Non-motor vehicle identification method, non-motor vehicle identification device and readable storage medium

Abstract

The application provides a non-motor vehicle identification method, a non-motor vehicle identification device and a computer readable storage medium. The non-motor vehicle identification method comprises the following steps: acquiring non-motor vehicle snapshot data of each intersection, acquiring a snapshot image of an un-identified license plate and un-fused radio frequency data from the non-motor vehicle snapshot data; matching non-motor vehicle features of the snapshot image, generating a non-motor vehicle video snapshot track by using the snapshot image with a successful match; matching the radio frequency data by using the non-motor vehicle video snapshot track, binding the radio frequency data with successful match and the non-motor vehicle video snapshot track; matching information of the non-motor vehicle video snapshot tracks with the same radio frequency data, fusing the non-motor vehicle video snapshot tracks with successful match, and obtaining a final non-motor vehicle video snapshot track of a target vehicle. In the above manner, the non-motor vehicle identification device is checked by video data and radio frequency data, and the accuracy of non-motor vehicle data fusion is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of non-motor vehicle identification, in particular to a non-motor vehicle identification method, a non-motor vehicle identification device and a computer readable storage medium. BACKGROUND

[0002] Non-motor vehicles (electric bicycles) have become an important means of transportation for people, and some non-motor vehicle drivers do not comply with traffic rules, resulting in frequent traffic accidents; the traffic control department constructs video and radio frequency equipment at each intersection, installs electronic license plates on non-motor vehicles, and collects non-motor vehicle passing video snapshot data and radio frequency reading data at the intersection equipment, matches and fuses the video-identified license plate with the radio frequency reading data to realize the judgment of non-motor vehicle illegal behavior and the identification of the driver's identity.

[0003] However, some drivers shield the electronic license plate, which makes it impossible to effectively identify the license plate, and how to identify the identity of the non-motor vehicle when the license plate is shielded is a problem to be solved at present, and it is impossible to accurately track the driving track of the non-motor vehicle when the license plate is shielded. SUMMARY

[0004] The present application provides a non-motor vehicle identification method, a non-motor vehicle identification device and a computer readable storage medium.

[0005] The present application provides a non-motor vehicle identification method, which comprises:

[0006] Obtaining non-motor vehicle snapshot data of each intersection, obtaining snapshot images of non-identified license plates and non-fused radio frequency data from the non-motor vehicle snapshot data;

[0007] Matching the non-motor vehicle features of the snapshot images, and generating non-motor vehicle video snapshot tracks by using the successfully matched snapshot images;

[0008] Matching the non-motor vehicle video snapshot tracks with the radio frequency data, and binding the successfully matched radio frequency data with the non-motor vehicle video snapshot tracks;

[0009] Matching the non-motor vehicle video snapshot tracks bound with the same radio frequency data, fusing the successfully matched non-motor vehicle video snapshot tracks, and obtaining the final non-motor vehicle video snapshot track of the target vehicle.

[0010] Among them, the obtaining of the non-motor vehicle snapshot data of each intersection, the obtaining of the snapshot images of the non-identified license plates and the non-fused radio frequency data from the non-motor vehicle snapshot data comprises:

[0011] Dividing the non-motor vehicle snapshot data according to the snapshot time, and dividing the non-motor vehicle snapshot data of the same snapshot time period into the same category;

[0012] Dividing the non-motor vehicle snapshot data of each snapshot time period according to the snapshot area, obtaining the snapshot image of the unrecognized license plate and the non-fused radio frequency data from the non-motor vehicle snapshot data of each snapshot area.

[0013] The information matching of the non-motor vehicle video snapshot trajectories bound with the same radio frequency data is performed, and the non-motor vehicle video snapshot trajectories with successful matching are fused to obtain the final non-motor vehicle video snapshot trajectory of the target vehicle, including:

[0014] The non-motor vehicle video snapshot trajectories bound with the same radio frequency data in multiple snapshot areas are fused to obtain the non-motor vehicle video area snapshot trajectory.

