Green channel vehicle tracking method and system

Abstract

The invention provides a green channel vehicle tracking method and system, and the method comprises the steps: obtaining a pre-judgment result at an entrance portal, and judging whether a vehicle is a green channel vehicle or not according to the pre-judgment result; if the vehicle is a green channel vehicle, constructing a vehicle label of the vehicle; in the vehicle driving process, the vehicle is monitored based on the roadside equipment, and whether the driving position of the vehicle is recorded corresponding to the vehicle label or not is judged based on the vehicle label; determining a driving path of the vehicle based on the driving positions of the vehicle at the plurality of time points, and determining a confidence coefficient of the driving path based on a pre-trained neural network model; and judging whether to carry out secondary detection on the vehicle based on the confidence coefficient. According to the scheme, the driving path of the vehicle is determined through the driving positions of the vehicle at the multiple time points, the path is analyzed through the pre-trained neural network model, the confidence degree of the vehicle to the green channel vehicle is judged, secondary detection is conducted on the vehicle with the low confidence degree, and whether the vehicle is the green channel vehicle or not is judged.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle supervision, and in particular to a green pass vehicle tracking method and system. Background Art

[0002] Green Channel vehicles are vehicles that use the green channel to transport fresh agricultural products. Green Channel vehicles carry the important task of ensuring the basic needs of the people and promoting the effective connection between agriculture and the market economy.

[0003] First of all, green-pass vehicles are responsible for the transportation of fresh agricultural products, which are directly related to the daily life and dietary health of the people. Effective supervision can ensure the freshness and safety of agricultural products during transportation. Green-pass supervision is also a necessary measure to optimize the allocation of transportation resources and improve logistics efficiency. With the rapid development of the logistics industry, the number of green-pass vehicles is increasing, and the demand for transportation resources is also growing. Through scientific and reasonable supervision, transportation routes can be reasonably planned, traffic congestion and energy consumption can be reduced, logistics efficiency can be improved, and logistics costs can be reduced.

[0004] In summary, supervision of green-pass vehicles is an inevitable requirement for ensuring food safety, promoting agricultural development, optimizing transportation resource allocation, and improving logistics efficiency. Only by strengthening supervision can we ensure the healthy and orderly operation of green-pass vehicles and make greater contributions to economic and social development. However, existing green-pass vehicles are usually supervised manually and lack automated supervision methods. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a green pass vehicle tracking method to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present invention provides a green pass vehicle tracking method, the method comprising the steps of:

[0007] Obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle;

[0008] If the vehicle is a green pass vehicle, construct the vehicle label of the vehicle;

[0009] During the driving process of the vehicle, the vehicle is monitored based on the roadside equipment, and the driving position of the vehicle is determined based on the vehicle tag whether to record the corresponding vehicle tag;

[0010] Determining a driving path of the vehicle based on the driving positions of the vehicle at multiple time points, and determining the confidence of the driving path based on a pre-trained neural network model;

[0011] Based on the confidence level, it is determined whether to perform a secondary inspection on the vehicle.

[0012] The above scheme is adopted. This scheme makes a preliminary judgment at the entrance gantry. If it is preliminarily judged to be a green pass vehicle, the vehicle is monitored. The vehicle is monitored based on roadside equipment, the vehicle's driving position is recorded, and the vehicle's driving path is determined by the vehicle's driving position at multiple time points. The path is analyzed by a pre-trained neural network model to determine the confidence of the vehicle for a green pass vehicle. For vehicles with lower confidence, a secondary inspection is performed to determine whether the vehicle is a green pass vehicle. On the one hand, it can realize the path supervision of green pass vehicles, and on the other hand, it can also prevent some vehicles from impersonating green pass vehicles.

[0013] In some embodiments of the present invention, in the step of obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle, the entrance gantry obtains vehicle information of the vehicle and searches a preset vehicle database to determine whether the vehicle is a green pass vehicle.

[0014] In some embodiments of the present invention, vehicle information of a vehicle is obtained at an entrance gantry, and a search is performed in a preset vehicle database to determine whether the vehicle is a green pass vehicle. The on-board unit loaded on the vehicle interacts with the entrance gantry to obtain vehicle information or capture an image of the vehicle through the entrance gantry to identify the vehicle's license plate number, and the license plate number is used as the vehicle information.

[0015] In some embodiments of the present invention, if the vehicle is a green pass vehicle, in the step of constructing a vehicle tag for the vehicle, an on-board unit loaded on the vehicle interacts with the entrance gantry to obtain vehicle information recorded in the on-board unit and construct a vehicle tag, wherein the vehicle tag includes the license plate number of the vehicle.

