Tunnel vehicle positioning method and system

Abstract

The invention discloses a tunnel vehicle positioning method and system, and the method comprises the steps: carrying out the time and space binding of a vehicle picture and license plate information of each vehicle at a tunnel entrance, carrying out the feature extraction of the vehicle pictures of all vehicles, and obtaining a picture feature set; collecting a vehicle picture of each vehicle in the tunnel to obtain a first feature vector of each vehicle, obtaining a picture feature set at the same time, and screening out a candidate feature set from the picture feature set by using a space-time constraint relationship; and performing similarity matching calculation on the first feature vector and feature vectors in the candidate feature set to obtain a second feature vector with the highest matching degree which exceeds a preset threshold value, and binding the first feature vector and the second feature vector to obtain positioning information of all vehicles at the tunnel entrance when driving into the tunnel. According to the technical scheme of the embodiment of the invention, real-time positioning and continuous tracking can be carried out on the tunnel vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicle positioning technology, and specifically to a method and system for locating vehicles in tunnels. Background Technology

[0002] With the rapid development of highways, tunnels, as an important transportation infrastructure, directly affect the overall level of traffic safety management through their operational safety and monitoring capabilities.

[0003] Currently, traditional technologies suffer from problems such as insufficient vehicle positioning capabilities in tunnels, poor tracking continuity, and insufficient real-time performance. Summary of the Invention

[0004] This invention provides a method and system for locating vehicles in tunnels, enabling full-process positioning and simulation monitoring of vehicles inside tunnels.

[0005] In a first aspect, the present invention provides a method for locating vehicles in a tunnel, comprising:

[0006] At the tunnel entrance, vehicle images of all vehicles are collected and license plate information of all vehicles is identified. The vehicle images and license plate information of each vehicle are then linked in terms of time and space. Feature extraction is performed on the vehicle images of all vehicles to obtain a set of image features.

[0007] Inside the tunnel, vehicle images of each vehicle are collected, and features are extracted from each vehicle image to obtain the first feature vector of each vehicle. The image feature set is obtained, and a candidate feature set is selected from the image feature set using spatiotemporal constraints.

[0008] The first feature vector is matched with the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds the preset threshold. By binding the first feature vector and the second feature vector, the positioning information of all vehicles at the tunnel entrance when they drive into the tunnel is obtained.

[0009] Furthermore, the step of binding vehicle images and license plate information of each vehicle in terms of time and space includes:

[0010] Video information of vehicles entering the tunnel is collected by video acquisition equipment set up at the tunnel entrance. When a vehicle passes the capture point, the capture time, vehicle type, lane and vehicle image are recorded.

[0011] The license plate recognition equipment installed at the tunnel entrance identifies the license plate information of vehicles entering the tunnel. When a vehicle passes the recognition calibration point, the recognition time, vehicle type, lane and license plate information are recorded.

[0012] By capturing the time point, recognizing the time point, vehicle type, and lane, the system matches vehicle images with license plate information for each vehicle.

[0013] Furthermore, the step of using spatiotemporal constraints to filter candidate feature sets from image feature sets includes:

[0014] Video information of vehicles entering the tunnel is collected by video acquisition equipment installed inside the tunnel. When a vehicle passes the capture point, the capture time, vehicle type, lane and vehicle image are recorded.

[0015] Based on the distance between the collection point at the tunnel entrance and the collection point inside the tunnel, and the speed range of any vehicle, the travel time range of any vehicle from the tunnel entrance to the inside of the tunnel is obtained.

[0016] Based on the capture time of any vehicle inside the tunnel and the travel time range of any vehicle, feature vectors that conflict with the time of any vehicle are removed from the image feature set.

[0017] Based on the lane to which any vehicle belongs as recorded inside the tunnel, feature vectors that spatially conflict with that vehicle are removed from the image feature set.

[0018] Furthermore, multiple points are set inside the tunnel. When each vehicle travels from the tunnel entrance to the first point inside the tunnel, the positioning information of all vehicles at the tunnel entrance when they travel to the first point inside the tunnel is obtained. At the first point, the first feature vector of each vehicle is updated to the image feature set, and the updated image feature set is passed to the next point after the first point.

[0019] Furthermore, when each vehicle travels from any point inside the tunnel to the next point, the image feature set at that point and the first feature vector of each vehicle at the next point are obtained. The first feature vector of each vehicle is then updated in the image feature set at the next point, and the updated image feature set is then passed to the next point after that point.