[0015] The non-motor vehicle video area snapshot trajectories bound with the same radio frequency data in multiple snapshot time periods are fused to obtain the final non-motor vehicle video snapshot trajectory.

[0016] The non-motor vehicle video snapshot trajectories bound with the same radio frequency data in multiple snapshot areas are fused to obtain the non-motor vehicle video area snapshot trajectory, including:

[0017] The non-motor vehicle video snapshot trajectories bound with the same radio frequency data in multiple snapshot areas are obtained.

[0018] The trajectory information of each non-motor vehicle video snapshot trajectory is matched.

[0019] The non-motor vehicle video area snapshot trajectories with successful matching are fused to obtain the non-motor vehicle video area snapshot trajectory.

[0020] The non-motor vehicle video area snapshot trajectories bound with the same radio frequency data in multiple snapshot time periods are fused to obtain the final non-motor vehicle video snapshot trajectory, including:

[0021] The non-motor vehicle video area snapshot trajectories bound with the same radio frequency data in multiple snapshot time periods are obtained.

[0022] The trajectory information of each non-motor vehicle video area snapshot trajectory is matched.

[0023] The non-motor vehicle video area snapshot trajectories with successful matching are fused to obtain the final non-motor vehicle video snapshot trajectory.

[0024] The trajectory information includes: a snapshot image, an appearing trajectory, and / or a trajectory endpoint.

[0025] The non-motor vehicle video snapshot trajectory is matched with the radio frequency data, and the radio frequency data with successful matching is bound with the non-motor vehicle video snapshot trajectory, including:

[0026] Match each trajectory point of the non-motorized vehicle video capture trajectory with several radio frequency data to be matched at the same time and in the same capture area;

[0027] Several radio frequency capture trajectories are generated using the aforementioned radio frequency data to be matched;

[0028] Compare the non-motorized vehicle video capture trajectory with the several radio frequency capture trajectories;

[0029] The radio frequency data to be matched in the radio frequency capture trajectory with a matching degree higher than a preset threshold is bound to the non-motorized vehicle video capture trajectory.

[0030] The non-motorized vehicle identification method further includes, after obtaining the captured image of the unidentified license plate and the unfused radio frequency data from the non-motorized vehicle capture data:

[0031] The radio frequency data is used to search for the corresponding target vehicle in the archive database;

[0032] If the target vehicle exists in the archive database, obtain the archive image of the target vehicle;

[0033] The captured image of the unidentified license plate is matched with the archive image;

[0034] The final non-motorized vehicle video capture trajectory of the target vehicle is generated using the successfully matched captured images.

[0035] The non-motorized vehicle identification method further includes, after matching the captured image of the unidentified license plate with the archive image:

[0036] If no matching image is found, the binding relationship between the radio frequency data and the target vehicle is released.

[0037] The step of generating the final non-motorized vehicle video capture trajectory of the target vehicle using the successfully matched captured images includes:

[0038] Based on the radio frequency data, the vehicle information of the target vehicle is read from the vehicle management system;

[0039] The vehicle information is then matched with the successfully captured image.

[0040] When the vehicle information is successfully matched, the final non-motorized vehicle video capture trajectory of the target vehicle is generated using the successfully matched captured image.

[0041] The application further provides a non-motor vehicle identification device, comprising a processor and a memory, wherein the memory stores program data, and the processor is used to execute the program data to realize the non-motor vehicle identification method as described above.

[0042] The application further provides a computer readable storage medium for storing program data, wherein the program data is used to realize the non-motor vehicle identification method as described above when executed by a processor.

