A vehicle path restoration method and device

Abstract

The present invention provides a method and device for restoring a vehicle path. The method includes: obtaining independent ETC transaction information and / or independent vehicle feature information sent by a plurality of ETC gantry device clusters, performing feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to a target vehicle; determining the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle, which can solve the problem in the related art that there is a deviation between the recorded path and the actual driving path due to the failure of reading the in-vehicle medium. By determining vehicle feature information through vehicle images, and based on the vehicle feature information, gantry identification, and the time of collecting the vehicle image (i.e., the capture time), the driving path of the vehicle is determined, improving the accuracy of the vehicle driving path.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular, to a vehicle path restoration method and device. Background Art

[0002] Intelligent Transportation System (ITS) brings convenience to traffic travel through intelligent devices, which is the development trend of China's transportation industry. After years of development, fruitful results have been achieved. In 2019, ETC was vigorously promoted across the country, and the installation rate of OBU reached more than 80%. At the same time, at the end of 2019, the provincial boundary toll stations on national highways were cancelled, and an ETC free-flow gantry system was installed on the sections before each entrance and exit of highways to achieve segmented billing, contributing to alleviating congestion at provincial boundary stations and reducing logistics costs.

[0003] Currently, most vehicles traveling on highways have installed OBU. Some vehicles without OBU will receive a CPC card with the vehicle license plate number written on it at the toll station entrance. OBU and CPC are collectively referred to as on-vehicle media. When a vehicle carrying on-vehicle media passes through a free-flow gantry, it will communicate wirelessly with the gantry device RSU, and the passing information and toll amount will be written into the card. At the toll station exit, the passing information and toll amount stored in the on-vehicle media (ETC automatic or manual) are read for charging, that is, the current toll collection system only relies on the passing information recorded in the on-vehicle media for charging.

[0004] However, in related technologies, there is a certain phenomenon of missed reading of on-vehicle media by the roadside unit RSU. In addition, if the vehicle owner actively or inadvertently blocks the on-vehicle media signal, removes the OBU card or the card falls off, it will cause a deviation between the driving path recorded in the on-vehicle media and the actual path.

[0005] A solution has not been proposed for the problem in related technologies that the recorded path deviates from the actual driving path due to the failure of reading the on-vehicle media. Summary of the Invention

[0006] Embodiments of the present invention provide a vehicle path restoration method and device to at least solve the problem in related technologies that the recorded path deviates from the actual driving path due to the failure of reading the on-vehicle media.

[0007] According to an embodiment of the present invention, a vehicle path restoration method is provided, including:

[0008] Obtain independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters, where the vehicle feature information is determined by the multiple ETC gantry device clusters based on vehicle images passing through the ETC gantries;

[0009] Perform feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0010] Determine the driving route of the target vehicle based on the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0011] Optionally, performing feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle includes:

[0012] Bind the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain binding information, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship;

[0013] Perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0014] Optionally, binding the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain the binding information includes:

[0015] Match the ETC transaction information and the vehicle feature information with the same ETC gantry identifier;

[0016] If the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information with the same ETC gantry identifier is less than a preset time threshold, and the number of identical characters in the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, determine that the match is successful and obtain the binding information.

[0017] Optionally, performing feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle includes:

[0018] Receive the binding information of the same target vehicle with a binding relationship sent by the multiple ETC gantry device clusters, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship.

[0019] Perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0020] Optionally, performing feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle includes:

[0021] Match the ETC transaction information in the binding information and / or the independent ETC transaction information;

[0022] Match the vehicle feature information in the binding information and / or the independent vehicle feature information;

[0023] Determine all the ETC transaction information and all the vehicle feature information of the target vehicle with successful matching as the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0024] Optionally, matching the ETC transaction information in the binding information and / or the independent ETC transaction information includes:

[0025] Perform license plate number matching between the ETC transaction information in the binding information and the independent ETC transaction information, perform license plate number matching between the ETC transaction information in the binding information, and perform license plate number matching between the independent ETC transaction information;

[0026] If the license plate numbers are the same, the matching is successful;

[0027] If the license plate numbers are different, the matching fails.

[0028] Optionally, matching the vehicle feature information in the binding information and / or the independent vehicle feature information includes:

[0029] Respectively determine the similarity between the vehicle feature information in the binding information and the independent vehicle feature information, between the vehicle feature information in the binding information, and between the independent vehicle feature information;

[0030] Obtain the maximum similarity;

[0031] If the maximum similarity is greater than or equal to the second preset threshold, it is determined that the vehicle feature information corresponding to the maximum similarity is successfully matched;

[0032] If the maximum similarity value is less than the second preset threshold, it is determined that the vehicle feature information corresponding to the maximum similarity is failed to be matched.

[0033] Optionally, determining the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle includes:

[0034] Determining the target position information corresponding to the ETC gantry identifier carried in the ETC transaction information and the vehicle feature information corresponding to the target vehicle according to the corresponding relationship between the pre-stored ETC gantry identifier and the position information;

[0035] Determining the driving path of the target vehicle according to the target position information.

[0036] Optionally, the vehicle feature information includes: license plate number, vehicle color, vehicle type, roof skylight shape, interior hanging ornaments, windshield annual inspection mark;

[0037] The ETC transaction information includes an ETC gantry identifier, a transaction time, and a license plate number.

