trajectory tracking application scenarios, it is necessary to search and associate vehicle images taken at different times, locations, and cameras from large amounts of data to obtain the vehicle trajectory of the same vehicle.

[0003] However, in actual applications, the amount of data is in the millions, tens of millions, or even more. Direct vehicle retrieval and trajectory generation has low accuracy and consumes a lot of resources.

[0004] Accordingly, the art needs a new target vehicle trajectory tracking solution to solve the above problems. Summary of the Invention

[0005] To overcome the above-mentioned drawbacks, the present invention is proposed to provide a solution or at least partially solve the technical problem of low accuracy and large error in existing vehicle trajectory tracking methods. The present invention provides a target vehicle trajectory tracking method, device, and storage medium.

[0006] In a first aspect, the present invention provides a method for tracking the trajectory of a target vehicle, the method comprising: obtaining an image to be identified containing the target vehicle; detecting the image to be identified to obtain attribute information of the target vehicle, and performing feature extraction on the image to be identified to obtain a feature vector of the target vehicle; obtaining at least one matching image that matches the attribute information and the feature vector; and performing clustering based on the image to be identified and the at least one matching image to obtain a vehicle trajectory of the target vehicle.

[0007] In a specific embodiment, the image to be identified is detected to obtain attribute information of the target vehicle, including: inputting the image to be identified into a target detection model to obtain attribute information of the target vehicle, wherein the attribute information of the target vehicle includes at least one of vehicle color, direction, type, license plate number and license plate color.

[0008] In a specific embodiment, the method also includes: obtaining time information and location information corresponding to the image to be identified; obtaining at least one matching image that matches the vehicle information, including: using at least one of the time information, location information and attribute information to query in a database to obtain a query image; using the feature vector of the target vehicle to match the query image to obtain the at least one matching image.

[0009] In a specific embodiment, clustering is performed based on the image to be identified and the at least one matching image to obtain the vehicle trajectory of the target vehicle, including: determining a characteristic distance between the image to be identified and the at least one matching image; judging whether the characteristic distance satisfies a distance threshold; if the characteristic distance satisfies the distance threshold, determining the speed of the target vehicle based on the image to be identified and the at least one matching image; judging whether the speed of the target vehicle satisfies a speed threshold; if the speed of the target vehicle satisfies the speed threshold, generating the vehicle trajectory of the target vehicle based on the image to be identified and the at least one matching image.

[0010] In a specific embodiment, determining the characteristic distance between the image to be identified and the at least one matching image includes: obtaining a feature vector of the at least one matching image; and determining the characteristic distance between the image to be identified and the at least one matching image based on the feature vector of the target vehicle and the feature vector of the at least one matching image.

[0011] In a specific embodiment, before detecting the image to be identified and obtaining the attribute information and feature vector of the target vehicle, it also includes: obtaining the position information of the target vehicle in the image to be identified; and obtaining the target vehicle image from the image to be identified based on the position information.

[0012] In a specific embodiment, when at least two images to be identified containing the target vehicle are obtained, the method further includes: determining a feature vector mean based on the feature vector of the target vehicle corresponding to each image to be identified; and matching the feature vector mean with the query image to obtain the at least one matching image.

[0013] In a second aspect, the present invention provides a target vehicle trajectory tracking device, comprising: an acquisition module, configured to acquire an image to be identified containing the target vehicle; a detection module, configured to detect the image to be identified to obtain attribute information of the target vehicle, and perform feature extraction on the image to be identified to obtain a feature vector of the target vehicle; a matching module, configured to acquire at least one matching image that matches the attribute information and the feature vector; and a clustering module, configured to perform clustering based on the image to be identified and the at least one matching image to obtain the vehicle trajectory of the target vehicle.

[0014] In a third aspect, an electronic device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute any of the aforementioned target vehicle trajectory tracking methods.

[0015] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute any one of the aforementioned target vehicle trajectory tracking methods.

[0016] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0017] The target vehicle trajectory tracking method of the present invention first obtains an image containing the target vehicle, then detects the image to be identified to obtain attribute information of the target vehicle, extracts features from the image to be identified to obtain a feature vector of the target vehicle, then obtains at least one matching image that matches the attribute information and feature vector, and finally clusters the image to be identified and the at least one matching image to obtain the target vehicle's trajectory. In this way, matching images that match the target vehicle's attribute information and feature vector are obtained from a database, and then clustered together with the image to be identified and the matching images to obtain a highly accurate vehicle trajectory, thereby improving the accuracy of the vehicle trajectory and reducing errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The disclosure of the present invention will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. Furthermore, similar numbers in the drawings represent similar components, wherein:

[0019] Figure 1 1 is a flow chart showing the main steps of a target vehicle trajectory tracking method according to an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of a process for obtaining vehicle trajectories by clustering according to one embodiment of the present invention;

[0021] Figure 3 1 is a schematic diagram of a complete step flow chart of a target vehicle trajectory tracking method according to an embodiment of the present invention;

[0022] Figure 4 It is a schematic diagram of the main structure block diagram of a target vehicle trajectory tracking device according to an embodiment of the present invention.