[0016] In some embodiments of the present invention, during vehicle driving, the vehicle is monitored based on roadside equipment, and in the step of determining whether a corresponding vehicle tag records the vehicle's driving position based on the vehicle tag, the roadside equipment interacts with an on-board unit loaded on the vehicle to obtain vehicle information or take a vehicle image through the roadside equipment, identify the vehicle's license plate number, use the license plate number as vehicle information, match the corresponding vehicle tag based on the vehicle information, and add the current position of the roadside equipment in the vehicle tag as the vehicle's driving position.

[0017] In some embodiments of the present invention, in the step of determining the driving path of the vehicle based on the driving positions of the vehicle at multiple time points, the multiple driving positions are connected based on the sequence of the time points to obtain the driving path of the vehicle.

[0018] In some embodiments of the present invention, in the step of determining the confidence of the driving path based on a pre-trained neural network model, the vehicle's driving path is marked on a preset path map, a path vector of the vehicle is constructed based on the path points passed by the vehicle in the path map, and the path vector is input into the pre-trained neural network model to determine the confidence of the driving path.

[0019] In some embodiments of the present invention, in the step of constructing a path vector of the vehicle based on the path points passed by the vehicle in the path map, the coordinate data of the path points are used as values ​​of each dimension in the path vector to construct the path vector of the vehicle.

[0020] In some embodiments of the present invention, in the step of determining whether to perform a secondary inspection on the vehicle based on the confidence level, if the confidence level is lower than a preset confidence threshold, then the vehicle is determined to perform a secondary inspection; if the confidence level is not lower than the preset confidence threshold, then the vehicle is determined not to perform a secondary inspection.

[0021] The second aspect of the present invention also provides a green pass vehicle tracking system, which includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0022] The third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned green pass vehicle tracking method.

[0023] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention can be specifically pointed out and obtained in the specification and the accompanying drawings.

[0024] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0026] Figure 1 A schematic diagram of an implementation method of the green pass vehicle tracking method of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0028] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0029] like Figure 1 As shown, the present invention proposes a green pass vehicle tracking method, the steps of the method comprising:

[0030] Step S100, obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle;

[0031] During the specific implementation process, the entrance gantry can be an ETC gantry.

[0032] In a specific implementation process, a plurality of gantries are arranged on the road on which the vehicle travels, the entrance gantry is the first gantry through which the vehicle enters the road, and the entrance gantry may be any one of the plurality of gantries.

[0033] During the specific implementation process, the entrance gantry is provided with a camera and a roadside unit (RSU). The camera is connected to the RSU to collect images and transmit the images to the RSU. The RSU interacts with an on-board unit (OBU) arranged on the vehicle.

[0034] In the specific implementation process, OBU (On-Board Unit): vehicle-mounted unit, installed on vehicles, used to communicate with RSU, obtain traffic information, provide location services, etc. In ETC (Electronic Toll Collection System), OBU is a key device for identifying vehicles, recording traffic information, sending and receiving data, and processing transactions.

[0035] RSU (Roadside Unit): Roadside unit, installed beside the road or on a gantry, used to communicate with OBUs, collect traffic information, control traffic lights, etc. It is a communication device deployed along the road, capable of receiving and sending wireless signals and communicating with passing vehicles in real time.

[0036] The interaction between OBU and RSU is mainly carried out in the following two ways:

[0037] Internet of Vehicles Communications:

[0038] With the help of mobile communication networks such as 4G and 5G, communication between OBU and RSU is achieved. The on-board equipment is connected to the mobile communication network through a SIM card and communicates with the RSU through the Internet. This communication method has high speed and reliability and is suitable for long-distance communication.

[0039] Radio Frequency Communications:

[0040] OBU and RSU communicate via radio signals, independent of mobile communication networks, and can use technologies such as Bluetooth, Wi-Fi, and DSRC (Dedicated Short-Range Communications) for communication. This communication method is suitable for short-range communication and has a lower transmission rate but higher real-time performance.

[0041] Step S200, if the vehicle is a green pass vehicle, construct a vehicle tag for the vehicle;

[0042] In the specific implementation process, if the vehicle is not a green pass vehicle, it does not need to be supervised and there is no need to construct a vehicle label for the vehicle.

[0043] Step S300, during the driving process of the vehicle, monitoring the vehicle based on the roadside equipment, and determining whether the corresponding vehicle tag records the driving position of the vehicle based on the vehicle tag;

[0044] In some embodiments of the present invention, the roadside equipment is installed on one side of the road, and the roadside equipment includes a camera and a roadside unit. The camera is connected to the RSU to collect images and transmit the images to the RSU. The RSU interacts with an on-board unit (OBU, On-Board Unit) set in the vehicle.