[0020] Furthermore, after updating the first feature vector of each vehicle to the image feature set at any given point, the process also includes:

[0021] The updated set of image features, vehicle models, vehicle images, and license plate information are used to construct vehicle identity record information.

[0022] The vehicle identification record information is transmitted to the next point after the given point.

[0023] Furthermore, during the similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set, if the matching degree between all feature vectors in the candidate feature set and the first feature vector does not exceed a preset threshold, then the next frame of vehicle images is switched, and the first feature vector is extracted again.

[0024] Secondly, the present invention provides a tunnel vehicle positioning system, comprising:

[0025] The information binding unit is used to collect vehicle images of all vehicles at the tunnel entrance and identify the license plate information of all vehicles. It binds the vehicle images and license plate information of each vehicle in terms of time and space. It also extracts features from the vehicle images of all vehicles to obtain a set of image features.

[0026] The information filtering unit is used to collect vehicle images of each vehicle inside the tunnel, extract features from each vehicle image to obtain the first feature vector of each vehicle, obtain the image feature set, and filter the candidate feature set from the image feature set using spatiotemporal constraints.

[0027] The information matching unit is used to perform similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds a preset threshold; by binding the first feature vector and the second feature vector, the positioning information of all vehicles at the tunnel entrance when driving into the tunnel is obtained.

[0028] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0029] At least one processor; and a memory communicatively connected to the at least one processor;

[0030] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the steps of the method according to any embodiment of the present invention.

[0031] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of a method according to any embodiment of the present invention.

[0032] Compared with the prior art, the present invention has the following advantages:

[0033] The technical solution in this embodiment of the invention first binds vehicle images and license plate information of each vehicle in terms of time and space at the tunnel entrance, and establishes an image feature set; then, inside the tunnel, it matches the first feature vector of each vehicle with the feature vector in the image feature set; finally, it binds the feature vector in the image feature set that has the highest matching degree with the first feature vector to the first feature vector to obtain the vehicle's positioning information. Through the technical solution in this embodiment, real-time positioning and continuous tracking of vehicles in the tunnel can be achieved. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only preferred embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a flowchart illustrating a tunnel vehicle positioning method provided in an embodiment of the present invention.

[0036] Figure 2 This is a schematic diagram of information transmission for an edge detection device A at a tunnel entrance, provided in an embodiment of the present invention.

[0037] Figure 3 This is a schematic diagram of information transmission for an edge detection device B inside a tunnel, provided in an embodiment of the present invention.

[0038] Figure 4 This is a schematic diagram illustrating the information transmission of an edge detection device A at a tunnel entrance, as provided in another embodiment of the present invention.

[0039] Figure 5 This is a schematic diagram of information transmission for another edge detection device B inside a tunnel provided in an embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of the structure of a tunnel vehicle positioning system provided in an embodiment of the present invention;

[0041] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Before introducing the technical solution of this application, it should be noted that the following health solutions for tunnel vehicles exist in the existing technical solutions:

[0044] 1) Install cameras inside the tunnel to monitor vehicle traffic in real time. However, this solution relies on manual observation or background video playback and lacks automated vehicle identification and continuous tracking capabilities.

[0045] 2) Deploy RFID tags or ETC systems inside the tunnel to collect vehicle passage information. However, this solution requires vehicles to carry specialized equipment, and it is not possible to achieve continuous and accurate tracking of vehicle locations inside the tunnel.

[0046] 3) Vehicle information is collected at the tunnel entrance using license plate recognition equipment, combined with cameras to record traffic. However, this solution can only obtain the time and information of vehicles entering the tunnel, and it is difficult to continuously track the movement trajectory of vehicles inside the tunnel.

[0047] In summary, existing solutions cannot accurately locate the real-time position of vehicles inside tunnels. Furthermore, due to insufficient lighting and limited video coverage in tunnel environments, it is difficult to achieve uninterrupted tracking of vehicles throughout the entire process. In addition, the data analysis process requires data to be transmitted to a central platform for centralized processing, resulting in high latency and insufficient real-time performance. Therefore, these solutions are not suitable for scenarios like tunnels where safety and real-time performance are extremely important.

