A video-assisted non-motor vehicle tag positioning method, system and device
Non-motor vehicle tag positioning is performed through video assist technology, and the positioning trigger threshold of RF antennas is automatically corrected, which solves the problems of missed and false alarms of non-motor vehicle positioning in the existing technology, simplifies the equipment deployment and calibration process, and improves the identification accuracy rate And reduce costs.
Patent Information
- Application Number
- CN202111625603.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-28
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2041-12-28
AI Technical Summary
The existing RF positioning methods have frequent missed and false alarm problems in non-motor vehicle label positioning, and require frequent calibration, resulting in high labor and time costs.
The video-assisted non-motor vehicle label positioning method is adopted to obtain the video license plate number string through video vehicle data for double-base matching, correct the positioning trigger threshold of the RF antenna, automatically calibrate the relative distance of the RF antenna, and simplify the equipment deployment and calibration process.
It improves the recognition accuracy of non-motor vehicle tag positioning, reduces positioning calibration steps, reduces labor and time costs, and realizes automatic calibration of radio frequency positioning.
Smart Images

Figure CN114283368B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of radio frequency identification and positioning technology, and in particular to a non-motor vehicle tag positioning method, system and device based on video assistance. Background Art
[0002] Non-motor vehicles are convenient and flexible, among which electric bicycles are the most representative. However, the control of non-motor vehicles has always been a difficult problem. Due to the small size and complex driving routes of non-motor vehicles, traditional road equipment that relies on video recognition technology and is mainly aimed at motor vehicle data collection is prone to frequent underreporting when the road conditions are complex and non-motor vehicles are the target. In addition, non-motor vehicle license plates are very easy to be altered and blocked, which is also easy to cause false alarms. This is a defect of video recognition. In recent years, more and more RV all-in-one machines that combine video and radio frequency are used for the deployment of road equipment, using radio frequency assisted video to improve vehicle recognition rate and success rate. Among them, radio frequency positioning is the core function of the radio frequency part of this technical route.
[0003] Radio frequency positioning, that is, according to the phase parameters in the radio frequency characteristics, after obtaining the phase information, the phase difference method can usually be used for positioning, that is, the change in phase is used to reflect the distance. The three more commonly used phase difference methods are: Time Domain Phase Difference of Arrival (TDPDOA), Frequency Domain Phase Difference of Arrival (FDPDOA) and Spatial Domain Phase Difference of Arrival (SDPDOA). These methods directly calculate the relative position based on the frequency information of the signal.
[0004] The drawback of the existing positioning method is that although the calculated relative distance value is consistent with the actual displacement change of the RFID tag, a correction value K needs to be subtracted to associate it with the actual distance value. The actual environment such as the antenna deployment position, performance, and feeder length will affect the selection of the K value. Therefore, when using the phase calculation method to achieve RFID positioning, it is necessary to calibrate the K value during the equipment deployment stage. The calibration method is generally to fix the test tag in the field and measure its actual distance to the antenna. At the same time, turn on the RFID inventory and perform phase calculation to obtain a relatively stable relative distance of the tag. The difference between the relative distance and the actual distance is the K value.
[0005] Since RF road equipment is generally equipped with multiple antennas, each antenna needs to go through one or more rounds of the same calibration steps. In addition, since the actual environment will affect the K value, such as high and low temperature changes or extreme weather, the K value of all antennas of all devices needs to be recalibrated every once in a while. Therefore, this method consumes a lot of manpower and time costs. Summary of the invention
[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a non-motor vehicle tag positioning method, system and device based on video assistance, simplify the deployment of video and radio frequency integrated devices and realize automatic calibration of radio frequency positioning based on phase calculation method.
[0007] In order to achieve the above object, the present invention provides the following technical solutions:
[0008] A non-motor vehicle tag positioning method based on video assistance, comprising:
[0009] Step S1: Acquire video vehicle data;
[0010] Step S2: extract the video license plate number string in the video vehicle data, and perform a double-base match in the radio frequency node list. If the match is successful, extract the relative distance value stored in the radio frequency node list of the vehicle at the current moment;
[0011] Step S3: Correcting the positioning trigger threshold of the radio frequency antenna according to the relative distance value.
