Abnormal vehicle tracking method and system, electronic equipment and storage medium

Abstract

The invention provides an abnormal vehicle tracking method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring image data containing a vehicle in real time at a key place; identifying basic information of vehicles in the image data, and marking at least one target vehicle of which the basic information meets a first preset condition for the first time; the basic information comprises license plate information and access frequency of the vehicle; identifying structure information of the target vehicle in the image data, and when the structure information meets a second preset condition, marking the target vehicle for the second time; the structure information represents the appearance characteristics of the target vehicle; tracking the target vehicle according to a digital map, and obtaining a driving track path of the target vehicle; and judging whether the target vehicle is abnormal or not according to the driving track path so as to track the abnormal vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an abnormal vehicle tracking method, system, electronic device and storage medium. Background Art

[0002] Large archipelagoes are usually composed of thousands of islands, most of which are uninhabited, with complex geographical features and a large number of visual blind spots, making the area a potential high-risk area for illegal activities. Regulatory authorities face the dual challenges of tight human resources and high equipment costs. Traditional regulatory methods such as manual evidence collection, publicity and guidance, departmental collaboration, and equipment support have limited effects when facing highly concealed illegal activities.

[0003] The current regulatory technologies used include manual evidence collection, publicity and guidance, multi-department joint operations, and support from drones and monitoring equipment. However, these technologies have obvious problems. On the one hand, due to geographical complexity and visual blind spots, the coverage of drones and monitoring equipment is far from enough, making it difficult to detect and prevent illegal activities in a timely manner. On the other hand, although a large amount of vehicle and trajectory information is collected, there is a lack of in-depth use of big data and artificial intelligence for efficient analysis, resulting in inefficient supervision, long processing time and strong lag. Summary of the invention

[0004] The present disclosure provides an abnormal vehicle tracking method, system, electronic device and storage medium to at least solve the above technical problems existing in the prior art.

[0005] According to a first aspect of the present disclosure, a method for tracking an abnormal vehicle is provided, the method comprising:

[0006] Acquire image data containing vehicles in real time at key locations;

[0007] Identify basic information of the vehicle in the image data, and mark at least one target vehicle whose basic information meets a first preset condition for the first time; the basic information includes license plate information and entry and exit frequency of the vehicle;

[0008] Identify structural information of the target vehicle in the image data, and when the structural information meets a second preset condition, mark the target vehicle for a second time; the structural information represents the appearance characteristics of the target vehicle;

[0009] Tracking the target vehicle according to the digital map to obtain the driving trajectory of the target vehicle;

[0010] Whether the target vehicle is abnormal is determined according to the driving trajectory path, so as to track the abnormal vehicle.

[0011] In one possible implementation manner, identifying basic information of the vehicle in the image data and marking for the first time at least one target vehicle whose basic information meets a first preset condition includes:

[0012] Using OCR technology to identify the license plate information of the vehicle in the image data;

[0013] According to the license plate information, determine whether there are multiple vehicles from the same area, and record the frequency of entry and exit of each vehicle;

[0014] A density parameter is set, and when the entry and exit frequency does not meet the density parameter, at least one target vehicle is determined and the target vehicle is marked for the first time.

[0015] In one possible implementation manner, the identifying the structural information of the target vehicle in the image data, and marking the target vehicle for a second time when the structural information meets a second preset condition, includes:

[0016] Using a first recognition model to identify the vehicle type and load information of the target vehicle in the image data, and using a second recognition model to identify the structural features of the target vehicle in the image data to obtain the structural information;

[0017] When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural features of the target vehicle meet the vehicle structural features in the second preset condition, the target vehicle is marked for the second time.

[0018] In one possible implementation manner, the preset vehicle structural features include: the target vehicle is a semi-enclosed compartment covered by a tarpaulin, and there is a loading crane device on the vehicle.

[0019] In one possible implementation manner, judging whether the target vehicle is abnormal according to the driving trajectory path includes:

[0020] According to the driving trajectory path, when it is determined that the target vehicle has unified dispatch behavior information, and within the same target time period, at least one target vehicle moves in a unified manner from the stop, and its driving trajectory path touches the marked area, it is determined that the target vehicle has an abnormality.