[0038] According to another embodiment of the present invention, there is also provided a vehicle path restoration method, including:

[0039] Obtaining a vehicle image passing through an ETC gantry, and determining vehicle feature information according to the vehicle image;

[0040] Obtaining ETC transaction information;

[0041] Sending independent ETC transaction information and / or independent vehicle feature information to a server, wherein the independent ETC transaction information and the independent vehicle feature information are used for the server to perform feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used for the server to determine the driving path of the target vehicle.

[0042] Optionally, the method further includes:

[0043] Matching the ETC transaction information and the vehicle feature information;

[0044] If the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters in the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, it is determined that the matching is successful, and binding information is obtained, where the binding information includes the ETC transaction information and the vehicle feature information having a binding relationship;

[0045] Send the binding information to the server, where the server is used to perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0046] Optionally, the obtaining of the vehicle image passing through the ETC gantry includes:

[0047] Receiving the vehicle video passing through the ETC gantry collected by the camera, and capturing the vehicle image from the vehicle video or extracting a frame of the image from the vehicle video as the vehicle image; or

[0048] Receiving the vehicle image captured by the camera passing through the ETC gantry.

[0049] According to another embodiment of the present invention, there is also provided a vehicle path restoration device, including:

[0050] A first obtaining module, configured to obtain independent ETC transaction information and / or independent vehicle feature information sent by a plurality of ETC gantry device clusters, where the vehicle feature information is determined by the plurality of ETC gantry device clusters according to the vehicle image passing through the ETC gantry;

[0051] A feature matching module, configured to perform feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0052] A first determining module, configured to determine the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0053] Optionally, the feature matching module includes:

[0054] A binding sub-module, configured to bind the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain binding information, where the binding information includes the ETC transaction information and the vehicle feature information having a binding relationship;

[0055] A feature matching sub-module, configured to perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information, so as to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0056] Optionally, the binding sub-module includes:

[0057] A first matching unit, configured to match the ETC transaction information and the vehicle feature information with the same ETC gantry identifier;

[0058] A first determination unit, configured to determine that the matching is successful and obtain the binding information if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information with the same ETC gantry identifier is less than a preset time threshold, and the number of identical characters between the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold.

[0059] Optionally, the feature matching module includes:

[0060] A receiving sub-module, configured to receive the binding information of the same target vehicle with a binding relationship sent by the multiple ETC gantry device clusters, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship;

[0061] A feature matching sub-module, configured to perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information, so as to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0062] Optionally, the feature matching sub-module includes:

[0063] A second matching unit, configured to match the ETC transaction information in the binding information and / or the independent ETC transaction information;

[0064] A third matching unit, configured to match the vehicle feature information in the binding information and / or the independent vehicle feature information;

[0065] A second determination unit, configured to determine all the ETC transaction information and all the vehicle feature information of the target vehicle with successful matching as the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0066] Optionally, the second matching unit is further configured to

[0067] Perform license plate number matching between the ETC transaction information in the binding information and the independent ETC transaction information, perform license plate number matching between the ETC transaction information in the binding information, and perform license plate number matching between the independent ETC transaction information;

[0068] In the case where the license plate numbers are the same, the matching is successful;

[0069] In the case where the license plate numbers are different, the matching fails.

[0070] Optionally, the third matching unit is further configured to

[0071] Determine the similarity between the vehicle feature information in the binding information and the independent vehicle feature information, between the vehicle feature information in the binding information, and between the independent vehicle feature information respectively;

[0072] Obtain the maximum similarity;

[0073] If the maximum similarity is greater than or equal to a second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity is successfully matched;

[0074] If the maximum similarity value is less than the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity is failed to be matched.

[0075] Optionally, the first determining module includes:

[0076] A first determining sub-module, configured to determine the target position information corresponding to the ETC transaction information of the target vehicle and the ETC gantry identifier carried in the vehicle feature information according to the corresponding relationship between the pre-stored ETC gantry identifier and the position information;

[0077] A second determining sub-module, configured to determine the driving path of the target vehicle according to the target position information.

[0078] Optionally, the vehicle feature information includes: license plate number, vehicle color, vehicle type, roof skylight shape, in-vehicle pendant, windshield annual inspection mark;

[0079] The ETC transaction information includes an ETC gantry identifier, a transaction time, and a license plate number.

[0080] According to another embodiment of the present invention, there is also provided a vehicle path restoration device, including:

[0081] A second acquisition module, configured to acquire an image of a vehicle passing through an ETC gantry, and determine vehicle feature information according to the vehicle image;

[0082] A third acquisition module, configured to acquire ETC transaction information;

[0083] A first sending module, configured to send independent ETC transaction information and / or independent vehicle feature information to a server, wherein the independent ETC transaction information and the independent vehicle feature information are used by the server to perform feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to a target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving route of the target vehicle.

[0084] Optionally, the device further includes:

[0085] A matching module, configured to match the ETC transaction information and the vehicle feature information;

[0086] A second determination module, configured to determine that the matching is successful and obtain binding information if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters between the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, wherein the binding information includes the ETC transaction information and the vehicle feature information having a binding relationship;

[0087] A second sending module, configured to send the binding information to the server, wherein the server is configured to perform feature matching according to the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0088] Optionally, the second acquisition module includes:

[0089] A first receiving sub-module, configured to receive a vehicle video of a vehicle passing through the ETC gantry collected by a camera, and capture the vehicle image from the vehicle video or extract a frame of the image from the vehicle video as the vehicle image; or

[0090] A second receiving sub-module, configured to receive the vehicle image of the vehicle passing through the ETC gantry captured by the camera.