[0045] Step S400, determining a driving path of the vehicle based on the driving positions of the vehicle at multiple time points, and determining the confidence of the driving path based on a pre-trained neural network model;

[0046] In the specific implementation process, the roadside device matches the vehicle tag by collecting the image of the vehicle, identifying the license plate number, or directly interacting with the vehicle's on-board unit (OBU, On-Board Unit) through the RSU to obtain vehicle information. If the match is successful, the current position of the roadside device is recorded as the vehicle's driving position, and the vehicle's driving path is constructed based on the multiple recorded driving positions.

[0047] In the specific implementation process, the pre-trained neural network model is a classification neural network using a softmax function and a cross entropy loss function;

[0048] Specifically, the neural network model includes an input layer, at least one hidden layer and an output layer;

[0049] Input layer: receives input vector.

[0050] Hidden layers: Each hidden layer has multiple neurons and uses ReLU or other activation functions.

[0051] Output layer: contains 10 neurons (corresponding to 10 digital categories) and uses the softmax function as the activation function.

[0052] The cross entropy loss function is used to train the neural network model to evaluate the difference between the probability distribution predicted by the model and the true label. During the training process, minimizing the cross entropy loss function can improve the prediction accuracy of the model and indirectly reflect the confidence of the model. The smaller the cross entropy loss, the higher the confidence of the model in the prediction result.

[0053] During the prediction phase, the neural network outputs the probability of each category. This solution can select the category with the highest probability as the prediction result and directly output the probability as the confidence. For example, if the model's output probability is [0.01, 0.02, 0.03, 0.9, 0.01, 0.01, 0.01, 0.001, 0.001, 0.001], the model predicts the number "3" (assuming the index starts at 0) and the confidence is 0.9.

[0054] Step S500: determining whether to perform a secondary inspection on the vehicle based on the confidence level.

[0055] In the specific implementation process, when determining whether to conduct a secondary inspection on the vehicle based on the confidence level, if the vehicle needs a secondary inspection, a notification is sent to each exit gantry. The staff at the vehicle entrance gantry conducts a manual inspection of the vehicle when the vehicle exits the road, and uses the inspection results and the vehicle's driving path as training data to train the neural network model.

[0056] In the specific implementation process, this solution uses AI image recognition computing technology to recognize license plates, and converts recognition images and entrance and exit lane snapshots into vehicle feature structured data.

[0057] The above scheme is adopted. This scheme makes a preliminary judgment at the entrance gantry. If it is preliminarily judged to be a green pass vehicle, the vehicle is monitored. The vehicle is monitored based on roadside equipment, the vehicle's driving position is recorded, and the vehicle's driving path is determined by the vehicle's driving position at multiple time points. The path is analyzed by a pre-trained neural network model to determine the confidence of the vehicle for a green pass vehicle. For vehicles with lower confidence, a secondary inspection is performed to determine whether the vehicle is a green pass vehicle. On the one hand, it can realize the path supervision of green pass vehicles, and on the other hand, it can also prevent some vehicles from impersonating green pass vehicles.

[0058] In some embodiments of the present invention, in the step of obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle, the entrance gantry obtains vehicle information of the vehicle and searches a preset vehicle database to determine whether the vehicle is a green pass vehicle.

[0059] In some embodiments of the present invention, vehicle information of a vehicle is obtained at an entrance gantry, and a search is performed in a preset vehicle database to determine whether the vehicle is a green pass vehicle. The on-board unit loaded on the vehicle interacts with the entrance gantry to obtain vehicle information or capture an image of the vehicle through the entrance gantry to identify the vehicle's license plate number, and the license plate number is used as the vehicle information.

[0060] In the specific implementation process, the vehicle information includes information such as the vehicle's license plate, axle, vehicle model and cargo box type.

[0061] In some embodiments of the present invention, if the vehicle is a green pass vehicle, in the step of constructing a vehicle tag for the vehicle, an on-board unit loaded on the vehicle interacts with the entrance gantry to obtain vehicle information recorded in the on-board unit and construct a vehicle tag, wherein the vehicle tag includes the license plate number of the vehicle.

[0062] In a specific implementation process, the vehicle label also includes the vehicle model.