[0021] According to a second aspect of the present disclosure, there is provided an abnormal vehicle tracking system, the system comprising:

[0022] An image acquisition unit, used for acquiring image data containing vehicles in real time at key locations;

[0023] A first marking unit, used to identify basic information of the vehicle in the image data, and to mark for the first time at least one target vehicle whose basic information meets a first preset condition; the basic information includes license plate information and entry and exit frequency of the vehicle;

[0024] a second marking unit, configured to identify structural information of the target vehicle in the image data, and to mark the target vehicle for a second time when the structural information meets a second preset condition; the structural information represents an appearance feature of the target vehicle;

[0025] A driving track acquisition unit, used for tracking the target vehicle according to a digital map and acquiring a driving track path of the target vehicle;

[0026] The tracking unit is used to determine whether the target vehicle is abnormal according to the driving trajectory path, so as to track the abnormal vehicle.

[0027] In one embodiment, the first marking unit is specifically used for:

[0028] Using OCR technology to identify the license plate information of the vehicle in the image data;

[0029] According to the license plate information, determine whether there are multiple vehicles from the same area, and record the frequency of entry and exit of each vehicle;

[0030] A density parameter is set, and when the entry and exit frequency does not meet the density parameter, at least one target vehicle is determined and the target vehicle is marked for the first time.

[0031] In one embodiment, the second marking unit is specifically used for:

[0032] Using a deep learning model to identify the vehicle type, load information, and structural features of the target vehicle in the image data to obtain the structural information;

[0033] When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural characteristics of the target vehicle meet the preset vehicle structural characteristics, the target vehicle is marked for the second time.

[0034] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0035] at least one processor; and

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.

[0038] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0039] The abnormal vehicle tracking method, system, electronic device and storage medium disclosed in the present invention obtains image data containing vehicles in real time, identifies the basic information of the vehicles in the images (such as license plate information and entry and exit frequency), and performs a first mark on the vehicles that meet the first preset conditions; secondly, further identifies the structural information of the target vehicle, and performs a second mark on the vehicles that meet the second preset conditions; then, uses digital maps and GPS positioning technology to track the driving trajectory of the target vehicle; finally, comprehensively judges whether the target vehicle has abnormal behavior based on the driving trajectory, and tracks the abnormal vehicle. In this way, the present invention not only realizes the accurate identification and real-time tracking of abnormal vehicles, is not limited by geographical complexity and visual blind spots, can achieve full coverage and efficient supervision of large archipelago areas, and effectively solves the problems of tight human resources and high equipment costs faced by regulatory authorities.

[0040] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0042] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0043] Figure 1 The schematic diagram shows the implementation process of the abnormal vehicle tracking method of the present disclosure. Figure 1 ;

[0044] Figure 2 The schematic diagram shows the implementation process of the abnormal vehicle tracking method of the present disclosure. Figure 2 ;

[0045] Figure 3 The schematic diagram shows the implementation process of the abnormal vehicle tracking method of the present disclosure. Figure 3 ;

[0046] Figure 4 A schematic diagram showing the structure of an abnormal vehicle tracking system according to an embodiment of the present disclosure is shown;

[0047] Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0049] The present disclosure provides a method for tracking abnormal vehicles. Figure 1 As shown, the method includes:

[0050] Step 101: Acquire image data containing vehicles at key locations in real time.

[0051] In this example, by installing high-definition cameras at major traffic arteries, highway intersections, border checkpoints or other key locations, image data of passing vehicles can be captured in real time. This image data is the basis for subsequent vehicle identification, tracking and abnormality judgment.

[0052] Step 102: Identify basic information of the vehicle in the image data, and perform a first mark on at least one target vehicle whose basic information meets a first preset condition; the basic information includes the vehicle's license plate information and entry and exit frequency.

[0053] In this example, advanced image recognition technology is used to extract the license plate information of the vehicles in the image and record the frequency of entry and exit of each vehicle. The license plate information is the key to identifying the identity of the vehicle, while the frequency of entry and exit reflects the flow of vehicles. When the basic information of one or several vehicles (such as license plate information, entry and exit frequency, etc.) meets the first preset condition, these vehicles will be regarded as potential target vehicles and marked for the first time.