[0091] According to another embodiment of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0092] According to another embodiment of the present invention, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0093] Through the present invention, independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters are obtained, and feature matching is performed based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle; the driving route of the target vehicle is determined according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle, which can solve the problem in the related art that the recorded route deviates from the actual driving route due to the failure of in-vehicle media reading. By determining vehicle feature information through vehicle images and determining the vehicle driving route based on the vehicle feature information and the ETC transaction information, the accuracy of the vehicle driving route is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0095] Figure 1 is a hardware structure block diagram of a mobile terminal for the vehicle route restoration method according to an embodiment of the present invention;

[0096] Figure 2 is a flowchart of the vehicle route restoration method according to an embodiment of the present invention Figure 1 ;

[0097] Figure 3 is a flowchart of the vehicle route restoration method according to an embodiment of the present invention Figure 2 ;

[0098] Figure 4 is a schematic diagram of a highway vehicle route restoration system according to an embodiment of the present invention;

[0099] Figure 5 is a block diagram of the vehicle route restoration device according to an embodiment of the present invention Figure 1 ;

[0100] Figure 6 is a block diagram of the vehicle route restoration device according to an embodiment of the present invention Figure 2 。 DETAILED DESCRIPTION OF THE EMBODIMENTS

[0101] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0102] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence.

[0103] Embodiment 1

[0104] The method embodiment provided by the first embodiment of the present application can be executed on a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of the mobile terminal for the vehicle path restoration method according to the embodiment of the present invention. As Figure 1 shown, the mobile terminal may include one or more ( Figure 1 only one is shown in Figure 1 the figure) processors 102 (the processors 102 may include, but are not limited to, processing devices such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above-mentioned mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown in Figure 1 is only schematic and does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal may further include more or fewer components than

[0105] shown in

[0106] The memory 104 can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to the vehicle path restoration method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 can be a high-speed random access memory, or a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further be a memory remotely set relative to the processor 102, and these remote memories can be connected to the mobile terminal through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and their combinations.

[0106] The transmission device 106 is used to receive or send data. For example, it receives or sends data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of a mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0107] In this embodiment, a vehicle path restoration method running on the above-mentioned mobile terminal or network architecture is provided. Figure 2 It is the flow of the vehicle path restoration method according to the embodiment of the present invention. Figure 1 , as Figure 2 shown, applied to a background server, and this flow includes the following steps:

[0108] Step S202, obtain independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters, where the vehicle feature information is determined by the multiple ETC gantry device clusters according to the vehicle images passing through the ETC gantries;

[0109] The above-mentioned independent ETC transaction information refers to the transaction information directly obtained from the gantry ETC transaction controller of the gantry device cluster, and the independent vehicle feature information refers to the feature information directly extracted from the vehicle images.

[0110] In the embodiment of the present invention, the vehicle feature information includes: license plate number, vehicle color, vehicle type, roof skylight shape, in-vehicle pendant, windshield annual inspection mark, etc. In addition, other information is determined through the vehicle image by the coke oven to lock the vehicle. For example, through the driver, driver's form, facial features, etc.; the ETC transaction information includes ETC gantry identification, transaction time, and license plate number.

[0111] Step S204, perform feature matching according to the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0112] For the target vehicle, if the ETC transaction information and the vehicle feature information match the same target vehicle. Specifically, for example, if the license plate number in the ETC transaction information matches the license plate number in the vehicle feature information successfully, that is, it corresponds to the same target vehicle, then it is called the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0113] Step S206: Determine the driving route of the target vehicle based on the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0114] In the embodiment of the present invention, the above step S206 may specifically include: determining the target position information corresponding to the ETC gate identification carried in the ETC transaction information and the vehicle feature information corresponding to the target vehicle according to the corresponding relationship between the pre-stored ETC gate identification and the position information; determining the driving route of the target vehicle according to the target position information, that is, the driving route of the target vehicle can be accurately determined through the pre-gate route table. It should be noted that the target vehicles in the embodiment of the present invention include multiple vehicles, that is, the driving routes of multiple vehicles can be identified simultaneously. Connect the vehicle images of different gates of the same vehicle together to generate the complete driving route of the target vehicle, and the complete driving route can be obtained through the gate identification.

[0115] Through the above steps S202 to S206, independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gate device clusters are obtained, and feature matching is performed according to the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle; determining the driving route of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle can solve the problem in the related art that the recorded route deviates from the actual driving route due to the failure of in-vehicle medium reading. The vehicle feature information is determined through the vehicle image, and based on the vehicle feature information, the gate identification, and the time of collecting the vehicle image (i.e., the capture time), the vehicle driving route is determined, improving the accuracy of the vehicle driving route.