[0048] Figure 1 This is a flowchart illustrating a tunnel vehicle positioning method provided in an embodiment of the present invention. This embodiment is particularly applicable to scenarios such as highway tunnels and urban tunnels. The method can be executed by a tunnel vehicle positioning system, which can be implemented in software and / or hardware and can be configured in an electronic device.

[0049] like Figure 1 As shown, the method specifically includes:

[0050] S1. Collect vehicle images of all vehicles at the tunnel entrance and identify the license plate information of all vehicles. Bind the vehicle images and license plate information of each vehicle in terms of time and space. Extract features from the vehicle images of all vehicles to obtain a set of image features.

[0051] Specifically, video capture equipment at the tunnel entrance captures images of all vehicles, license plate recognition equipment at the tunnel entrance captures license plate information of all vehicles, and edge detection equipment at the tunnel entrance acquires images of all vehicles and license plate information of all vehicles. The images of each vehicle and the license plate information are then linked in time and space. Feature extraction is performed on the linked images of all vehicles to obtain an image feature set.

[0052] Among them, the edge detection device uses communication protocols to access video acquisition devices and license plate recognition devices. The edge detection device also has edge computing capabilities and computing power cards, which can load intelligent algorithm models such as vehicle target recognition, vehicle target tracking and vehicle feature extraction to realize edge data analysis.

[0053] In some embodiments, vehicle images and license plate information for each vehicle are bound together in terms of time and space, specifically as follows:

[0054] S1011 uses video capture equipment at the tunnel entrance to collect video information of vehicles entering the tunnel. When a vehicle passes the capture point, the capture time, vehicle type, lane, and vehicle image are recorded.

[0055] S1012 uses license plate recognition equipment at the tunnel entrance to identify the license plate information of vehicles entering the tunnel. When a vehicle passes the recognition calibration point, the recognition time, vehicle type, lane and license plate information are recorded.

[0056] S1013 matches vehicle images and license plate information for each vehicle by capturing the time point, recognizing the time point, vehicle type, and lane.

[0057] The video capture equipment can be a network HD camera with video capture capabilities, and the license plate recognition equipment can be a license plate recognition camera. License plate recognition cameras are widely used in scenarios such as parking lot entrances and exits, highway toll stations, and urban traffic monitoring. A license plate recognition camera can be deployed at the tunnel entrance to identify vehicle type and license plate information; simultaneously, a network HD camera can be deployed at the tunnel entrance, pointing directly at the license plate recognition camera, to capture video information of vehicles entering the tunnel.

[0058] Figure 2 This is a schematic diagram of information transmission for an edge detection device A at a tunnel entrance, provided in an embodiment of the present invention. Figure 2 As shown, the edge detection device at the tunnel entrance is denoted as edge intelligent detection device A, and the edge detection device inside the tunnel is denoted as edge intelligent detection device B. Firstly, edge intelligent detection device A receives structured data collected by the license plate recognition device and video streams collected by network high-definition cameras. Secondly, edge intelligent detection device A binds vehicle images and license plate information to each vehicle in terms of time and space. Thirdly, edge intelligent detection device A uploads the vehicle's location or trajectory to the upper-level monitoring platform. Fourthly, edge intelligent detection device A transmits image feature sets to the downstream edge intelligent detection device B.

[0059] S2. Collect vehicle images of each vehicle inside the tunnel, extract features from each vehicle image to obtain the first feature vector of each vehicle; obtain the image feature set, and use spatiotemporal constraints to filter out the candidate feature set from the image feature set.

[0060] Specifically, vehicle images of each vehicle are captured by video acquisition equipment inside the tunnel. The edge detection equipment B inside the tunnel extracts features from the vehicle images of each vehicle to obtain the first feature vector of each vehicle. The edge detection equipment B inside the tunnel obtains the image feature set constructed by the edge detection equipment A at the tunnel entrance, and uses spatiotemporal constraints to filter out the candidate feature set from the image feature set.