[0054] Step 103: Identify the structural information of the target vehicle in the image data, and when the structural information meets the second preset condition, mark the target vehicle for the second time; the structural information represents the appearance characteristics of the target vehicle.

[0055] In this example, the structural information of the target vehicle in the image data is analyzed, such as the vehicle type, compartment shape, load characteristics, etc., which can usually reflect the function and purpose of the vehicle. When the structural information of the target vehicle meets the second preset condition (for example, the compartment shape is abnormal, the load is suspicious, etc.), these vehicles will be marked for the second time. The second marking means that these vehicles are more likely to be abnormal and need closer attention and tracking.

[0056] Step 104: Track the target vehicle according to the digital map to obtain the driving trajectory path of the target vehicle.

[0057] In this example, digital maps and GPS positioning technology are used to track the target vehicle's driving trajectory. The driving trajectory includes the vehicle's driving speed, driving direction, dwell time, and actual moving path. When the target vehicle frequently stays in a specific area or deviates from the regular driving route, it indicates abnormal behavior.

[0058] Step 105: Determine whether the target vehicle is abnormal based on the driving trajectory path, so as to track the abnormal vehicle.

[0059] In this example, based on the collected driving trajectory path, a comprehensive judgment is made as to whether the target vehicle has abnormal behavior. If the target vehicle's driving trajectory path matches the preset driving trajectory path pattern, or its driving behavior is significantly different from the normal driving behavior pattern (such as frequent night driving, speeding, etc.), the target vehicle is judged to be abnormal. Once the target vehicle is confirmed to be abnormal, the tracking program is immediately started to continuously monitor its location and driving conditions so that timely measures can be taken to intervene and deal with it.

[0060] The present disclosure provides a method for tracking abnormal vehicles, which obtains image data containing vehicles in real time, identifies the basic information of the vehicles in the image (such as license plate information and entry and exit frequency), and marks the vehicles that meet the first preset conditions for the first time; secondly, further identifies the structural information of the target vehicle, and marks the vehicles that meet the second preset conditions for the second time; then, uses digital maps and GPS positioning technology to track the driving trajectory of the target vehicle; finally, comprehensively judges whether the target vehicle has abnormal behavior based on the driving trajectory, and tracks the abnormal vehicle. In this way, the present disclosure not only realizes the accurate identification and real-time tracking of abnormal vehicles, is not limited by geographical complexity and visual blind spots, can achieve full coverage and efficient supervision of large archipelago areas, and effectively solves the problems of tight human resources and high equipment costs faced by regulatory authorities.

[0061] In one example, basic information of a vehicle in the image data is identified, and at least one target vehicle whose basic information meets a first preset condition is marked for the first time, such as Figure 2 As shown, including:

[0062] Step 201: Use OCR technology to identify the license plate information of vehicles in the image data.

[0063] In this example, Optical Character Recognition (OCR) technology is used to read the license plate information of vehicles in the image data. OCR technology can recognize the text information in the image and convert it into a computer-readable text format. In a vehicle tracking system, a camera is used to capture vehicle images, and then the letters and numbers on the license plate are recognized through an OCR algorithm. License plate information is an important identifier of vehicle identity. Based on the license plate information, vehicle registration information, owner information, etc. can be associated, providing key data for subsequent analysis and tracking.

[0064] Step 202: According to the license plate information, determine whether there are multiple vehicles from the same region, and record the entry and exit frequencies of each vehicle.

[0065] In this example, the license plate information is analyzed to determine whether there are multiple vehicles from the same region. By comparing the license plate information with a geographical database, the region code in the license plate can be identified (e.g., "Zhejiang B" represents Ningbo, Zhejiang, "Anhui C" represents Bengbu, Anhui, etc.). At the same time, the entry and exit frequencies of each vehicle will also be recorded, that is, the number of times a vehicle enters and exits within a certain period of time.