[0116] In an embodiment, the server binds the received ETC transaction information and the vehicle feature information that belong to the same target vehicle collected by the same ETC gate device cluster. Specifically, the above step S204 may specifically include:

[0117] Bind the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identification to obtain binding information, that is, the ETC transaction information and the vehicle feature information with a binding relationship can be obtained from the binding information. The ETC transaction information includes the ETC gantry identification, the transaction time, and the license plate number. The vehicle feature information at least includes the license plate number, and the vehicle feature information also carries the ETC gantry identification and the capture time of the vehicle image. The binding can be performed in the following manner: match the ETC transaction information and the vehicle feature information of the same ETC gantry identification; if the difference between the transaction time included in the ETC transaction information of the same ETC gantry identification and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters in the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, determine that the match is successful and obtain the binding information; perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0118] In another embodiment, the server can also directly receive the binding information of the ETC transaction information and the vehicle feature information of the same target vehicle collected by the same gantry device cluster, and perform matching based on the binding information, the separate ETC transaction information, and the vehicle feature information. Specifically, step S204 above can specifically include: receiving the binding information of the same target vehicle with a binding relationship sent by the multiple ETC gantry device clusters, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship; performing feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0119] In the embodiment of the present invention, during the process of performing feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information, matching is performed between the binding information and the independent ETC transaction information, between the binding information and the independent vehicle feature information, and between the independent ETC transaction information and the independent vehicle feature information. Matching is also required between different binding information, between different independent ETC transaction information, and between different independent vehicle feature information. Finally, the ETC transaction information and the vehicle feature information corresponding to the target vehicle are obtained, which specifically includes:

[0120] Match the ETC transaction information in the binding information and / or the independent ETC transaction information. Further, perform license plate number matching between the ETC transaction information in the binding information and the independent ETC transaction information, perform license plate number matching between the ETC transaction information in the binding information, and perform license plate number matching between the independent ETC transaction information; if the license plate numbers are the same, the matching is successful; if the license plate numbers are different, the matching fails;

[0121] Match the vehicle feature information in the binding information and / or the independent vehicle feature information. Further, respectively determine the similarity between the vehicle feature information in the binding information and the independent vehicle feature information, between the vehicle feature information in the binding information, and between the independent vehicle feature information; obtain the maximum similarity. If the maximum similarity is greater than or equal to the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity is successfully matched; if the maximum similarity value is less than the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity fails to match;

[0122] Determine all the ETC transaction information and all the vehicle feature information of the target vehicle with successful matching as the ETC transaction information and the vehicle feature information corresponding to the target vehicle, that is, summarize all the ETC transaction information and vehicle feature information of the same target vehicle, and the corresponding matching result can be obtained. Through the matching of the above features, for some gantry device clusters that fail to collect vehicle images and thus fail to obtain the vehicle feature information of the target vehicle, or the vehicle feature information transmission fails, or when performing target recognition on the vehicle image, the recognition is inaccurate and the vehicle feature information is inaccurate, resulting in a matching failure, the matching failure caused by this can be compensated by the ETC transaction information, further improving the accuracy of driving path determination.

[0123] Embodiment 2

[0124] According to another embodiment of the present invention, a vehicle path restoration method is further provided. Figure 3 is the flow of the vehicle path restoration method according to the embodiment of the present invention Figure 2 , as Figure 3 shown, applied to a gantry device cluster, and the process includes the following steps:

[0125] Step S302, obtain a vehicle image passing through the ETC gantry, and determine vehicle feature information according to the vehicle image;

[0126] In an embodiment of the present invention, vehicle images are collected by the road section video collection devices of the gantry device cluster. Specifically, the above step S302 may include: receiving the vehicle video collected by the camera passing through the ETC gantry, and capturing the vehicle image from the vehicle video or extracting a frame of the image from the vehicle video as the vehicle image; or directly obtaining the image collected by the camera and receiving the vehicle image captured by the camera passing through the ETC gantry. Whether directly obtaining the vehicle image captured by the camera or obtaining a frame of the vehicle image from the video, it is a frame of the image during the process of the vehicle passing through the gantry device cluster, so that the vehicle feature information can be accurately obtained, and the vehicle path can be restored through the video, image and ETC transaction flow information to help the toll station charge the vehicle correctly.

[0127] The ETC gantry device cluster in an embodiment of the present invention specifically may include video collection devices. The video collection devices may be cameras covering single or multiple lanes, or panoramic cameras. The devices are installed on the ETC gantries of each road section to trigger and capture the passing vehicles of the gantry all-weather to obtain vehicle images.

[0128] Step S304, obtain ETC transaction information;

[0129] The above ETC gantry device cluster further includes a gantry ETC transaction controller, which is a controller for running the ETC transaction software on the traditional ETC gantry. The ETC transaction information is obtained through the gantry ETC transaction controller.

[0130] Step S306, send independent ETC transaction information and / or independent vehicle feature information to the server, where the independent ETC transaction information and the independent vehicle feature information are used by the server for feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving path of the target vehicle.

[0131] Through the above steps S302 to S306, the problem in the related technology that the recorded path deviates from the actual driving path due to the failure of reading the in-vehicle medium can be solved. The vehicle feature information is determined through the vehicle image, and based on the vehicle feature information, the gantry identifier and the time of collecting the vehicle image (i.e., the capture time), the driving path of the vehicle is determined, improving the accuracy of the driving path of the vehicle.