[0023] Reference Signs List :

[0024] 11: Acquisition module; 12: Detection module; 13: Matching module; 14: Clustering module. DETAILED DESCRIPTION

[0025] Some embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0026] In the description of the present invention, "module" and "processor" may include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory. It may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. A processor has data and / or signal processing capabilities. A processor may be implemented in software, hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or both A and B. The terms "at least one of A or B" or "at least one of A and B" have similar meanings to "A and / or B" and may include only A, only B, or both A and B. The singular forms "one" and "the" may also include the plural forms.

[0027] Currently, vehicle trajectory tracking applications require searching and correlating vehicle images taken at different times, locations, and with different cameras from large amounts of data to obtain the trajectory of the same vehicle. However, in real-world applications, data volumes can reach millions, tens of millions, or even more. Direct vehicle retrieval and trajectory generation suffers from low accuracy and high resource usage.

[0028] To this end, the present application provides a method for tracking the trajectory of a target vehicle. The method first obtains an image to be identified containing the target vehicle, then detects the image to be identified to obtain attribute information of the target vehicle, and extracts features from the image to be identified to obtain a feature vector of the target vehicle. At least one matching image that matches the attribute information and feature vector is then obtained, and finally, clustering is performed based on the image to be identified and the at least one matching image to obtain the target vehicle's trajectory. In this way, matching images that match the attribute information and feature vector of the target vehicle are obtained from a database, and then clustering the image to be identified and the matching images to obtain a highly accurate vehicle trajectory, thereby improving the accuracy of the vehicle trajectory and reducing errors.

[0029] See attached Figure 1 , Figure 1 1 is a flow chart of the main steps of a target vehicle trajectory tracking method according to an embodiment of the present invention.

[0030] like Figure 1As shown, the target vehicle trajectory tracking method in the embodiment of the present invention mainly includes the following steps S101 to S104.

[0031] Step S101: Acquire an image to be identified containing a target vehicle.

[0032] Specifically, one image to be identified containing the target vehicle can be obtained, or multiple images to be identified containing the target vehicle can be obtained. In this application, the main purpose is to obtain an image to be identified containing the target vehicle to track the vehicle trajectory of the target vehicle, but it is not limited to this.

[0033] In addition, in order to improve the detection accuracy of the target vehicle, the target vehicle image can be cut out from the image to be identified.

[0034] In a specific embodiment, before detecting the image to be identified and obtaining the attribute information and feature vector of the target vehicle, it also includes: obtaining the position information of the target vehicle in the image to be identified; and obtaining the target vehicle image from the image to be identified based on the position information.

[0035] Specifically, a vehicle detection algorithm can be used to first detect the specific location of the vehicle in the image to be identified, and then the target vehicle image can be extracted from the image based on the specific location. Alternatively, a vehicle head detection model can be used to detect the location of the vehicle head in the image to be identified, and then the target vehicle head image can be extracted from the image to be identified. This helps improve detection accuracy when subsequently extracting the target vehicle's feature vector or detecting its attribute information.

[0036] The above-mentioned vehicle detection algorithms and vehicle face detection models include but are not limited to any one of the Retina algorithm, the YOLO series algorithm, and the Faster-RCNN algorithm.

[0037] Step S102: Detecting the image to be identified to obtain attribute information of the target vehicle, and extracting features from the image to be identified to obtain a feature vector of the target vehicle.

[0038] In a specific embodiment, the image to be identified is detected to obtain attribute information of the target vehicle, including: inputting the image to be identified into a target detection model to obtain attribute information of the target vehicle, wherein the attribute information of the target vehicle includes at least one of vehicle color, direction, type, license plate number and license plate color.

[0039] The object detection model is based on an object detection algorithm or an image classification algorithm. It can detect attributes of the input image to be identified and obtain the target vehicle's attribute information. The target vehicle's attribute information can include vehicle color, brand, year, direction, type, purpose, license plate number, license plate color, interior accessories, annual inspection sticker, sun visor, and other information.