[0066] Step 203: Set a density parameter. When the entry and exit frequency does not meet the density parameter, determine at least one target vehicle and perform a first marking on the target vehicle.

[0067] In this example, the density parameter is set according to actual needs to define the "abnormal" entry and exit frequency. The density parameter involves multiple factors, such as the time window (e.g., "within xx minutes"), the region code (e.g., "vehicles from xx region"), and the frequency threshold (e.g., "more than xx times"). When it is detected that the entry and exit frequencies of one or several vehicles do not meet the preset density parameter, these vehicles will be regarded as potential target vehicles or target fleets and will be marked for the first time.

[0068] The marking methods include overlaying a marking box on the image and recording the marking information in the database, etc., for subsequent analysis and tracking to further determine whether these vehicles have abnormal behaviors.

[0069] In one example, identify the structural information of the target vehicle in the image data. When the structural information meets the second preset condition, perform a second marking on the target vehicle, such as Figure 3 shown, including:

[0070] Step 301: using a first recognition model to recognize the vehicle type and load information of a target vehicle in the image data, and using a second recognition model to recognize the structural features of the target vehicle in the image data to obtain structural information.

[0071] In this example, the initial deep learning model is trained with a training image set containing various types of trucks and their corresponding load information. This training set should include micro, medium, large, heavy, and extra-heavy trucks, and each type should contain multiple samples to ensure the generalization ability of the model. During the training process, the model will learn how to identify the type and load information of the vehicle based on the features in the image (such as vehicle size, number of tires, number of axles, etc.).

[0072] After obtaining the trained and optimized deep learning model, it is applied to the image data captured in the surveillance video stream. The first recognition model analyzes these images and identifies the type of target vehicle (such as micro, medium, large, etc.) and the corresponding load information (such as 2T, 6T, 10T, etc.).

[0073] Similarly, another deep learning model is trained using a training image set containing trucks with different structural features (such as fully enclosed, semi-enclosed with upper opening, semi-trailer flatbed, trailer truck, etc.). This model will learn how to identify the structural type of the vehicle based on the features in the image.

[0074] The trained second recognition model is applied to the same image data to identify the structural features of the target vehicle. This includes determining whether the vehicle is a semi-enclosed compartment, whether it is covered by a tarpaulin, and whether there is a crane.

[0075] Step 302: When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural characteristics of the target vehicle meet the vehicle structural characteristics in the second preset condition, the target vehicle is marked for the second time.

[0076] In this example, the preset vehicle weight range includes micro 2T, medium 6T, large 10T, heavy 20T, and super heavy 30T. Vehicle structure features: The preset structure features include fully enclosed, semi-enclosed with upper opening, semi-trailer flatbed, trailer, etc., and special attention is paid to whether the semi-enclosed truck with upper opening is covered by tarpaulin and whether there is a crane.

[0077] In step 301, the vehicle type, load information and structural features of the target vehicle are identified according to the first recognition model and the second recognition model, and compared with the preset second preset condition. If the vehicle type and load information of the target vehicle meet the preset weight range, and its structural features also meet the preset vehicle structural features (for example, it is a semi-enclosed truck with an upper opening, covered by a tarpaulin, or with a crane), the target vehicle is marked for the second time.

[0078] In one example, based on the driving trajectory path, when it is determined that the target vehicle has unified scheduling behavior information, and within the same target time period, at least one target vehicle moves in a unified manner from the stop, and its driving trajectory path touches the marked area, it is determined that the target vehicle has an abnormality.

[0079] In this example, based on the driving trajectory paths of multiple target vehicles, it is determined whether they have unified scheduling behavior. Specifically, based on the trajectory paths of the target vehicles, it is determined whether they have the following behavior information:

[0080] (1) When multiple target vehicles start from point A1 and then stop at point B1;

[0081] (2) When multiple target vehicles start from point A1 and stop at different points (B1, B2, B3…), but each stop position is very close (the average coordinate of the threshold is set to no more than x kilometers);

[0082] (3) When multiple target vehicles exit the station from different points (A1, A2, A3…), are there multiple vehicles that eventually stop at point B1, or different points (B1, B2, B3…), but each location is very close (the threshold average coordinate is set to no more than x kilometers).