[0132] In the embodiments of the present invention, the ETC transaction information and vehicle feature information of the same vehicle collected in each gantry device cluster can also be bound. Specifically, the ETC transaction information and the vehicle feature information are matched; if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters in the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, it is determined that the matching is successful, and binding information is obtained, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship, and the ETC transaction information includes an ETC gantry identifier, a transaction time, and a license plate number; the binding information is sent to the server, where the server is used to perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle. The binding can be performed by the gantry control computer of the gantry device cluster. The gantry control computer is a computer with certain computing power and storage capacity; it is placed on the ETC gantries of each section, connected to the video acquisition device, connected to the gantry ETC transaction controller, and connected to the network data transmission dedicated line; it receives the video stream or the vehicle image captured by the gantry passing vehicle from the video acquisition device, receives the ETC transaction record from the gantry ETC transaction controller, and sorts and packages the data according to a certain strategy, and transmits the data to the background computing server through the network data transmission dedicated line, so that the background server directly performs vehicle feature matching based on the binding information, the individual ETC transaction information, and the vehicle feature information, thereby improving the determination efficiency of the driving path of the target vehicle.

[0133] Figure 4 is a schematic diagram of a highway vehicle path restoration system according to an embodiment of the present invention, as Figure 4 shown, including a plurality of ETC gantry device clusters 42 and a background computing server 44 (abbreviated as the above-mentioned server), where the gantry ETC transaction controller includes a GPU / CPU and a memory.

[0134] The ETC 42 includes a gantry ETC transaction controller, a section video acquisition device, and a gantry control computer.

[0135] The gantry ETC transaction controller is a controller used to run the ETC transaction software on a traditional ETC gantry, connected to the gantry control computer, and sends the ETC transaction record to it.

[0136] The video acquisition device for the section can be a camera covering a single or multiple lanes, or a panoramic camera. The device is installed on the ETC gantry of each section and is connected to the gantry control computer; it triggers and captures the passing vehicles at the gantry and transmits the captured vehicle images to the gantry control computer.

[0137] The gantry control computer is a computer with certain computing power and storage capacity; it is placed on the ETC gantry of each section, connected to the video acquisition device, the gantry ETC transaction controller, and the network data transmission dedicated line; it receives the video stream or the images captured by the passing vehicles at the gantry from the video acquisition device, receives the ETC transaction details from the gantry ETC transaction controller, and sorts and packages the data according to a certain strategy, and transmits the data to the background computing server 44 through the network data transmission dedicated line;

[0138] Connecting the gantry control computer and the background computing server 44 through the network data transmission dedicated line can meet the corresponding data transmission bandwidth requirements.

[0139] The background computing server 44 includes a calculator with certain computing power: GPU or CPU, and a memory with certain storage capacity: memory, hard disk. It receives and aggregates in real time through the network data transmission dedicated line the data such as the passing vehicle images captured by multiple gantries, the ETC transaction details, extracts the features of the images, uses the features for feature matching, links the captured images of the same vehicle at different gantries together, and combines with the ETC transaction details to generate the complete driving path of a certain vehicle, and the path is characterized by the gantry numbers (corresponding to the above gantry identifiers) passed by the vehicle.

[0140] The method for restoring the vehicle path on the highway proposed in the embodiment of the present invention includes the following steps: gantry video and image acquisition, video and image vehicle feature extraction, vehicle feature matching, and vehicle path restoration.

[0141] Step1, gantry video and image acquisition;

[0142] The video acquisition device at the gantry end can acquire video of the passing vehicles at the gantry and transmit it to the gantry control computer;

[0143] The video acquisition device at the gantry end can also acquire images of the passing vehicles at the gantry and transmit it to the gantry control computer;

[0144] Step2, video and image vehicle feature extraction;

[0145] The gantry control calculator receives the vehicle-passing video of this gantry and extracts vehicle features from the video stream. The features include but are not limited to: license plate number, vehicle color, vehicle model, shape of the roof skylight, interior hanging ornaments, annual inspection mark on the windshield, driver's form, etc. At the same time, the gantry control calculator receives the transaction flow information sent by the ETC transaction controller of this gantry, and compares the license plate number, vehicle model and other information in the transaction flow information with the feature information extracted from the video stream. If the requirements are met, the binding can be completed. The vehicle feature information and the corresponding ETC transaction flow information after the binding are packaged and uploaded to the background calculation server. The unbound ETC transaction flow information and vehicle feature information are uploaded independently.

[0146] The gantry control calculator receives the vehicle-passing image of this gantry and extracts vehicle features from the image. The features include but are not limited to: license plate number, vehicle color, vehicle model, shape of the roof skylight, interior hanging ornaments, annual inspection mark on the windshield, driver's form, etc. At the same time, the gantry control calculator receives the transaction flow information sent by the ETC transaction controller of this gantry, and compares the license plate number, vehicle model and other information in the transaction flow information with the feature information extracted from the image. If the requirements are met, the binding can be completed. The vehicle feature information and the corresponding ETC transaction flow information after the binding are packaged and uploaded to the background calculation server. The unbound ETC transaction flow information and vehicle feature information are uploaded independently.

[0147] The gantry control calculator receives the vehicle-passing image of this gantry, receives the ETC transaction flow information sent by the ETC transaction controller of this gantry, and uploads the received vehicle-passing image and ETC transaction flow information to the background calculation server. The background calculation server extracts vehicle features from the image. The features include but are not limited to: license plate number, vehicle color, vehicle model, shape of the roof skylight, interior hanging ornaments, annual inspection mark on the windshield, driver's form, etc. At the same time, the background calculation server attempts to bind the ETC transaction flow and the feature information extracted from the image belonging to the same gantry. If the requirements are met, the binding can be completed.