[0061] Figure 3 This is a schematic diagram of information transmission for an edge detection device B inside a tunnel, provided in an embodiment of the present invention. Figure 3 As shown, the edge detection device at the tunnel entrance is denoted as edge intelligent detection device A, and the edge detection device inside the tunnel is denoted as edge intelligent detection device B. Firstly, edge intelligent detection device B acquires the video stream captured by the video acquisition device inside the tunnel, as well as the image feature set constructed or updated by the upstream edge intelligent detection device (the upstream device can be either the device at the tunnel entrance or the device inside the tunnel). Secondly, edge intelligent detection device B captures the first feature vector of each vehicle. Thirdly, edge intelligent detection device B performs spatiotemporal constraint-based feature matching between the first feature vector of each vehicle and the feature vectors in the image feature set, and updates the image feature set after a successful match, transmitting it to the downstream edge intelligent detection device (the downstream device is the device inside the tunnel). Fourthly, edge intelligent detection device B uploads the vehicle's position or trajectory to the upper-level monitoring platform.

[0062] It should be noted that one or more network HD cameras can be deployed inside the tunnel to collect video information; simultaneously, one or more edge intelligent detection devices can be deployed inside the tunnel for data analysis and edge computing. One network HD camera can correspond to one edge intelligent detection device. For example, when multiple devices are set up, one network HD camera and one edge intelligent detection device can be placed every 150 meters.

[0063] In some embodiments, a candidate feature set is selected from the image feature set using spatiotemporal constraints, including:

[0064] S2011 uses video capture equipment installed inside the tunnel to collect video information of vehicles entering the tunnel. When a vehicle passes the capture point, the capture time, vehicle type, lane, and vehicle image are recorded.

[0065] S2012, Based on the distance between the collection point at the tunnel entrance and the collection point inside the tunnel, and the speed range of any vehicle, the travel time range of any vehicle from the tunnel entrance to the inside of the tunnel is obtained.

[0066] S2013, based on the capture time point recorded by any vehicle inside the tunnel and the travel time range of any vehicle, remove the feature vectors that conflict with the time of any vehicle from the image feature set.

[0067] S2014: Based on the lane to which any vehicle belongs as recorded inside the tunnel, remove feature vectors from the image feature set that have spatial conflicts with that vehicle.

[0068] It is understandable that when the video capture equipment at the tunnel entrance captures multiple vehicles at the same time, and when any target vehicle drives into the tunnel, it cannot be accurately located due to interference from other vehicles. Based on this, vehicles can be screened according to spatiotemporal constraints to reduce the computational load for subsequent similarity matching calculations, and finally accurately complete the real-time positioning and continuous tracking of the target vehicle.

[0069] In some embodiments, multiple points are set inside the tunnel. When each vehicle travels from the tunnel entrance to the first point inside the tunnel, the positioning information of all vehicles at the tunnel entrance when they travel to the first point inside the tunnel is obtained. At the first point, the first feature vector of each vehicle is updated to the image feature set, and the updated image feature set is passed to the next point after the first point.

[0070] It should be noted that the edge detection device at the first location is upstream of the edge detection device at the tunnel entrance.

[0071] Figure 4 This is a schematic diagram of information transmission for another edge detection device A at a tunnel entrance provided in an embodiment of the present invention, as shown below. Figure 4 As shown, when multiple points are set up inside the tunnel, one video acquisition device and one edge detection device are set up for each point. Taking the first point as an example, the edge detection device at the tunnel entrance is denoted as edge intelligent detection device A, and the edge detection device at the first point is denoted as edge intelligent detection device B1.

[0072] Edge intelligent detection device A binds the vehicle images and license plate information of each vehicle in terms of time and space, and extracts features from the vehicle images of all vehicles to obtain an image feature set. At the same time, edge intelligent detection device A can also construct vehicle identity record information by combining the image feature set, vehicle license plate, vehicle model, and vehicle image, and transmit the image feature set or vehicle identity record information to the downstream edge intelligent detection device B1.

[0073] Understandably, the edge detection device at any point needs to match the feature vectors of each captured vehicle with the image feature set passed from the previous point, update the image feature set, and then pass the updated image feature set to the next point.

[0074] In some embodiments, when each vehicle travels from any point inside the tunnel to the next point, an image feature set at the any point and a first feature vector of each vehicle at the next point are obtained, and the first feature vector of each vehicle is updated to the image feature set at the next point. The updated image feature set is then passed to the next point after the next point.

[0075] Figure 5 This is a schematic diagram illustrating the information transmission of another edge detection device B inside a tunnel, as provided in an embodiment of the present invention. Figure 5 As shown, when multiple points are set up inside the tunnel, one video acquisition device and one edge detection device are set up for each point. Taking the nth point as an example, the edge detection device at the nth point is denoted as edge intelligent detection device Bn, the edge detection device at its upstream point is denoted as edge intelligent detection device B(n-1), and the edge detection device at its downstream point is denoted as edge intelligent detection device B(n+1).