[0043] The application has the following beneficial effects: the non-motor vehicle identification device acquires non-motor vehicle snapshot data of each intersection, acquires snapshot images of non-identified license plates and non-fused radio frequency data from the non-motor vehicle snapshot data; the non-motor vehicle features of the snapshot images are matched, and the non-motor vehicle video snapshot track is generated by using the snapshot images with successful matching; the radio frequency data is matched by using the non-motor vehicle video snapshot track, and the radio frequency data with successful matching is bound to the non-motor vehicle video snapshot track; the non-motor vehicle video snapshot tracks bound to the same radio frequency data are matched, the non-motor vehicle video snapshot track with successful matching is fused, and the final non-motor vehicle video snapshot track of the target vehicle is obtained. Through the above method, the non-motor vehicle identification device is checked by using video data and radio frequency data, and the accuracy of non-motor vehicle data fusion is effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings. Among them:

[0045] Figure 1 is a framework schematic diagram of an embodiment of the non-motor vehicle identification system provided by the application;

[0046] Figure 2 is a flow schematic diagram of an embodiment of the non-motor vehicle identification method provided by the application;

[0047] Figure 3 is a whole flow schematic diagram of an embodiment of the non-motor vehicle identification method provided by the application;

[0048] Figure 4 is Figure 2 is a specific flow schematic diagram of the non-motor vehicle identification method step S13 shown in the figure;

[0049] Figure 5 is a flow schematic diagram of another embodiment of the non-motor vehicle identification method provided by the application;

[0050] Figure 6 This is a schematic diagram of an embodiment of the non-motorized vehicle identification device provided in this application;

[0051] Figure 7 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0053] The problem this application aims to solve is to accurately identify non-motorized vehicles when there are one or more vehicles with unidentified license plates at an intersection.

[0054] Traffic management departments have installed violation capture equipment and promoted electronic license plates to determine non-motorized vehicle violations and identify drivers. However, some drivers obscure their electronic license plates, making effective identification impossible. Electric bicycle electronic license plates are a type of information-based license plate integrating RFID, license plate, and barcode technologies. Through RFID and QR codes, the license plate number of non-motorized vehicles is read using information technology, achieving unique vehicle identification. This is an extension of passive radio frequency identification (RFID) based on the Internet of Things in the field of intelligent transportation.

[0055] To address this issue, this application proposes a data analysis-based method and system for identifying non-motorized vehicles, enabling identification of non-motorized vehicles when license plates are obscured. The system utilizes front-end equipment to provide video capture data and RFID data, combined with vehicle registration information from the vehicle management office. After identifying the vehicle information, the system outputs this information to the business application system.

[0056] Please refer to the details. Figure 1 , Figure 1 This is a schematic diagram of the framework of an embodiment of the non-motorized vehicle identification system provided in this application.

[0057] like Figure 1As shown, the non-motor vehicle identification system of the present application mainly consists of front-end equipment, back-end analysis server and vehicle management office system. Among them, the front-end equipment includes radio frequency equipment and video equipment, which provides video snapshot data and radio frequency reading data to the back-end analysis server. The back-end analysis server is divided into two parts, namely business application and data analysis. The data analysis part analyzes the video snapshot data and radio frequency reading data through the image analysis module, data analysis module, storage and database, so as to judge the identity of the non-motor vehicle; the business application part realizes traffic control through the intelligent control module and the early warning center according to the determined non-motor vehicle identity. The vehicle management office system provides vehicle registration information in the data analysis part, including but not limited to: vehicle image, license plate, vehicle owner information and other vehicle information, which further improves the accuracy of data fusion by providing vehicle management office data comparison and verification.

[0058] The specific non-motor vehicle identification method is further introduced as follows Figure 1 The specific function implementation of the non-motor vehicle identification system is shown in Figure 2 and Figure 3 , Figure 2 is a flowchart of an embodiment of the non-motor vehicle identification method provided by the present application, Figure 3 is a schematic diagram of the overall flow of an embodiment of the non-motor vehicle identification method provided by the present application.

[0059] Among them, the non-motor vehicle identification method of the present application is applied to a non-motor vehicle identification device. The non-motor vehicle identification device of the present application can be a server, or a system cooperated by a server and a terminal device. Correspondingly, each part of the non-motor vehicle identification device, such as each unit, sub-unit, module and sub-module, can be all set in the server, or can be respectively set in the server and the terminal device.