[0148] The binding of the ETC transaction flow information and the feature information extracted from the image needs to be calculated with the help of two dimensions: time and similarity. The license plate number and transaction time information in the ETC transaction flow information form an information queue Message1:

[0149] Message1:

[0150] [No1 Transaction Time Time1 License Plate Number PlateNum1];

[0151] [No2 Time2 PlateNum2];

[0152] [No3 Time3 PlateNum3];

[0153] …

[0154] [No20 Time20 PlateNum20];

[0155] …

[0156] The license plate number and the captured time information in the feature information extracted from the image form an information queue Message2:

[0157] [No1 Captured Time Time1 License Plate Number PlateNum1];

[0158] [No2 Time2 PlateNum2];

[0159] [No3 Time3 PlateNum3];

[0160] …

[0161] [No20 Time20 PlateNum20];

[0162] …

[0163] When and only when abs(Message1.TimeX - Message2.TimeY) < DeltaT, and the number of identical characters between Message1.PlateNumX and Message2.PlateNumY is greater than or equal to a preset threshold, which can be set according to actual requirements, for example, it can be set to 5, 6, etc. This value is only for illustration and does not limit the embodiments of the present invention. It is determined that Message1.NoX and Message2.NoY are successfully bound. Where DeltaT is a preset threshold, for example, 20 seconds.

[0164] Step3, vehicle feature matching and vehicle path restoration.

[0165] After Step2, there are three types of information in the background calculation server:

[0166] Type1: ETC transaction flow information and feature information that have completed binding;

[0167] {[Transaction Time License Plate Number Vehicle Type…], [Captured Time License Plate Number, Vehicle Color, Vehicle Type, Roof Sunroof Shape, Interior Hanging Accessories, Windshield Annual Inspection Mark, Driver's Form…]}

[0168] Type2: Separate ETC transaction flow information;

[0169] {[Transaction Time License Plate Number Vehicle Type…]}

[0170] Type 3: Separate feature information;

[0171] {[Snap - shot time, license plate number, vehicle color, vehicle model, shape of the roof skylight, interior hanging ornaments, annual inspection sign on the windshield, driver's form...]}

[0172] The background calculation server first performs 'ETC transaction flow matching' on the two types of data, Type 1 and Type 2. Vehicles with the same license plate number in the ETC transaction flow information are grouped into one category. And once multiple Type 1 data are grouped into one category, only the Type 1 data with the latest time in this category will be used as the representative of this category to participate in the calculation when it comes to vehicle matching calculations later. Then, it processes the'vehicle feature matching' of Type 1 and Type 3 data. Using vehicle re - identification (Vehicle ReID) technology, it searches for Type 3 data in the Type 1 and Type 3 data sets of the server. By comparing vehicle feature information, it obtains the maximum similarity value Fmax. When the similarity F > DeltaF, the two vehicles are grouped into one category. And once multiple Type 1 or Type 3 data are grouped into one category, only the Type 1 or Type 3 data with the latest time in this category will be used as the representative of this category to participate in the calculation when it comes to vehicle feature matching calculations later.

[0173] After completing the vehicle feature matching, for the same - category vehicles, in chronological order, combined with the gantry number, a path information table PathMessage of the vehicle is formed:

[0174] [Time1 GantryNo1]

[0175] [Time2 GantryNo1]

[0176] …

[0177] [Time5 GantryNo5]

[0178] …

[0179] Then, combined with the gantry path table including the corresponding relationship between gantry identification and location information, the driving path of the vehicle is determined.

[0180] Since the current toll - collection system only relies on the passing - station information recorded in the on - vehicle medium for toll collection, and the on - vehicle medium is prone to failure for various reasons. Once there is a deviation between the recorded path and the actual path, it will result in incorrect toll collection.

[0181] In the embodiment of the present invention, by means of the video acquisition device of the gantry equipment cluster, the video information or image of the vehicle passing through the gantry is actively captured, and various types of information are centrally aggregated in the background for path restoration, without being affected by in-vehicle media, which increases the accuracy rate of the toll collection system.

[0182] Embodiment 3

[0183] According to another embodiment of the present invention, a vehicle path restoration device is further provided. Figure 5 is a block diagram of the vehicle path restoration device according to the embodiment of the present invention. Figure 1 as Figure 5 shown, including:

[0184] A first acquisition module 52, configured to acquire independent ETC transaction information and / or independent vehicle feature information sent by a plurality of ETC gantry equipment clusters, wherein the vehicle feature information is determined by the plurality of ETC gantry equipment clusters according to the vehicle image passing through the ETC gantry;

[0185] A feature matching module 54, configured to perform feature matching according to the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0186] A first determination module 56, configured to determine the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0187] Optionally, the feature matching module 54 includes:

[0188] A binding sub-module, configured to bind the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain binding information, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship;

[0189] A feature matching sub-module, configured to perform feature matching according to the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0190] Optionally, the binding sub-module includes:

[0191] A first matching unit, configured to match the ETC transaction information and the vehicle feature information with the same ETC gantry identifier;

[0192] A first determination unit, configured to determine a successful match and obtain the binding information if a difference between a transaction time included in the ETC transaction information of the same ETC gantry identifier and a capture time included in the vehicle feature information is less than a preset time threshold, and a number of identical characters between a license plate number included in the ETC transaction information and a license plate number included in the vehicle feature information is greater than or equal to a first preset threshold.