[0076] Edge intelligent detection device Bn acquires the image feature set constructed by edge intelligent detection device B(n-1). Simultaneously, it obtains the first feature vector for each vehicle using video information captured by the video acquisition device at the nth location. It then calculates cosine similarity to determine if a second feature vector exists in the image feature set. If it exists, the first feature vector is updated in the image feature set, replacing the second feature vector, and the updated image feature set is uploaded to the platform and edge intelligent detection device B(n+1). If it does not exist, the system switches to the next frame containing vehicle images and re-extracts the first feature vector.

[0077] In some embodiments, after updating the first feature vector of each vehicle to the image feature set at any point, the method further includes:

[0078] S2021, the updated set of image features, vehicle model of each vehicle, vehicle image of each vehicle, and license plate information of each vehicle are used to construct vehicle identity record information.

[0079] S2022, transmits vehicle identification record information to the next point after the given point.

[0080] S3, perform similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds the preset threshold; by binding the first feature vector and the second feature vector, obtain the positioning information of all vehicles at the tunnel entrance when they drive into the tunnel.

[0081] In some embodiments, during the process of performing similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set, if the matching degree between all feature vectors in the candidate feature set and the first feature vector does not exceed a preset threshold, then the vehicle images of each vehicle in the next frame are switched, and the first feature vector is extracted again.

[0082] Understandably, at any point inside the tunnel, multiple vehicle images are captured simultaneously. If the feature vector matching of the current vehicle image is unsatisfactory, the vehicle image is switched. If none of the vehicle images meet the matching requirements, the matching of that vehicle at that point is abandoned, and the capture time is marked to provide detailed information for matching that vehicle at subsequent points.

[0083] The technical solution in this invention binds vehicle feature vectors to vehicle information at the tunnel entrance, and extracts feature vectors of each vehicle inside the tunnel to match them with the feature vectors at the tunnel entrance, thus achieving vehicle positioning within the tunnel. During the matching process, high-precision vehicle matching is achieved based on spatiotemporal constraints and cosine similarity calculations, while also obtaining the positioning information of each vehicle as it travels from the tunnel entrance to the tunnel interior. Furthermore, by setting multiple points inside the tunnel and employing relay matching with distributed edge intelligent detection devices, continuous vehicle positioning and tracking within the tunnel are achieved. Simultaneously, combining license plate information, vehicle type, captured images, and feature binding information at the tunnel entrance enhances the accuracy of vehicle recognition and feature matching. Utilizing the characteristics of edge computing for local video processing significantly reduces data transmission latency, ensuring real-time tunnel monitoring.

[0084] Based on the same inventive concept Figure 6 This is a schematic diagram of a tunnel vehicle positioning system provided in an embodiment of the present invention, as shown below. Figure 6 As shown, the system specifically includes:

[0085] The information binding unit 100 is used to collect vehicle images of all vehicles at the tunnel entrance and identify the license plate information of all vehicles. It binds the vehicle images and license plate information of each vehicle in terms of time and space. It also extracts features from the vehicle images of all vehicles to obtain an image feature set.

[0086] The information filtering unit 200 is used to collect vehicle images of each vehicle inside the tunnel, extract features from the vehicle images of each vehicle to obtain the first feature vector of each vehicle, obtain the image feature set, and filter the candidate feature set from the image feature set using spatiotemporal constraints.

[0087] The information matching unit 300 is used to perform similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds a preset threshold; by binding the first feature vector and the second feature vector, the positioning information of all vehicles at the tunnel entrance when driving into the tunnel is obtained.

[0088] Based on the same inventive concept Figure 7 This is a schematic diagram of the structure of an electronic device that implements the tunnel vehicle positioning method according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, 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 processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0089] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0090] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0091] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as tunnel vehicle positioning methods.

[0092] In some embodiments, the tunnel vehicle positioning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the tunnel vehicle positioning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the tunnel vehicle positioning method by any other suitable means (e.g., by means of firmware).