[0063] In some embodiments of the present invention, during vehicle driving, the vehicle is monitored based on roadside equipment, and in the step of determining whether a corresponding vehicle tag records the vehicle's driving position based on the vehicle tag, the roadside equipment interacts with an on-board unit loaded on the vehicle to obtain vehicle information or take a vehicle image through the roadside equipment, identify the vehicle's license plate number, use the license plate number as vehicle information, match the corresponding vehicle tag based on the vehicle information, and add the current position of the roadside equipment in the vehicle tag as the vehicle's driving position.

[0064] In a specific implementation process, each roadside device pre-records data for indicating the position of the road test device. The data for indicating the position of the road test device may be coordinates or a serial number of the road test device.

[0065] In some embodiments of the present invention, in the step of determining the driving path of the vehicle based on the driving positions of the vehicle at multiple time points, the multiple driving positions are connected based on the sequence of the time points to obtain the driving path of the vehicle.

[0066] In some embodiments of the present invention, in the step of determining the confidence of the driving path based on a pre-trained neural network model, the vehicle's driving path is marked on a preset path map, a path vector of the vehicle is constructed based on the path points passed by the vehicle in the path map, and the path vector is input into the pre-trained neural network model to determine the confidence of the driving path.

[0067] In the specific implementation process, the route map is a map drawn based on the actual road location, and multiple route points are marked in the route map. The route points are pre-marked location points of the marked road, such as road forks or the starting and ending points of the road speed limit intervals.

[0068] By adopting the above scheme, in the process of constructing the path vector, the path points of the area covered by the vehicle's driving path in the preset path map are determined, rather than directly constructing the vehicle's driving position as a path vector. On the one hand, there are many driving positions of the vehicle, and the amount of data of the path vector finally constructed is large, which is inefficient in the subsequent judgment process; on the other hand, the scheme pre-sets path points that have the function of identifying roads, and by determining the path points of the area covered by the vehicle's driving path in the preset path map, the data in the generated path vector can be more representative, and the vehicle's driving path can be more accurately represented, thereby improving the accuracy of subsequent judgments.

[0069] In some embodiments of the present invention, in the step of constructing a path vector of the vehicle based on the path points passed by the vehicle in the path map, the coordinate data of the path points are used as values ​​of each dimension in the path vector to construct the path vector of the vehicle.

[0070] In some embodiments of the present invention, in the step of determining whether to perform a secondary inspection on the vehicle based on the confidence level, if the confidence level is lower than a preset confidence threshold, then the vehicle is determined to perform a secondary inspection; if the confidence level is not lower than the preset confidence threshold, then the vehicle is determined not to perform a secondary inspection.

[0071] By adopting the above scheme, this scheme can make a secondary judgment on vehicles with low confidence, ensure the authenticity of green pass vehicles, and improve the degree of supervision.

[0072] This solution is based on the collection of ETC transaction data, video data and radar data to establish vehicle portraits, and assist in the construction of a green pass prediction model based on the vehicle portrait library. Through the green pass vehicle portrait, the characteristics of less inspection, no omissions and continuous optimization are achieved, the accuracy of green pass vehicle assessment is improved, and the road traffic efficiency and the processing efficiency of the inspection personnel are improved.

[0073] The beneficial effects of this program include:

[0074] 1. This solution makes a preliminary judgment at the entrance gantry. If it is initially determined to be a green pass vehicle, the vehicle is monitored. The vehicle is monitored based on roadside equipment, the vehicle's driving position is recorded, and the vehicle's driving path is determined by the vehicle's driving position at multiple time points. The path is analyzed by a pre-trained neural network model to determine the confidence of the vehicle for a green pass vehicle. For vehicles with low confidence, a secondary inspection is performed to determine whether the vehicle is a green pass vehicle. On the one hand, it can realize the path supervision of green pass vehicles, and on the other hand, it can also prevent some vehicles from pretending to be green pass vehicles;

[0075] 2. This solution can conduct a secondary assessment of vehicles with low confidence levels, ensuring the authenticity of green pass vehicles and improving the degree of supervision;

[0076] 3. In the process of constructing the path vector, this solution determines the path points of the area covered by the vehicle's driving path in the preset path map, rather than directly constructing the vehicle's driving position as the path vector. On the one hand, there are many driving positions of the vehicle, and the amount of data of the path vector finally constructed is large, which is inefficient in the subsequent determination process; on the other hand, this solution pre-sets the path points that have the function of identifying the road, and by determining the path points of the area covered by the vehicle's driving path in the preset path map, the data in the generated path vector can be more representative, and the vehicle's driving path can be more accurately represented, thereby improving the accuracy of subsequent determinations;