[0060] Further, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules for providing a distributed server, or as a single software or software module, which is not limited here. In some possible implementation manners, the non-motor vehicle identification method of the embodiment of the present application can be realized by the processor calling the computer readable instructions stored in the memory.

[0061] It should be noted that the non-motor vehicle identification device in the embodiment of the present application can be mounted on a monitoring camera or a monitoring camera, directly controlling the camera or the camera; or it can be a kind of remote control intelligent terminal.

[0062] Specifically, as Figure 2As shown, the non-motor vehicle recognition method of the embodiment of the present application specifically comprises the following steps:

[0063] Step S11: Obtain non-motor vehicle snapshot data of each intersection, and obtain snapshot images of un-recognized license plates and un-fused radio frequency data from the non-motor vehicle snapshot data.

[0064] In the embodiment of the present application, video equipment and radio frequency equipment are arranged at each intersection, and electronic license plates are installed on non-motor vehicles. The non-motor vehicle recognition device collects non-motor vehicle passing video snapshot data and radio frequency reading data through the video equipment and the radio frequency equipment. The non-motor vehicle recognition device matches and fuses the video recognition license plate and the radio frequency reading data, and filters out the snapshot images of un-recognized license plates in the video data and the un-fused radio frequency data in the radio frequency data, and stores them into the basic database respectively.

[0065] Among them, the snapshot image of the un-recognized license plate, that is, the license plate part is partially or completely blocked in the snapshot image, and the license plate cannot be completely recognized; the un-fused radio frequency data, that is, the recognized radio frequency data cannot be bound with the snapshot image of the completely recognized license plate.

[0066] Specifically, before matching the snapshot image and the radio frequency data, the non-motor vehicle recognition device can also clean up the non-motor vehicle snapshot data of each intersection according to the time dimension and the space dimension, so as to improve the matching efficiency and the matching accuracy.

[0067] The non-motor vehicle recognition device divides the non-motor vehicle snapshot data in the basic database according to the snapshot time, for example, the snapshot data of the same day can be divided into a category. In other embodiments, other snapshot time period lengths can also be set, which are not limited here.

[0068] Then, the non-motor vehicle recognition device divides the non-motor vehicle snapshot data of the same day according to the snapshot area, and the snapshot area can be according to the administrative region range, the card mouth range or the self-defined range, etc.

[0069] In the subsequent matching, the non-motor vehicle recognition device first matches the snapshot images and the radio frequency data in the same category after division, please continue to read the subsequent steps.

[0070] Step S12: Match the non-motor vehicle features of the snapshot image, and generate the non-motor vehicle video snapshot track by using the matched snapshot image.

[0071] In the embodiment of the present application, the non-motor vehicle recognition device compares and analyzes the snapshot images in the non-motor vehicle snapshot data of the same snapshot area on the same day, extracts the non-motor vehicle vehicle features and the driver features, and compares and analyzes them, and classifies the matched snapshot images, that is, all the snapshot images of the target vehicle in the snapshot area on the same day can be obtained.

[0072] Specifically, the non-motor vehicle recognition device can compare the images by a 2-channel CNN model, and compare the vehicle images without recognized license plates according to vehicle features and driver features.

[0073] Further, the non-motor vehicle recognition device generates a non-motor vehicle video snapshot track according to snapshot positions in all snapshot images classified into one category.

[0074] Step S13: Match the radio frequency data with the non-motor vehicle video snapshot track.

[0075] In the embodiment of the present application, the non-motor vehicle recognition device matches the corresponding non-fused radio frequency reading data according to the snapshot positions and snapshot times in the vehicle snapshot records constituting the non-motor vehicle video snapshot track. If the radio frequency snapshot track of the same radio frequency reading data can be matched with the non-motor vehicle video snapshot track, it indicates that the vehicle corresponding to the radio frequency data and the vehicle corresponding to the non-motor vehicle video snapshot track are the same non-motor vehicle, and the radio frequency data can be bound with the non-motor vehicle video snapshot track.