[0083] According to the behavior information corresponding to the trajectory path of the above target vehicle, the license plate information and time data labels are used to calculate the path similarity, stop density, etc., which can be used as conditions for determining whether the target vehicle or target fleet has abnormal behavior.

[0084] The marking principle of marking areas in the entire digital map is that normal freight loading and unloading areas are generally located in the commercial areas, agricultural areas, factories or legal seaports of the entire city. Therefore, if the target vehicle's driving trajectory is determined to be heading to an unmanned area or unmanned port or an area with a very low density of target vehicle driving trajectories, and the trajectory disappears, the abnormal vehicles can be marked by combining the first two parts of data and the collected target vehicle's driving trajectory data and the digital map warning area. At the same time, a time dimension is added to provide more accurate screening. Whether it is a single target vehicle or a target fleet, its abnormal behavior generally occurs in the early morning. If more target vehicles appear at the same time and act in unison from the stop, and the driving trajectory touches the above-marked warning area, these target vehicles will be judged as abnormal vehicles.

[0085] The present disclosure also provides an abnormal vehicle tracking system, such as Figure 4 As shown, the system includes:

[0086] An image acquisition unit 401 is used to acquire image data containing vehicles in real time at key locations;

[0087] The first marking unit 402 is used to identify basic information of the vehicle in the image data, and to mark at least one target vehicle whose basic information meets the first preset condition for the first time; the basic information includes the license plate information and the frequency of entry and exit of the vehicle;

[0088] The second marking unit 403 is used to identify the structural information of the target vehicle in the image data, and to mark the target vehicle for the second time when the structural information meets the second preset condition; the structural information represents the appearance characteristics of the target vehicle;

[0089] The driving track acquisition unit 404 is used to track the target vehicle according to the digital map and acquire the driving track path of the target vehicle;

[0090] The tracking unit 405 is used to determine whether the target vehicle is abnormal according to the driving trajectory path, so as to track the abnormal vehicle.

[0091] In one example, the first marking unit 402 is specifically configured to:

[0092] Use OCR technology to identify the vehicle license plate information in the image data;

[0093] Based on the license plate information, determine whether there are multiple vehicles from the same area, and record the frequency of entry and exit of each vehicle;

[0094] Set density parameters. When the entry and exit frequency does not meet the density parameters, determine at least one target vehicle and mark the target vehicle for the first time.

[0095] In one example, the second marking unit 403 is specifically configured to:

[0096] Use the deep learning model to identify the vehicle type, load information and structural features of the target vehicle in the image data to obtain structural information;

[0097] When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural characteristics of the target vehicle meet the preset vehicle structural characteristics, the target vehicle is marked for the second time.

[0098] In one example, the preset vehicle structural features include: the target vehicle is a semi-enclosed compartment covered by a tarpaulin, and there is a loading crane device on the vehicle.

[0099] In one example, the tracking unit 405 is specifically configured to:

[0100] According to the driving trajectory path, when it is determined that the target vehicle has unified dispatch behavior information, and within the same target time period, at least one target vehicle moves in a unified manner from the stop, and its driving trajectory path touches the marked area, it is determined that the target vehicle has an abnormality.

[0101] In addition, the abnormal vehicle tracking system stores monitoring data from different locations in a unified database, and digitally restores the behavioral trajectory characteristics of vehicles or fleets with abnormal behaviors. At the same time, a customized vertical large model is imported into the abnormal vehicle tracking system, including multi-modal training such as image recognition and trajectory recognition, which can not only continuously improve accuracy in the future, but also provide intelligent assistant applications in vertical fields. When the vehicle leaves the city, the load quantity will also be recorded to confirm whether it is loading and unloading goods but the data is not collected.

[0102] The entire information collection of the abnormal vehicle tracking system is tracked with vehicles as the main body, and intelligent screening is performed through multiple rounds of abnormal marking. The screening adjustment price and threshold can be adjusted manually in the integrated tracking system. The abnormal vehicle tracking system integrates daily data and then uses a large model for training to achieve higher accuracy, which is used to feed back to relevant agencies for key inspection recommendations and early warnings.