[0077] 4. Based on historical data and real-time incremental data, establish and update the green pass vehicle portrait library, including: license plate, axle, vehicle model, container type and historical traffic records, etc.;

[0078] 5. Build a green pass vehicle confidence prediction model based on the vehicle portrait library to make real-time predictions on the green pass vehicle confidence;

[0079] 6. Radar and vision integrated verification: For vehicles with low confidence in the model output, the vehicle is verified based on the gantry data and the radar and vision integrated equipment;

[0080] 7. Track restoration: For non-green pass vehicles after verification, track restoration is performed based on gantry big data and video acquisition data, and the chain of evidence is output;

[0081] 8. Model iteration: Update the vehicle portrait library based on the confidence prediction of green pass vehicles and vehicle inspection results, and optimize the iterative prediction model.

[0082] An embodiment of the present invention also provides a green pass vehicle tracking system, which includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0083] The embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps implemented by the aforementioned green pass vehicle tracking method are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0084] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0085] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0086] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A green pass vehicle tracking method, characterized in that: The steps of the method include: Obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle; If the vehicle is a green pass vehicle, construct the vehicle label of the vehicle; During the driving process of the vehicle, the vehicle is monitored based on the roadside equipment, and the driving position of the vehicle is determined based on the vehicle tag whether to record the corresponding vehicle tag; Determining a driving path of the vehicle based on the driving positions of the vehicle at multiple time points, and determining the confidence of the driving path based on a pre-trained neural network model; Based on the confidence level, it is determined whether to perform a secondary inspection on the vehicle.

2. The green pass vehicle tracking method according to claim 1, characterized in that: In the step of obtaining a pre-determination result at the entrance gantry, wherein the pre-determination result determines whether the vehicle is a green pass vehicle, the entrance gantry obtains vehicle information of the vehicle and searches in a preset vehicle database to determine whether the vehicle is a green pass vehicle.

3. The green pass vehicle tracking method according to claim 2, characterized in that: In the step of obtaining vehicle information of the vehicle at the entrance gantry and searching in a preset vehicle database to determine whether the vehicle is a green pass vehicle, the on-board unit loaded on the vehicle interacts with the entrance gantry to obtain vehicle information or capture an image of the vehicle through the entrance gantry to identify the vehicle's license plate number and use the license plate number as the vehicle information.

4. The green pass vehicle tracking method according to claim 1, characterized in that: If the vehicle is a green pass vehicle, in the step of constructing a vehicle tag for the vehicle, the on-board unit loaded on the vehicle interacts with the entrance gantry to obtain the vehicle information recorded in the on-board unit and construct it into a vehicle tag, wherein the vehicle tag includes the license plate number of the vehicle.

5. The green pass vehicle tracking method according to claim 1, characterized in that: During the driving process of the vehicle, in the step of monitoring the vehicle based on the roadside equipment and determining whether the corresponding vehicle tag records the driving position of the vehicle based on the vehicle tag, the roadside equipment interacts with the on-board unit loaded on the vehicle to obtain vehicle information or take a vehicle image through the roadside equipment, recognize the vehicle license plate number, use the license plate number as the vehicle information, match the corresponding vehicle tag based on the vehicle information, and add the current position of the roadside equipment in the vehicle tag as the driving position of the vehicle.

6. The green pass vehicle tracking method according to claim 1, characterized in that: In the step of determining the driving path of the vehicle based on the driving positions of the vehicle at multiple time points, the multiple driving positions are connected based on the sequence of the time points to obtain the driving path of the vehicle.

7. The green pass vehicle tracking method according to any one of claims 1 to 6, characterized in that: In the step of determining the confidence of the driving path based on a pre-trained neural network model, the vehicle's driving path is marked on a preset path map, a path vector of the vehicle is constructed based on the path points passed by the vehicle in the path map, and the path vector is input into the pre-trained neural network model to determine the confidence of the driving path.

8. The green pass vehicle tracking method according to claim 7, characterized in that: In the step of constructing a path vector of the vehicle based on the path points passed by the vehicle in the path map, the coordinate data of the path points are used as the values ​​of each dimension in the path vector to construct the path vector of the vehicle.

9. The green pass vehicle tracking method according to claim 1, characterized in that: In the step of determining whether to perform a secondary inspection on the vehicle based on the confidence level, if the confidence level is lower than a preset confidence threshold, it is determined that the vehicle is to be subjected to a secondary inspection; if the confidence level is not lower than the preset confidence threshold, it is determined that the vehicle is not to be subjected to a secondary inspection.

10. A green pass vehicle tracking system, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 9.

Images