[0076] Specifically, the specific way of matching the non-motor vehicle video snapshot track with the radio frequency data can refer to the specific process of step S13 of the non-motor vehicle recognition method shown in Figure 4 , Figure 4 is Figure 2 a specific flowchart of step S13 of the non-motor vehicle recognition method.

[0077] As shown in Figure 4 , the non-motor vehicle recognition method of the embodiment of the present application specifically includes the following steps:

[0078] Step S131: Match a plurality of to-be-matched radio frequency data at the same time and in the same snapshot area according to each track point of the non-motor vehicle video snapshot track.

[0079] In the embodiment of the present application, the non-motor vehicle recognition device acquires the non-fused radio frequency data at the same time and in the same snapshot area as each track point of the non-motor vehicle video snapshot track, as the to-be-matched radio frequency data.

[0080] Step S132: Generate a plurality of radio frequency snapshot tracks by using the plurality of to-be-matched radio frequency data.

[0081] In the embodiment of the present application, the non-motor vehicle recognition device acquires the radio frequency snapshot track of each to-be-matched radio frequency data.

[0082] Step S133: Compare the non-motor vehicle video snapshot track with the plurality of radio frequency snapshot tracks.

[0083] In the embodiment of the present application, the non-motor vehicle identification device compares the capture location and capture time of all track points of the non-motor vehicle video capture track with the track points of the radio frequency capture track one by one. If a video capture track point and a radio frequency capture track point appear at the same capture location and the same capture time, it is considered that the video capture track point is matched successfully. Finally, the non-motor vehicle identification device counts the matching degree of each radio frequency capture track and the non-motor vehicle video capture track, that is, the proportion of the video capture track points of the non-motor vehicle video capture track matched successfully with the radio frequency capture track in all video capture track points.

[0084] Step S134: binding the to-be-matched radio frequency data in the radio frequency capture track with a higher matching degree than the preset threshold value with the non-motor vehicle video capture track.

[0085] In the embodiment of the present application, the non-motor vehicle identification device can set a threshold value to determine the matching condition of the non-motor vehicle video capture track and the to-be-matched radio frequency data. For example, if the preset threshold value is 90%, when the proportion of the video capture track points of the non-motor vehicle video capture track matched successfully with the radio frequency capture track in all video capture track points is higher than 90%, it is considered that the track matching is successful, and the non-motor vehicle video capture track is bound with the to-be-matched radio frequency data.

[0086] If multiple to-be-matched radio frequency tracks and the non-motor vehicle video capture track have a matching degree meeting the threshold value requirement, the to-be-matched radio frequency data can be bound with the non-motor vehicle video capture track respectively, and then screened through subsequent secondary comparison; or only the to-be-matched radio frequency data with the highest matching degree can be bound with the non-motor vehicle video capture track.

[0087] Step S14: performing information matching on the non-motor vehicle video capture tracks bound with the same radio frequency data, fusing the non-motor vehicle video capture tracks matched successfully, and obtaining the final non-motor vehicle video capture track of the target vehicle.

[0088] In the embodiment of the present application, the non-motor vehicle identification device further compares the track information of the non-motor vehicle video capture tracks bound with the same radio frequency data, and classifies the vehicles with the vehicle image, travel track and OD point (track starting point and ending point) matched successfully or with a matching degree meeting a certain threshold value as the same vehicle, and finally obtains the final non-motor vehicle video capture track of the vehicle and the bound radio frequency reading data.

[0089] Further, since the non-motor vehicle recognition device divides the non-motor vehicle snapshot data according to the time dimension and the space dimension in step S11, the non-motor vehicle recognition device can fuse the non-motor vehicle video snapshot trajectories of different snapshot areas and different snapshot times according to the logic of binding the same radio frequency data from the time dimension and the space dimension, thereby obtaining the final non-motor vehicle video snapshot trajectory.