[0012] In the present invention, further, the correction method in step S3 correcting the positioning trigger threshold of the radio frequency antenna by the relative distance value is:
[0013] The average value of the relative distance this time and the positioning trigger threshold recorded last time is taken as the new positioning trigger threshold of the RF antenna and saved.
[0014] In the present invention, further, it also includes
[0015] Step S0: The RF antenna periodically counts the electronic tags. Each round of inventory creates or updates the RF node linked list to record vehicle information and calculates the relative distance between the electronic tag and the RF antenna.
[0016] In the present invention, further, it also includes
[0017] Step S4: starting from the head of the radio frequency node linked list, check and update the status of each node in turn;
[0018] Step S5: When the relative distance recorded in the radio frequency node linked list meets the trigger threshold of the new positioning of the radio frequency antenna, a capture instruction is generated and sent to the camera to realize capture and evidence collection.
[0019] In the present invention, further, step S2 includes
[0020] Remove Chinese characters from the video license plate string to obtain the video string to be matched, and poll the RF node list based on the video string to be matched. When the similarity rate between the RF string in the RF node list and the video string to be matched is greater than the set value, it is considered a successful match.
[0021] A non-motor vehicle tag positioning control system based on video assistance includes a video module and a radio frequency module electrically connected to the video module, the radio frequency module includes a radio frequency inventory thread and a message processing thread, the radio frequency inventory thread is used for periodic inventory creation or update nodes, record vehicle information and calculate relative distances and store them in a radio frequency node linked list in the form of linked list nodes, the message processing thread is used to receive video vehicle data from the video module, extract the video license plate number string in the video vehicle data, and perform double-base matching in the radio frequency node linked list, and if the match is successful, extract the relative distance value stored in the radio frequency node linked list of the vehicle at the current moment, take the average of the relative distance value and the positioning trigger threshold recorded last time as the new positioning trigger threshold of the radio frequency antenna and save it.
[0022] In the present invention, further, the RF module also includes a RF node polling thread, which is used to check the RF nodes in sequence starting from the head of the RF node linked list and update the node status. When the relative distance recorded in the RF node linked list meets the new positioning trigger threshold of the RF antenna, the RF node polling thread notifies the message processing thread and generates a capture instruction and sends it to the video module, and the video module realizes the capture of the vehicle for evidence.
[0023] In the present invention, preferably, the video module includes an active identification thread and a passive capture thread, the active identification thread is used to control the camera to actively obtain video vehicle data and input the data into the message processing thread, and the passive capture thread is used to control the camera to capture the vehicle according to the capture instruction output by the message processing thread.
[0024] In the present invention, further, the RF inventory thread uses the tag identification number in the video vehicle data as a unique identifier to distinguish different tags. For the tags counted for the first time, a new RF node is applied for, the data is copied and inserted into the RF node linked list, and then the node acquisition time is updated; for the existing nodes, only the acquisition time is updated.
[0025] A non-motor vehicle tag positioning device based on video assistance includes a camera, a radio frequency antenna and a controller. The controller adopts a non-motor vehicle tag positioning control system based on video assistance. The camera and the radio frequency antenna are electrically connected to the controller. The inventory range of the radio frequency antenna is larger than the camera field of view. When a non-motor vehicle carrying a radio frequency tag enters the inventory range of the radio frequency antenna, the controller updates the relative distance in real time. When the radio frequency tag reaches the camera frame, the camera takes a picture of the radio frequency tag. After processing by the controller, the positioning trigger threshold is determined. When the non-motor vehicle travels to the location of the positioning trigger threshold, the controller notifies the camera to capture and obtain the evidence information of the non-motor vehicle. .
[0026] Compared with the prior art, the present invention has the following beneficial effects:
[0027] The video-assisted non-motor vehicle tag positioning method described in the present invention can automatically correct the positioning trigger threshold of the radio frequency antenna by using video recognition to trigger the radio frequency antenna, and correct the error of the radio frequency positioning by the stability of the video recognition position. Therefore, the radio frequency positioning based on phase calculation no longer needs to establish a numerical connection between the relative distance and the actual distance, and the trigger position can be directly calibrated with the relative distance, eliminating the time-consuming and labor-intensive positioning calibration steps.