[0040] The target detection algorithm can be a conventional algorithm and will not be described here.

[0041] In addition, the present application can also extract the feature vector of the target vehicle. Exemplarily, the feature vector of the target vehicle can be extracted using the backbone of the feature pyramid network.

[0042] Step S103: Obtain at least one matching image that matches the attribute information and the feature vector. Specifically, obtain the matching image from the database, which is a database that stores all images taken by the camera.

[0043] In a specific embodiment, the method further includes: obtaining time information and location information corresponding to the image to be identified.

[0044] The specific shooting time and shooting location of the image to be identified can be obtained as a supplementary query condition, but is not limited thereto. The ETC information corresponding to the target vehicle can also be obtained.

[0045] Acquiring at least one matching image that matches the vehicle information includes: using at least one of the time information, location information, and attribute information to query in a database to obtain a query image; using a feature vector of the target vehicle to match the query image to obtain the at least one matching image.

[0046] For example, the specific shooting time, shooting location and attribute information of the target vehicle of the image to be identified are first used to query in the database to obtain multiple query images, and then the feature vectors of the target vehicle are matched with the multiple query images respectively to obtain matching images.

[0047] The feature vector of the target vehicle is used to match the query image. This means that the feature vector of the target vehicle is convolved with the feature vector of the query image. If the result is 1, it means that the query image is a matching image; if the result is 0, it means that the query image is not a matching image and is deleted.

[0048] Step S104: performing clustering based on the image to be identified and at least one matching image to obtain a vehicle trajectory of the target vehicle.

[0049] This application mainly uses a spatiotemporal clustering algorithm combined with spatiotemporal constraints to generate the vehicle trajectory of the target vehicle.

[0050] In a specific embodiment, Figure 2 As shown, clustering is performed based on the image to be identified and at least one matching image to obtain the vehicle trajectory of the target vehicle, including:

[0051] First, a characteristic distance between the image to be identified and at least one matching image is determined. In one specific embodiment, determining the characteristic distance between the image to be identified and the at least one matching image includes: first obtaining a feature vector of the at least one matching image; and then determining the characteristic distance between the image to be identified and the at least one matching image based on the feature vector of the target vehicle and the feature vector of the at least one matching image.

[0052] Specifically, after obtaining the feature vectors corresponding to the two images, the feature distance can be calculated using the Euclidean distance calculation formula.

[0053] Then, it is determined whether the feature distance meets a distance threshold, where the distance threshold may be obtained in advance through experiments.

[0054] If the characteristic distance meets the distance threshold, the target vehicle's speed is determined based on the image to be identified and at least one matching image. Specifically, the specific shooting location and time of the image to be identified, as well as the specific shooting location and time of at least one matching image, are obtained. The shooting distance and time difference between the two are then determined. The target vehicle's speed is then derived from this difference.

[0055] Then, it is determined whether the speed of the target vehicle meets a speed threshold value. The speed threshold value here can be a value obtained in advance through experiments.

[0056] When the target vehicle's speed meets a speed threshold, a vehicle trajectory of the target vehicle is generated based on the image to be identified and at least one matching image. Specifically, the matching images that meet the conditions are arranged in a time series to obtain the target vehicle's trajectory.

[0057] Based on steps S101-S104 above, an image containing the target vehicle is first acquired. The image is then detected to obtain the target vehicle's attribute information, and features are extracted from the image to obtain a feature vector for the target vehicle. At least one matching image that matches the attribute information and feature vector is then acquired. Finally, clustering is performed based on the image to be identified and the at least one matching image to obtain the target vehicle's trajectory. In this manner, matching images that match the target vehicle's attribute information and feature vector are acquired from a database, and clustering is then performed on the image to be identified and the matching images to obtain a highly accurate vehicle trajectory, thereby improving the accuracy of the vehicle trajectory and reducing errors.

[0058] In a specific embodiment, accurate identity information about the target vehicle can be obtained in advance. When querying the database to obtain the query image, more precise retrieval conditions, such as the license plate number, can be added. In this way, a high-precision vehicle trajectory can be further obtained.

[0059] In a specific embodiment, when at least two images to be identified containing the target vehicle are obtained, the method further includes: determining a feature vector mean based on the feature vector of the target vehicle corresponding to the image to be identified; and matching the feature vector mean with the query image to obtain the at least one matching image.

[0060] For example, when two images containing the target vehicle are acquired, these two images can be taken from different perspectives and at different times. The feature vectors corresponding to the target vehicle in the two images can be averaged to obtain a mean feature vector. This mean feature vector is then matched against the query image obtained in the previous step to obtain a matching image, thereby obtaining a more accurate and complete vehicle trajectory.