[0090] After the matching is completed, the non-motor vehicle recognition device stores the snapshot data of the same vehicle in the archive database, including vehicle image, incomplete license plate number, snapshot time, snapshot location, and vehicle binding radio frequency reading data; and some vehicle information has an incomplete license plate, which can be used to check whether the vehicle classification is accurate again.

[0091] In the embodiment of the present application, the non-motor vehicle recognition device obtains non-motor vehicle snapshot data of each intersection, obtains snapshot images of non-identified license plates and non-fused radio frequency data from the non-motor vehicle snapshot data; matches non-motor vehicle features of the snapshot images, generates non-motor vehicle video snapshot trajectories using the snapshot images that match successfully; matches radio frequency data using the non-motor vehicle video snapshot trajectories, binds the radio frequency data that matches successfully with the non-motor vehicle video snapshot trajectories; and matches information of the non-motor vehicle video snapshot trajectories that bind the same radio frequency data, fuses the non-motor vehicle video snapshot trajectories that match successfully, and obtains the final non-motor vehicle video snapshot trajectory of the target vehicle. Through the above-mentioned manner, the non-motor vehicle recognition device effectively improves the accuracy of non-motor vehicle data fusion through double verification of video data and radio frequency data.

[0092] The present application identifies vehicle information through data analysis and comparison in the case that there are multiple non-identified license plate vehicles at an intersection in a sampling period, and video data and radio frequency data cannot be directly fused, thereby meeting the scene of accurately identifying the identity of multiple vehicles with license plate shielding. The present application is realized by a 2-channel CNN model when constructing a basic database and comparing and analyzing current intersection video data and radio frequency data, thereby improving the accuracy of image analysis and improving the calculation speed.

[0093] As shown in Figure 3 When the intersection front-end device again snapshots the non-identified license plate vehicle image and non-fused radio frequency data, the radio frequency reading data is compared with the radio frequency data in the archive database to determine whether the vehicle exists in the archive database. If the vehicle exists, the snapshot image in the archive database can be directly used to analyze the non-identified license plate vehicle image, and historical data can be used to further improve the efficiency of non-motor vehicle recognition.

[0094] For details, please refer to Figure 5 , Figure 5 is a flowchart of another embodiment of the non-motor vehicle recognition method provided by the present application.

[0095] As Figure 5 shown, the non-motor vehicle identification method of the embodiment of the application specifically includes the following steps:

[0096] Step S21: searching the corresponding target vehicle in the archive database for the radio frequency data.

[0097] In the embodiment of the application, if the radio frequency data does not exist in the archive database, the radio frequency data is put into the basic database for analysis, that is, the radio frequency data and the video snapshot data are synchronously analyzed by the non-motor vehicle identification method as shown in Figure 2 .

[0098] Step S22: if the target vehicle exists in the archive database, the archive image of the target vehicle is acquired.

[0099] Step S23: using the archive image to match the snapshot image of the un-identified license plate.

[0100] In the embodiment of the application, if the radio frequency data exists in the archive database, the vehicle archive image bound with the radio frequency data is compared and matched with the un-identified license plate snapshot image of the current intersection. If there is no successfully matched snapshot image, it means that the target vehicle is bound with errors, and the radio frequency reading data bound with the vehicle is removed, and the vehicle information is put back to the basic database for analysis.

[0101] Step S24: using the successfully matched snapshot image to generate the final non-motor vehicle video snapshot track of the target vehicle.

[0102] In the embodiment of the application, as shown in Figure 3 , if the un-identified license plate snapshot image is successfully matched with the archive image, the vehicle registration information of the traffic management department is continued to be connected, the vehicle registration picture information and the license plate information of the vehicle are queried according to the radio frequency reading information of the vehicle, the vehicle image comparison analysis and the license plate comparison are performed, if the comparison and matching are not successful, the related information is output to the traffic management department for review; if the comparison is successful, the vehicle license plate is successfully fused with the radio frequency reading data, and the vehicle information is output to the business system.