[0028] The device provided by the present invention uses an all-in-one video and radio frequency device, which simplifies the deployment of video and radio frequency road equipment, and makes up for the stability of radio frequency positioning triggering through video. At the same time, radio frequency positioning triggering makes up for the problem of video underreporting in complex situations of non-motor vehicles, thereby improving the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0030] Figure 1 It is an overall flow chart of a non-motor vehicle tag positioning method based on video assistance of the present invention;
[0031] Figure 2 It is a structural schematic diagram of a non-motor vehicle tag positioning system based on video assistance of the present invention;
[0032] Figure 3 It is a deployment schematic diagram of a non-motor vehicle tag positioning device based on video assistance of the present invention. DETAILED DESCRIPTION
[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0034] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a component centered. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a component centered. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a component centered. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.
[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.
[0036] See also Figure 1 The present invention is based on a positioning method for radio frequency phase calculation. When the radio frequency antenna counts the tag, the phase information of the tag can be obtained, thereby calculating the relative distance between the tag and the antenna. The fundamental purpose of using radio frequency positioning as a trigger basis in the integrated video and radio frequency machine is to notify the camera to take a snapshot when a non-motor vehicle carrying a radio frequency tag reaches a specific position in the camera frame, thereby obtaining the image information of the non-motor vehicle. The determination of this specific position is the problem to be solved by the present invention.
[0037] Specifically, a preferred embodiment of the present invention provides a non-motor vehicle tag positioning method based on video assistance, comprising:
[0038] Step S0: The RF antenna periodically counts the electronic tags. Each round of inventory creates or updates the RF node linked list to record vehicle information and calculates the relative distance between the electronic tag and the RF antenna.
[0039] Step S1: Acquire video vehicle data;
[0040] Step S2: extract the video license plate number string in the video vehicle data, and perform a double-base match in the radio frequency node list. If the match is successful, extract the relative distance value stored in the radio frequency node list of the vehicle at the current moment;
[0041] Step S3: Correcting the positioning trigger threshold of the radio frequency antenna according to the relative distance value.
[0042] Specifically, first of all, the RF antenna periodically counts the electronic tags. Each round of inventory creates or updates the RF node list to record vehicle information and calculates the relative distance between the electronic tag and the RF antenna. The specific calculation method can refer to the prior art, but in order to ensure the accuracy of the measurement, the present invention takes 8 average values and eliminates abnormal distances with a variance less than 2, and finally obtains a relative distance stability value. The vehicle information and relative distance are stored in the RF node list for recording. Vehicle information includes data such as license plate number, vehicle type, body color, tag card number, and vehicle factory date.
[0043] When a non-motor vehicle arrives within the camera's field of view, the camera takes a picture of the non-motor vehicle's electronic tag, identifies the captured picture and extracts the vehicle data, which includes at least the video license plate number. The video license plate number is processed and a double-base matching is performed on the processed video license plate number in the RF node list. If the match is successful, the relative distance value stored in the vehicle's RF node list at the current moment is extracted, and the positioning trigger threshold of the RF antenna is corrected by the relative distance value.
[0044] Therefore, the method of the present invention can use video recognition to trigger the RF antenna to automatically correct the positioning trigger threshold of the RF antenna, and correct the error of RF positioning by the stability of the video recognition position. Therefore, the RF positioning based on phase calculation no longer needs to establish a numerical connection between the relative distance and the actual distance. The trigger position can be directly calibrated with the relative distance, eliminating the time-consuming and labor-intensive positioning calibration steps.
[0045] In one embodiment provided by the present invention, for example, if the device has 4 antennas and there are 3 tags in the field for a period of time, then ideally, at the end of a round of inventory, each antenna will receive the positioning data of 3 tags, for a total of 12 sets of positioning data, which refers to the relative distance between the electronic tag and the radio frequency antenna.
[0046] Each round of inventory creates or updates the RF node linked list to record vehicle information and the relative distance between the electronic tag and the RF antenna. When a non-motorized vehicle arrives within the camera's field of view, the camera takes a picture of the non-motorized vehicle's electronic tag, identifies the captured image, extracts the vehicle data, and then performs a dual-base matching operation.