[0061] like Figure 3 The complete flow chart of the target vehicle trajectory tracking method of the present application is shown.

[0062] S201, first perform vehicle detection or vehicle head detection on the acquired image to be identified containing the target vehicle to obtain the specific location of the vehicle or the vehicle head, thereby extracting the target vehicle image or vehicle head image from the image to be identified. The target vehicle image will be used for explanation in subsequent steps.

[0063] S202: Extract features from the target vehicle image to obtain a feature vector of the target vehicle.

[0064] S203: Extract attributes of the target vehicle image to obtain attribute information of the target vehicle.

[0065] S204, obtaining other identity information of the target vehicle, such as the license plate number.

[0066] S205 , filtering the database using the time and location information of the image to be identified and other spatiotemporal information and the attribute information of the target vehicle, and matching the filtering results using the feature vector of the target vehicle to obtain a matching image.

[0067] S206 , clustering the matching image and the target vehicle image using a spatiotemporal clustering algorithm to obtain a vehicle trajectory.

[0068] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0069] Furthermore, the present invention also provides a target vehicle trajectory tracking device.

[0070] See attached Figure 4 , Figure 4 4 is a main structural block diagram of a target vehicle trajectory tracking device according to an embodiment of the present invention.

[0071] like Figure 4 As shown, the target vehicle trajectory tracking device in the embodiment of the present invention mainly includes an acquisition module 11, a detection module 12, a matching module 13 and a clustering module 14. In some embodiments, one or more of the acquisition module 11, the detection module 12, the matching module 13 and the clustering module 14 can be combined into one module.

[0072] In some embodiments, the acquisition module 11 may be configured to acquire an image to be identified that includes a target vehicle.

[0073] The detection module 12 may be configured to detect the image to be identified to obtain attribute information of the target vehicle, and to extract features from the image to be identified to obtain a feature vector of the target vehicle.

[0074] The matching module 13 may be configured to obtain at least one matching image that matches the attribute information and the feature vector.

[0075] The clustering module 14 may be configured to perform clustering based on the image to be recognized and the at least one matching image to obtain the vehicle trajectory of the target vehicle.

[0076] In one implementation, the description of specific implementation functions can refer to steps S101 to S104.

[0077] The target vehicle trajectory tracking device provided by the present application first obtains an image to be identified containing the target vehicle by an acquisition module. Then, the detection module detects the image to be identified to obtain attribute information of the target vehicle and extracts features from the image to be identified to obtain a feature vector of the target vehicle. Then, the matching module obtains at least one matching image that matches the attribute information and feature vector. Finally, the clustering module clusters the image to be identified and the at least one matching image to obtain the vehicle trajectory of the target vehicle. In this way, matching images that match the attribute information and feature vector of the target vehicle are obtained from a database, and then the image to be identified and the matching images are clustered to obtain a vehicle trajectory with high accuracy, thereby improving the accuracy of the vehicle trajectory and reducing errors.

[0078] The target vehicle trajectory tracking device is used to perform Figure 1 The target vehicle trajectory tracking method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the target vehicle trajectory tracking device can refer to the contents described in the embodiment of the target vehicle trajectory tracking method, and will not be repeated here.

[0079] Those skilled in the art will appreciate that all or part of the processes in the method for implementing the above-mentioned embodiment of the present invention may also be accomplished by instructing the relevant hardware through a computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, it may implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium capable of carrying the computer program code. It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0080] Furthermore, the present invention also provides an electronic device. In one embodiment of an electronic device according to the present invention, the electronic device includes a processor and a storage device. The storage device can be configured to store a program for executing the target vehicle trajectory tracking method of the above-mentioned method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to a program for executing the target vehicle trajectory tracking method of the above-mentioned method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiment of the present invention.

[0081] Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the trajectory tracking method of the target vehicle of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned trajectory tracking method of the target vehicle. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-transitory computer-readable storage medium.

[0082] Furthermore, it should be understood that since the configuration of each module is merely for the purpose of illustrating the functional units of the apparatus of the present invention, the physical devices corresponding to these modules may be the processor itself, or a portion of the software in the processor, a portion of the hardware, or a combination of software and hardware. Therefore, the number of modules in the figure is merely illustrative.

[0083] Those skilled in the art will appreciate that the various modules in the device can be adaptively split or merged. Such splitting or merging of specific modules does not cause the technical solution to deviate from the principles of the present invention. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of the present invention.