[0103] The application analyzes the historical video data of the un-identified license plate vehicle, classifies the same vehicle, establishes a basic database, combines the radio frequency data in the vehicle historical track information, preliminarily binds the vehicle video data and the radio frequency data, establishes a corresponding database, when the un-identified license plate vehicle is snapped, the video data and the radio frequency data of the current intersection are compared and analyzed with the data in the database, the identity of the vehicle is identified, through the double verification of the video data and the radio frequency data in the current snapshot location and the historical track and the comparison and verification of the data of the traffic management department, the accuracy of the data fusion is improved.

[0104] Those skilled in the art can understand that the sequence of writing each step in the above method of the specific embodiment does not mean a strict execution sequence and does not constitute any limitation on the implementation process. The specific execution sequence of each step should be determined by its function and possible internal logic.

[0105] To implement the non-motor vehicle identification method of the above-mentioned embodiments, the application further provides a non-motor vehicle identification device, please refer to Figure 6 , Figure 6 is a structural schematic diagram of an embodiment of the non-motor vehicle identification device provided by the application.

[0106] The non-motor vehicle identification device 300 of the embodiment of the application comprises a memory 31 and a processor 32, wherein the memory 31 and the processor 32 are coupled.

[0107] The memory 31 is used to store program data, and the processor 32 is used to execute the program data to implement the non-motor vehicle identification method described in the above-mentioned embodiments.

[0108] In the embodiment, the processor 32 can also be referred to as a CPU (Central Processing Unit). The processor 32 can be an integrated circuit chip with signal processing capability. The processor 32 can also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor 32 can also be any conventional processor.

[0109] To implement the non-motor vehicle identification method of the above-mentioned embodiments, the application further provides a computer readable storage medium, as shown in Figure 7 The computer readable storage medium 400 is used to store program data 41, and the program data 41 is used to implement the non-motor vehicle identification method as described in the above-mentioned embodiments when executed by a processor.

[0110] The application further provides a computer program product, wherein the above-mentioned computer program product comprises a computer program, and the above-mentioned computer program is operable to make a computer execute the non-motor vehicle identification method as described in the embodiments of the application. The computer program product can be a software installation package.

[0111] The non-motor vehicle identification method described in the above embodiments of the present application exists in the form of a software functional unit when implemented and sold or used as an independent product, and can be stored in a device, such as a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0112] The above description is only an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is based on the content of the specification and drawings of the present application, is also included in the patent protection scope of the present application.

Claims

1. A non-motor vehicle identification method characterized by, The non-motor vehicle identification method comprises: acquiring non-motor vehicle snapshot data of each intersection, acquiring snapshot images of non-identified license plates and non-fused radio frequency data from the non-motor vehicle snapshot data; matching non-motor vehicle features of the snapshot images, and generating non-motor vehicle video snapshot tracks by using the snapshot images matched successfully; matching the radio frequency data by using the non-motor vehicle video snapshot tracks, and binding the radio frequency data matched successfully and the non-motor vehicle video snapshot tracks; performing information matching on non-motor vehicle video snapshot tracks bound with the same radio frequency data, fusing the non-motor vehicle video snapshot tracks matched successfully, and obtaining a final non-motor vehicle video snapshot track of a target vehicle; the matching the radio frequency data by using the non-motor vehicle video snapshot tracks, and binding the radio frequency data matched successfully and the non-motor vehicle video snapshot tracks comprises: matching a plurality of to-be-matched radio frequency data of the same snapshot region at the same time according to each track point of the non-motor vehicle video snapshot tracks; generating a plurality of radio frequency snapshot tracks by using the plurality of to-be-matched radio frequency data; comparing the non-motor vehicle video snapshot tracks and the plurality of radio frequency snapshot tracks; binding the to-be-matched radio frequency data in the radio frequency snapshot track with the non-motor vehicle video snapshot tracks, the matching degree of which is higher than a preset threshold.