[0193] Optionally, the feature matching module 54 includes:

[0194] A receiving sub-module, configured to receive binding information of the same target vehicle with a binding relationship sent by the multiple ETC gantry device clusters, where the binding information includes the ETC transaction information and the vehicle feature information with the binding relationship.

[0195] A feature matching sub-module, configured to perform feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0196] Optionally, the feature matching sub-module includes:

[0197] A second matching unit, configured to match the ETC transaction information in the binding information and / or the independent ETC transaction information.

[0198] A third matching unit, configured to match the vehicle feature information in the binding information and / or the independent vehicle feature information.

[0199] A second determination unit, configured to determine all the ETC transaction information and all the vehicle feature information of the target vehicle with a successful match as the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0200] Optionally, the second matching unit is further configured to

[0201] Perform license plate number matching between the ETC transaction information in the binding information and the independent ETC transaction information, perform license plate number matching between the ETC transaction information in the binding information, and perform license plate number matching between the independent ETC transaction information;

[0202] If the license plate numbers are the same, the match is successful;

[0203] If the license plate numbers are different, the match fails.

[0204] Optionally, the third matching unit is further configured to

[0205] Determine the similarity between the vehicle feature information in the binding information and the independent vehicle feature information, between the vehicle feature information of the binding information, and between the independent vehicle feature information respectively;

[0206] Obtain the maximum similarity;

[0207] If the maximum similarity is greater than or equal to the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity matches successfully;

[0208] If the maximum similarity value is less than the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity fails to match.

[0209] Optionally, the first determination module 56 includes:

[0210] A first determination sub-module, configured to determine the target position information corresponding to the ETC transaction information of the target vehicle and the ETC gantry identifier carried in the vehicle feature information according to the corresponding relationship between the pre-stored ETC gantry identifier and the position information;

[0211] A second determination sub-module, configured to determine the driving path of the target vehicle according to the target position information.

[0212] Optionally, the vehicle feature information further includes: vehicle color, vehicle model, roof skylight shape, in-vehicle pendant, windshield annual inspection mark;

[0213] The ETC transaction information includes an ETC gantry identifier, a transaction time, and a license plate number.

[0214] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to this: the above-mentioned modules are all located in the same processor; or, the above-mentioned various modules are respectively located in different processors in any combination form.

[0215] Embodiment 4

[0216] According to another embodiment of the present invention, there is also provided a vehicle path restoration device, Figure 6 is a block diagram of the vehicle path restoration device according to the embodiment of the present invention Figure 2 , as Figure 6 shown, includes:

[0217] A second acquisition module 62, configured to acquire an image of a vehicle passing through an ETC gantry and determine vehicle feature information according to the vehicle image;

[0218] A third acquisition module 64, configured to acquire ETC transaction information;

[0219] The first sending module 66 is configured to send independent ETC transaction information and / or independent vehicle feature information to the server. The independent ETC transaction information and the independent vehicle feature information are used by the server for feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving route of the target vehicle.

[0220] Optionally, the apparatus further includes:

[0221] A matching module, configured to match the ETC transaction information and the vehicle feature information;

[0222] A second determination module, configured to determine that the matching is successful and obtain binding information if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters of the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold. The binding information includes the ETC transaction information and the vehicle feature information having a binding relationship.

[0223] A second sending module, configured to send the binding information to the server, where the server is configured to perform feature matching according to the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0224] Optionally, the second obtaining module 62 includes:

[0225] A first receiving sub-module, configured to receive a vehicle video of a vehicle passing through the ETC gantry collected by a camera, and capture the vehicle image from the vehicle video or extract a frame of image from the vehicle video as the vehicle image; or

[0226] A second receiving sub-module, configured to receive the vehicle image of the vehicle passing through the ETC gantry captured by the camera.

[0227] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above-mentioned modules are all located in the same processor; or, the above-mentioned various modules are respectively located in different processors in any combination form.

[0228] Embodiment 5

[0229] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0230] Optionally, in this embodiment, the above storage medium may be configured to store a computer program for executing the following steps:

[0231] S11. Obtain independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters, wherein the vehicle feature information is determined by the multiple ETC gantry device clusters based on vehicle images passing through the ETC gantries;

[0232] S12. Perform feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0233] S13. Determine the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0234] Optionally, in this embodiment, the above storage medium may also be configured to store a computer program for executing the following steps:

[0235] S21. Obtain a vehicle image passing through the ETC gantry and determine vehicle feature information according to the vehicle image;

[0236] S22. Obtain ETC transaction information;

[0237] S23. Send independent ETC transaction information and / or independent vehicle feature information to the server, wherein the independent ETC transaction information and the independent vehicle feature information are used by the server for feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving path of the target vehicle.

[0238] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media that can store computer programs such as USB flash drives, read-only memories (ROM for short), random access memories (RAM for short), mobile hard disks, magnetic disks, or optical discs.