[0093] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0095] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0096] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0097] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0098] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0099] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0100] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for locating vehicles in a tunnel, characterized in that, include: At the tunnel entrance, images of all vehicles are collected and license plate information of all vehicles is identified. The images of each vehicle and the license plate information are then linked in terms of time and space. Feature extraction is performed on the vehicle images of all vehicles to obtain an image feature set; Inside the tunnel, vehicle images of each vehicle are collected, and features are extracted from each vehicle image to obtain the first feature vector of each vehicle. The image feature set is obtained, and a candidate feature set is selected from the image feature set using spatiotemporal constraints. The first feature vector is matched with the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds the preset threshold. By binding the first feature vector and the second feature vector, the positioning information of all vehicles at the tunnel entrance when they drive into the tunnel is obtained.

2. The method according to claim 1, characterized in that, The process of binding vehicle images and license plate information to each vehicle in terms of time and space includes: Video information of vehicles entering the tunnel is collected by video acquisition equipment set up at the tunnel entrance. When a vehicle passes the capture point, the capture time, vehicle type, lane and vehicle image are recorded. The license plate recognition equipment installed at the tunnel entrance identifies the license plate information of vehicles entering the tunnel. When a vehicle passes the recognition calibration point, the recognition time, vehicle type, lane and license plate information are recorded. By capturing the time point, recognizing the time point, vehicle type, and lane, the system matches vehicle images with license plate information for each vehicle.

3. The method according to claim 1, characterized in that, The process of selecting a candidate feature set from the image feature set using spatiotemporal constraints includes: Video information of vehicles entering the tunnel is collected by video acquisition equipment installed inside the tunnel. When a vehicle passes the capture point, the capture time, vehicle type, lane and vehicle image are recorded. Based on the distance between the collection point at the tunnel entrance and the collection point inside the tunnel, and the speed range of any vehicle, the travel time range of any vehicle from the tunnel entrance to the inside of the tunnel is obtained. Based on the capture time of any vehicle inside the tunnel and the travel time range of any vehicle, feature vectors that conflict with the time of any vehicle are removed from the image feature set. Based on the lane to which any vehicle belongs as recorded inside the tunnel, feature vectors that spatially conflict with that vehicle are removed from the image feature set.

4. The method according to claim 1, characterized in that, Also includes: Multiple points are set inside the tunnel. When each vehicle travels from the tunnel entrance to the first point inside the tunnel, the positioning information of all vehicles at the tunnel entrance when they travel to the first point inside the tunnel is obtained. At the first point, the first feature vector of each vehicle is updated to the image feature set, and the updated image feature set is passed to the next point after the first point.

5. The method according to claim 4, characterized in that, Also includes: When each vehicle travels from any point inside the tunnel to the next point, the image feature set at that point and the first feature vector of each vehicle at the next point are obtained. The first feature vector of each vehicle is then updated in the image feature set at the next point, and the updated image feature set is then passed to the next point after that point.

6. The method according to claim 4 or 5, characterized in that, After updating the first feature vector of each vehicle to the image feature set at any given point, the process also includes: The updated set of image features, vehicle models, vehicle images, and license plate information are used to construct vehicle identity record information. The vehicle identification record information is transmitted to the next point after the given point.

7. The method according to claim 1, characterized in that, During the process of calculating the similarity between the first feature vector and the feature vectors in the candidate feature set, if the matching degree between all feature vectors in the candidate feature set and the first feature vector does not exceed the preset threshold, then switch to the next frame of vehicle images for each vehicle and re-extract the first feature vector.

8. A tunnel vehicle positioning system, characterized in that, The system is configured to implement the method according to any one of claims 1-7, the system comprising: The information binding unit is used to collect vehicle images of all vehicles at the tunnel entrance and identify the license plate information of all vehicles. It binds the vehicle images and license plate information of each vehicle in terms of time and space. It also extracts features from the vehicle images of all vehicles to obtain a set of image features. The information filtering unit is used to collect vehicle images of each vehicle inside the tunnel, extract features from each vehicle image to obtain the first feature vector of each vehicle, obtain the image feature set, and filter the candidate feature set from the image feature set using spatiotemporal constraints. The information matching unit is used to perform similarity matching calculation between the first feature vector and the feature vectors in the candidate feature set to obtain the second feature vector in the candidate feature set that has the highest matching degree with the first feature vector and whose matching degree exceeds a preset threshold; by binding the first feature vector and the second feature vector, the positioning information of all vehicles at the tunnel entrance when driving into the tunnel is obtained.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to perform the steps of the method according to any one of claims 1-7.

Images