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0104] Figure 5A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0105] like Figure 5 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0106] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as an abnormal vehicle tracking method. For example, in some embodiments, the abnormal vehicle tracking method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the abnormal vehicle tracking method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the abnormal vehicle tracking method in any other appropriate manner (e.g., by means of firmware).

[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0113] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0115] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0116] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An abnormal vehicle tracking method, characterized in that: The method comprises: Acquire image data containing vehicles in real time at key locations; Identify basic information of the vehicle in the image data, and mark for the first time at least one target vehicle whose basic information meets a first preset condition; the basic information includes license plate information and entry and exit frequency of the vehicle; Identify structural information of the target vehicle in the image data, and when the structural information meets a second preset condition, mark the target vehicle for a second time; the structural information represents the appearance characteristics of the target vehicle; Tracking the target vehicle according to the digital map to obtain the driving trajectory of the target vehicle; Whether the target vehicle is abnormal is determined according to the driving trajectory path, so as to track the abnormal vehicle.

2. The method according to claim 1, characterized in that The identifying basic information of the vehicle in the image data and marking for the first time at least one target vehicle whose basic information meets the first preset condition includes: Using OCR technology to identify the license plate information of the vehicle in the image data; According to the license plate information, determine whether there are multiple vehicles from the same area, and record the frequency of entry and exit of each vehicle; A density parameter is set, and when the entry and exit frequency does not meet the density parameter, at least one target vehicle is determined and the target vehicle is marked for the first time.

3. The method according to claim 1, characterized in that The identifying the structural information of the target vehicle in the image data, and marking the target vehicle for a second time when the structural information meets a second preset condition, comprises: Using a first recognition model to identify the vehicle type and load information of the target vehicle in the image data, and using a second recognition model to identify the structural features of the target vehicle in the image data to obtain the structural information; When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural features of the target vehicle meet the vehicle structural features in the second preset condition, the target vehicle is marked for the second time.

4. The method according to claim 3, characterized in that The preset vehicle structural features include: the target vehicle is a semi-enclosed compartment covered by a tarpaulin, and there is a loading crane device on the vehicle.

5. The method according to claim 1, characterized in that The determining whether the target vehicle is abnormal according to the driving trajectory path includes: According to the driving trajectory path, when it is determined that the target vehicle has unified dispatch behavior information, and within the same target time period, at least one target vehicle moves in a unified manner from the stop, and its driving trajectory path touches the marked area, it is determined that the target vehicle has an abnormality.

6. An abnormal vehicle tracking system, characterized in that: The system comprises: An image acquisition unit, used for acquiring image data containing vehicles in real time at key locations; A first marking unit, used to identify basic information of the vehicle in the image data, and to mark for the first time at least one target vehicle whose basic information meets a first preset condition; the basic information includes license plate information and entry and exit frequency of the vehicle; a second marking unit, configured to identify structural information of the target vehicle in the image data, and to mark the target vehicle for a second time when the structural information meets a second preset condition; the structural information represents an appearance feature of the target vehicle; A driving track acquisition unit, used for tracking the target vehicle according to a digital map and acquiring a driving track path of the target vehicle; The tracking unit is used to determine whether the target vehicle is abnormal according to the driving trajectory path, so as to track the abnormal vehicle.

7. The system according to claim 6, characterized in that The first marking unit is specifically used for: Using OCR technology to identify the license plate information of the vehicle in the image data; According to the license plate information, determine whether there are multiple vehicles from the same area, and record the frequency of entry and exit of each vehicle; A density parameter is set, and when the entry and exit frequency does not meet the density parameter, at least one target vehicle is determined and the target vehicle is marked for the first time.

8. The method according to claim 6, characterized in that The second marking unit is specifically used for: Using a deep learning model to identify the vehicle type, load information, and structural features of the target vehicle in the image data to obtain the structural information; When the vehicle type and load information of the target vehicle meet the vehicle weight range preset in the second preset condition, and the structural characteristics of the target vehicle meet the preset vehicle structural characteristics, the target vehicle is marked for the second time.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

Images