[0084] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A target vehicle trajectory tracking method, characterized in that: The method comprises: Acquire an image to be identified containing the target vehicle; Detecting the image to be identified to obtain attribute information of the target vehicle, and extracting features from the image to be identified to obtain a feature vector of the target vehicle, wherein the attribute information includes time information and position information corresponding to the image to be identified; Acquiring at least one matching image that matches the attribute information and the feature vector, including: querying a database using at least one of the time information, the location information, and the attribute information to obtain a query image; Matching the query image with the feature vector of the target vehicle to obtain the at least one matching image; Clustering is performed based on the image to be identified and the at least one matching image to obtain a vehicle trajectory of the target vehicle, including: determining a characteristic distance between the image to be recognized and the at least one matching image; Determining whether the characteristic distance meets a distance threshold; When the characteristic distance satisfies a distance threshold, determining the speed of the target vehicle based on the image to be identified and the at least one matching image, including: obtaining a specific shooting position and a specific shooting time of the image to be identified, and obtaining a specific shooting position and a specific shooting time of the at least one matching image, determining a shooting distance and a shooting time difference between the two, and obtaining the speed of the target vehicle based on the shooting distance and the shooting time difference; Determining whether the speed of the target vehicle meets a speed threshold; When the speed of the target vehicle meets a speed threshold, generating a vehicle trajectory of the target vehicle based on the image to be identified and the at least one matching image includes: arranging matching images that meet the conditions in a time series to obtain the trajectory of the target vehicle.

2. The target vehicle trajectory tracking method according to claim 1, characterized in that: Detecting the image to be identified to obtain attribute information of the target vehicle includes: inputting the image to be identified into a target detection model to obtain attribute information of the target vehicle, wherein the attribute information of the target vehicle includes at least one of vehicle color, direction, type, license plate number and license plate color.

3. The target vehicle trajectory tracking method according to claim 1, characterized in that: Determining a characteristic distance between the image to be recognized and the at least one matching image includes: Obtaining a feature vector of the at least one matching image; A feature distance between the image to be recognized and the at least one matching image is determined based on the feature vector of the target vehicle and the feature vector of the at least one matching image.

4. The target vehicle trajectory tracking method according to claim 1, characterized in that: Before detecting the image to be identified and obtaining the attribute information and feature vector of the target vehicle, the method further includes: Obtaining position information of the target vehicle in the image to be identified; A target vehicle image is acquired from the image to be identified based on the position information.

5. The target vehicle trajectory tracking method according to claim 1, characterized in that: When at least two images to be identified containing the target vehicle are acquired, the method further includes: Determining a feature vector mean based on a feature vector of a target vehicle corresponding to the image to be identified; The feature vector mean is used to match the query image to obtain the at least one matching image.

6. A target vehicle trajectory tracking device, characterized in that: The device comprises: An acquisition module is configured to acquire an image to be identified containing the target vehicle; a detection module configured to detect the image to be identified to obtain attribute information of the target vehicle, and to extract features from the image to be identified to obtain a feature vector of the target vehicle, wherein the attribute information includes time information and location information corresponding to the image to be identified; A matching module is configured to obtain at least one matching image that matches the attribute information and the feature vector, including: querying a database using at least one of the time information, the location information, and the attribute information to obtain a query image; Matching the query image with the feature vector of the target vehicle to obtain the at least one matching image; A clustering module is configured to perform clustering based on the image to be identified and the at least one matching image to obtain a vehicle trajectory of the target vehicle, including: determining a characteristic distance between the image to be recognized and the at least one matching image; Determining whether the characteristic distance meets a distance threshold; When the characteristic distance satisfies a distance threshold, determining the speed of the target vehicle based on the image to be identified and the at least one matching image, including: obtaining a specific shooting position and a specific shooting time of the image to be identified, and obtaining a specific shooting position and a specific shooting time of the at least one matching image, determining a shooting distance and a shooting time difference between the two, and obtaining the speed of the target vehicle based on the shooting distance and the shooting time difference; Determining whether the speed of the target vehicle meets a speed threshold; When the speed of the target vehicle meets a speed threshold, generating a vehicle trajectory of the target vehicle based on the image to be identified and the at least one matching image includes: arranging matching images that meet the conditions in a time series to obtain the trajectory of the target vehicle.

7. An electronic device comprising a processor and a storage device, wherein the storage device is adapted to store a plurality of program codes, wherein: The program code is suitable for being loaded and run by the processor to execute the target vehicle trajectory tracking method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the target vehicle trajectory tracking method according to any one of claims 1 to 5.

Images