2. The non-motor vehicle identification method according to claim 1, wherein the acquiring non-motor vehicle snapshot data of each intersection, and acquiring snapshot images of non-identified license plates and non-fused radio frequency data from the non-motor vehicle snapshot data comprises: dividing the non-motor vehicle snapshot data according to snapshot time, and dividing non-motor vehicle snapshot data of a same snapshot time period into a same category; dividing non-motor vehicle snapshot data of each snapshot time period according to a snapshot region, and acquiring snapshot images of non-identified license plates and non-fused radio frequency data from non-motor vehicle snapshot data of each snapshot region.

3. The non-motor vehicle identification method according to claim 2, wherein the performing information matching on non-motor vehicle video snapshot tracks bound with the same radio frequency data, fusing the non-motor vehicle video snapshot tracks matched successfully, and obtaining a final non-motor vehicle video snapshot track of a target vehicle comprises: fusing non-motor vehicle video snapshot tracks bound with the same radio frequency data in a plurality of snapshot regions, and obtaining non-motor vehicle video regional snapshot tracks; fusing non-motor vehicle video regional snapshot tracks bound with the same radio frequency data in a plurality of snapshot time periods, and obtaining a final non-motor vehicle video snapshot track.

4. The non-motor vehicle identification method according to claim 3, wherein the fusing non-motor vehicle video snapshot tracks bound with the same radio frequency data in a plurality of snapshot regions, and obtaining non-motor vehicle video regional snapshot tracks comprises: acquiring non-motor vehicle video snapshot tracks bound with the same radio frequency data in a plurality of snapshot regions; matching track information of each non-motor vehicle video snapshot track; fusing the non-motor vehicle video snapshot tracks matched successfully, and obtaining the non-motor vehicle video regional snapshot tracks. And / or, the non-motor vehicle video area snapshot trajectory bound with the same radio frequency data in multiple snapshot time periods is fused to obtain a final non-motor vehicle video snapshot trajectory, comprising: obtaining non-motor vehicle video area snapshot trajectories bound with the same radio frequency data in multiple snapshot time periods; matching the trajectory information of each non-motor vehicle video area snapshot trajectory; fusing the non-motor vehicle video area snapshot trajectories that are successfully matched to obtain the final non-motor vehicle video snapshot trajectory; wherein the trajectory information comprises: a snapshot image, an appearing trajectory, and / or a trajectory endpoint.

5. The non-motor vehicle identification method according to claim 1, wherein, after obtaining the snapshot image of the un-identified license plate and the non-fused radio frequency data from the non-motor vehicle snapshot data, the non-motor vehicle identification method further comprises: searching for a corresponding target vehicle in an archive database using the radio frequency data; if the target vehicle exists in the archive database, obtaining an archive image of the target vehicle; matching the snapshot image of the un-identified license plate with the archive image; generating a final non-motor vehicle video snapshot trajectory of the target vehicle using the snapshot image that is successfully matched.

6. The non-motor vehicle identification method according to claim 5, wherein, after matching the snapshot image of the un-identified license plate with the archive image, the non-motor vehicle identification method further comprises: if there is no snapshot image that is successfully matched, releasing the binding relationship between the radio frequency data and the target vehicle.

7. The non-motor vehicle identification method according to claim 5, wherein, the generating of the final non-motor vehicle video snapshot trajectory of the target vehicle using the snapshot image that is successfully matched comprises: reading vehicle information of the target vehicle from a vehicle management system based on the radio frequency data; matching the vehicle information with the snapshot image that is successfully matched; when the vehicle information is successfully matched, generating the final non-motor vehicle video snapshot trajectory of the target vehicle using the snapshot image that is successfully matched. The non-motor vehicle identification device comprises a processor and a memory, the memory stores program data, and the processor is used to execute the program data to realize the non-motor vehicle identification method according to any one of claims 1-7. The computer readable storage medium is used to store program data, and the program data is used to realize the non-motor vehicle identification method according to any one of claims 1-7 when executed by a processor. ​ 8. A non-motor vehicle identification device, characterized by, ​ 9. A computer-readable storage medium, characterized in that, ​

Images