[0047] The dual-base matching of the present invention is implemented using a minimum edit distance (Levenshtein distance) algorithm. The principle of the minimum edit distance algorithm is the minimum number of modification operations required to convert one of two character strings into the other, where the modification operations include inserting a character, deleting a character, and replacing a character.
[0048] Therefore, based on the above method, the present invention first processes the video license plate number, removes Chinese characters from the video license plate number string, and only retains numbers and letters to participate in the matching, obtains the video string to be matched, and polls the radio frequency node list according to the video string to be matched. When the radio frequency string in the radio frequency node list and the video string to be matched have a similarity rate greater than a set value, it is considered to be a successful match. This set value is set to 70% based on a combination of multiple groups of experimental data and actual needs. That is to say, when the radio frequency string in the radio frequency node list and the video string to be matched have a similarity rate greater than 70%, it is considered that the radio frequency has calibrated the same vehicle. If it is less than the set value, the video license plate number is a coded data packet (the data packet includes the captured picture) and is reported separately.
[0049] Furthermore, after the visual and radio frequency dual base matching is successful, the relative distance stored in the radio frequency node of the vehicle at the current moment is extracted, and the positioning trigger threshold of the radio frequency antenna is corrected with this distance value. The specific correction method is to take the average value of this relative distance and the positioning trigger threshold recorded last time as the new positioning trigger threshold of the radio frequency antenna and save it. In this way, the positioning trigger threshold of the radio frequency antenna is determined.
[0050] In the present invention, further, it also includes
[0051] Step S4: starting from the head of the radio frequency node linked list, check and update the status of each node in turn;
[0052] Step S5: When the relative distance recorded in the radio frequency node linked list meets the trigger threshold of the new positioning of the radio frequency antenna, a capture instruction is generated and sent to the camera to realize capture and evidence collection.
[0053] Specifically, when the node is polled, the RF nodes are checked in sequence starting from the head of the linked list, and the node status is updated, including node status such as not triggered, triggered, not captured, captured, and waiting for reporting. This process is mainly used to identify the lanes of non-motor vehicles and whether there are any illegal behaviors through radio frequency identification. After the illegal behavior is determined, and the relative distance recorded in the RF node linked list meets the new positioning trigger threshold of the RF antenna, a capture instruction is generated and sent to the camera to realize capture and evidence collection.
[0054] In another embodiment provided by the present invention, see Figure 2, a non-motor vehicle tag positioning control system based on video assistance is also provided, including a video module and a radio frequency module electrically connected to the video module. At present, most video modules have a positioning function. For example, the positioning function is reflected in the scene view drawn during deployment, including lane lines, stop lines, trigger lines, etc. In actual application, when the vehicle passes the position of the trigger line in the frame according to the drawn lane line, the video module will identify the license plate through an algorithm. This solution places the video module and the radio frequency module in the same system. The radio frequency module can use the real-time nature of video recognition to know the time when the non-motor vehicle crosses the video trigger line, and the position of the video trigger line in the frame should be the same as the radio frequency trigger position. Therefore, when a non-motor vehicle is successfully identified by video, if the inventory of a certain antenna of the radio frequency module also receives the radio frequency tag data carried by the vehicle and calculates the relative distance at this time, the relative distance at this time point can be regarded as the radio frequency trigger distance of the antenna, that is, the positioning trigger threshold of the radio frequency antenna we mentioned.
[0055] In the present invention, further, the video module includes an active recognition thread and a passive capture thread. The active recognition thread is used to control the camera to actively obtain video vehicle data and input the data into the message processing thread, and the passive capture thread is used to control the camera to capture the vehicle according to the capture instruction output by the message processing thread.
[0056] Specifically, in this embodiment, the radio frequency module includes a radio frequency inventory thread and a message processing thread. The radio frequency inventory thread is used to periodically create or update nodes, record vehicle information and calculate relative distances, and store them in the radio frequency node linked list in the form of linked list nodes.
[0057] Among them, the RF node linked list uses the tag identification number in the video vehicle data as the unique identifier to distinguish different tags. For the tags counted for the first time, a new RF node is applied for, the data is copied and inserted into the RF node linked list, and then the node acquisition time is updated; for existing nodes, only the acquisition time is updated.