[0239] Embodiment 6

[0240] An embodiment of the present invention further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0241] Optionally, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0242] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0243] S11. Obtain independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters, where the vehicle feature information is determined by the multiple ETC gantry device clusters based on vehicle images passing through the ETC gantry;

[0244] S12. Perform feature matching according to the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle;

[0245] S13. Determine the driving path of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

[0246] Optionally, in this embodiment, the above processor may also be configured to execute the following steps through a computer program:

[0247] S21. Obtain a vehicle image passing through the ETC gantry and determine vehicle feature information according to the vehicle image;

[0248] S22. Obtain ETC transaction information;

[0249] S23. Send independent ETC transaction information and / or independent vehicle feature information to the server, where the independent ETC transaction information and the independent vehicle feature information are used by the server for feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving path of the target vehicle.

[0250] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0251] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0252] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A vehicle path restoration method, characterized in that, Including: Obtaining independent ETC transaction information and / or independent vehicle feature information sent by multiple ETC gantry device clusters, where the vehicle feature information is determined by the multiple ETC gantry device clusters based on vehicle images passing through the ETC gantries; Performing feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, including: binding the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain binding information, including: matching the ETC transaction information and the vehicle feature information with the same ETC gantry identifier; if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information with the same ETC gantry identifier is less than a preset time threshold, and the number of identical characters in the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, determining that the matching is successful and obtaining the binding information, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship; Determining the driving path of the target vehicle based on the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

2. The vehicle path restoration method according to claim 1, wherein, Performing feature matching based on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, including: Receiving the binding information of the same target vehicle sent by the multiple ETC gantry device clusters; Performing feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

3. The vehicle path restoration method according to claim 2, wherein Performing feature matching based on the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, including: Matching the ETC transaction information in the binding information and / or the independent ETC transaction information; Matching the vehicle feature information in the binding information and / or the independent vehicle feature information; Determining all the ETC transaction information and all the vehicle feature information of the target vehicle with successful matching as the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

4. The vehicle path restoration method according to claim 3, wherein Matching the ETC transaction information in the binding information and / or the independent ETC transaction information includes: Perform license plate number matching between the ETC transaction information in the binding information and the independent ETC transaction information, perform license plate number matching between the ETC transaction information in the binding information, and perform license plate number matching between the independent ETC transaction information; if the license plate numbers are the same, the matching is successful; if the license plate numbers are different, the matching fails. The matching of the vehicle feature information in the binding information and / or the independent vehicle feature information includes: Respectively determine the similarity between the vehicle feature information in the binding information and the independent vehicle feature information, between the vehicle feature information in the binding information, and between the independent vehicle feature information; obtain the maximum similarity; if the maximum similarity is greater than or equal to the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity is successfully matched; if the maximum similarity value is less than the second preset threshold, determine that the vehicle feature information corresponding to the maximum similarity fails to match.

5. A vehicle path restoration method, characterized in that, Include: Obtain the vehicle image passing through the ETC gantry, and determine the vehicle feature information according to the vehicle image; Obtain the ETC transaction information; Send the independent ETC transaction information and / or the independent vehicle feature information to the server, where the independent ETC transaction information and the independent vehicle feature information are used by the server for feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving path of the target vehicle; Match the ETC transaction information and the vehicle feature information; If the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than the preset time threshold, and the number of identical characters between the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to the first preset threshold, determine that the matching is successful and obtain the binding information, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship; Send the binding information to the server, where the server is used to perform feature matching according to the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

6. A vehicle path restoration device, characterized in that, Include: The first acquisition module is used to acquire the independent ETC transaction information and / or the independent vehicle feature information sent by multiple ETC gantry device clusters, where the vehicle feature information is determined by the multiple ETC gantry device clusters according to the vehicle image passing through the ETC gantry; A feature matching module, configured to perform feature matching on the independent ETC transaction information and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, including: binding the ETC transaction information and the vehicle feature information of the same target vehicle with the same ETC gantry identifier to obtain binding information, including: matching the ETC transaction information and the vehicle feature information with the same ETC gantry identifier; if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information with the same ETC gantry identifier is less than a preset time threshold, and the number of identical characters between the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, it is determined that the matching is successful, and the binding information is obtained, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship; A first determination module, configured to determine the driving route of the target vehicle according to the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

7. A vehicle path restoration device, characterized in that, Including: A second acquisition module, configured to acquire an image of a vehicle passing through an ETC gantry and determine vehicle feature information according to the vehicle image; A third acquisition module, configured to acquire ETC transaction information; A first sending module, configured to send independent ETC transaction information and / or independent vehicle feature information to a server, where the independent ETC transaction information and the independent vehicle feature information are used by the server to perform feature matching to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle, and the ETC transaction information and the vehicle feature information corresponding to the target vehicle are used by the server to determine the driving route of the target vehicle; A matching module, configured to match the ETC transaction information and the vehicle feature information; A second determination module, configured to determine that the matching is successful and obtain binding information if the difference between the transaction time included in the ETC transaction information and the capture time included in the vehicle feature information is less than a preset time threshold, and the number of identical characters between the license plate number included in the ETC transaction information and the license plate number included in the vehicle feature information is greater than or equal to a first preset threshold, where the binding information includes the ETC transaction information and the vehicle feature information with a binding relationship; A second sending module, configured to send the binding information to the server, where the server is configured to perform feature matching according to the binding information, the independent ETC transaction information, and the independent vehicle feature information to obtain the ETC transaction information and the vehicle feature information corresponding to the target vehicle.

8. A computer-readable storage medium, characterized in that, A computer program is stored in the storage medium, where the computer program is set to execute the method described in any one of claims 1 to 4, 5 when running.

9. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of claims 1 to 4 and 5.

Images