[0058] The message processing thread is used to receive video vehicle data from the video module, extract the video license plate number string in the video vehicle data, and perform double-base matching in the radio frequency node linked list. If the match is successful, the relative distance value stored in the radio frequency node linked list of the vehicle at the current moment is extracted, and the average value of the current relative distance value and the positioning trigger threshold recorded last time is taken as the new positioning trigger threshold of the radio frequency antenna and saved.
[0059] In the present invention, further, the RF module also includes a RF node polling thread, which is used to check the RF nodes in sequence starting from the head of the RF node linked list and update the node status. When the relative distance recorded in the RF node linked list meets the new positioning trigger threshold of the RF antenna, the RF node polling thread notifies the message processing thread and generates a capture instruction and sends it to the video module, and the video module realizes the capture of the vehicle for evidence.
[0060] In this embodiment, the working principle is:
[0061] The RF inventory thread is used to create or update nodes for periodic inventory, record vehicle information and calculate relative distances, and store them in the RF node linked list in the form of linked list nodes.
[0062] When a non-motor vehicle passes the trigger line in the video frame according to the drawn lane line, the active identification thread obtains the electronic tag image of the vehicle and identifies it, obtains the unique video license plate string of the vehicle, and sends the data to the message processing thread. The message processing thread first removes Chinese characters from the video license plate string, retains only numbers and letters for matching, obtains the video string to be matched, and polls the RF node list according to the video string to be matched. When the same rate of the RF string in the RF node list and the video string to be matched is greater than the set value, it is considered that the dual-base matching is successful, and the relative distance value stored in the RF node list of the vehicle at the current moment is extracted. The average of this relative distance value and the last recorded positioning trigger threshold is taken as the new positioning trigger threshold of the RF antenna and saved. The frequency node polling thread starts from the head of the RF node list and checks the RF nodes in turn to update the node status.
[0063] When the non-motor vehicle travels to the distance triggered by the new positioning of the RF antenna, that is, when the relative distance recorded in the RF node linked list meets the new positioning trigger threshold of the RF antenna, the RF node polling thread notifies the message processing thread and generates a capture instruction and sends it to the passive capture thread to realize the capture of the vehicle for evidence collection.
[0064] In another embodiment provided by the present invention, a non-motor vehicle tag positioning device based on video assistance is also provided, including a camera, a radio frequency antenna and a controller. The controller adopts a non-motor vehicle tag positioning control system based on video assistance. The camera and the radio frequency antenna are electrically connected to the controller. The inventory range of the radio frequency antenna is larger than the field of view of the camera. When a non-motor vehicle carrying a radio frequency tag enters the inventory range of the radio frequency antenna, the controller updates the relative distance in real time. When the radio frequency tag reaches the camera frame, the camera takes a picture of the radio frequency tag, and the positioning trigger threshold is determined after processing by the controller. When the non-motor vehicle travels to the position where the positioning trigger threshold is located, the controller notifies the camera to capture and obtain the evidence information of this non-motor vehicle.
[0065] like Figure 3 The figure shows the deployment diagram of the device. This deployment method can ensure that non-motorized vehicles carrying RFID tags can be captured by the RFID antenna before entering the camera's field of view, and the relative distance can be updated in real time. When the vehicle drives to the video recognition point, the RF module can regard this position as the RF distance trigger point, that is, the relative distance at this time is regarded as the positioning trigger threshold of the RF antenna in the controller. The whole process can automatically correct the RF trigger position in a more precise direction during the subsequent actual use of the device.
[0066] In summary, the method described in the present invention can automatically correct the RF positioning trigger threshold using the video trigger line, greatly simplifying the deployment of RF road equipment. It can make up for the stability of RF positioning triggering through video, and at the same time, make up for the problem of video underreporting in complex situations of non-motor vehicles through RF positioning triggering.
[0067] The above description is a detailed description of the preferred feasible embodiments of the present invention, but the embodiments are not intended to limit the scope of the patent application of the present invention. All equivalent changes or modified changes completed under the technical spirit suggested by the present invention should fall within the patent scope covered by the present invention.
Claims
1. A video-assisted non-motor vehicle tag positioning method, characterized in that: include Step S0: Periodically count the electronic tags. Each round of inventory creates or updates the radio frequency node list to record vehicle information and calculates the relative distance between the electronic tag and the radio frequency antenna. Step S1: Acquire video vehicle data; Step S2: extract the video license plate number string in the video vehicle data, and perform a double-base match in the radio frequency node list. If the match is successful, extract the relative distance value stored in the radio frequency node list of the vehicle at the current moment; Step S3: Correcting the positioning trigger threshold of the radio frequency antenna according to the relative distance value; Step S4: starting from the head of the radio frequency node linked list, check and update the status of each node in turn; Step S5: When the relative distance recorded in the radio frequency node linked list meets the trigger threshold of the new positioning of the radio frequency antenna, a capture instruction is generated and sent to the camera to realize capture and evidence collection.
2. The video-assisted non-motor vehicle tag positioning method according to claim 1 is characterized in that: The correction method in step S3 is to correct the positioning trigger threshold of the radio frequency antenna by the relative distance value: The average value of the relative distance this time and the positioning trigger threshold recorded last time is taken as the new positioning trigger threshold of the RF antenna and saved.
3. The video-assisted non-motor vehicle tag positioning method according to claim 1 is characterized in that: The step S2 includes Remove Chinese characters from the video license plate string to obtain the video string to be matched, and poll the RF node list based on the video string to be matched. When the similarity rate between the RF string in the RF node list and the video string to be matched is greater than the set value, it is considered a successful match.
4. A video-assisted non-motor vehicle tag positioning system, characterized in that: The invention comprises a video module and a radio frequency module electrically connected to the video module, wherein the radio frequency module comprises a radio frequency inventory thread and a message processing thread, wherein the inventory thread is used for periodic inventory creation or updating of nodes, recording vehicle information and calculating relative distances and storing the same in the radio frequency node linked list in the form of linked list nodes, wherein the message processing thread is used for receiving video vehicle data of the video module, extracting the video license plate number character string in the video vehicle data, and performing double base matching in the radio frequency node linked list, and if the matching is successful, extracting the relative distance value stored in the radio frequency node linked list of the vehicle at the current moment, taking the average value of the relative distance value and the positioning trigger threshold recorded last time as the new positioning trigger threshold of the radio frequency antenna and saving the average value, wherein the radio frequency module further comprises a radio frequency node polling thread, wherein the radio frequency node polling thread is used for checking radio frequency nodes in sequence from the linked list head of the radio frequency node linked list, updating the node status, and when the relative distance recorded in the radio frequency node linked list meets the new positioning trigger threshold of the radio frequency antenna, the radio frequency node polling thread notifies the message processing thread and generates a capture instruction and sends it to the video module, wherein the video module realizes capturing and collecting evidence of the vehicle.
5. The video-assisted non-motor vehicle tag positioning system according to claim 4 is characterized in that: The video module includes an active recognition thread and a passive capture thread. The active recognition thread is used to control the camera to actively obtain video vehicle data and input the data into the message processing thread. The passive capture thread is used to control the camera to capture the vehicle according to the capture instruction output by the message processing thread.
6. The video-assisted non-motor vehicle tag positioning system according to claim 5, characterized in that: The RF inventory thread uses the tag identification number in the video vehicle data as a unique identifier to distinguish different tags. For the tags counted for the first time, a new RF node is applied for, the data is copied and inserted into the RF node list, and then the node acquisition time is updated; For existing nodes, only update the acquisition time.
7. A video-assisted non-motor vehicle tag positioning device, characterized in that: It includes a camera, a radio frequency antenna and a controller. The controller adopts a non-motor vehicle tag positioning system based on video assistance as described in any one of claims 4-6. The camera and the radio frequency antenna are electrically connected to the controller. The inventory range of the radio frequency antenna is larger than the field of view of the camera. When a non-motor vehicle equipped with a radio frequency tag enters the inventory range of the radio frequency antenna, the controller updates the relative distance in real time. When the radio frequency tag reaches the camera frame, the camera takes a picture of the radio frequency tag, and determines the positioning trigger threshold after processing by the controller. When the non-motor vehicle travels to the position where the positioning trigger threshold is located, the controller notifies the camera to capture and obtain the evidence information of the non-motor vehicle.
