A system and method for generating high point AR video tags based on ETC data

Abstract

This invention belongs to the technical fields of ETC communication, high-precision AR augmented reality, high-point cameras, and ETC checkpoint linkage. Specifically, it relates to a system and method for generating high-point AR video tags based on ETC data. This solution uploads vehicle data identified by ETC checkpoints to high-point videos for analysis and full utilization, supplementing the information in the high-point videos and reducing information acquisition costs. Simultaneously, it uses continuous comparison of video frames to determine the movement trajectory of the same object in different frames, thereby binding AR license plate tags. Other detailed vehicle information can also be bound in this way.

Description

Technical Field

[0001] This invention belongs to the technical fields of ETC communication, high-precision AR augmented reality, high-point camera and ETC checkpoint linkage, and specifically relates to a system and method for generating high-point AR video tags based on ETC data. Background Technology

[0002] Currently, due to the limited resolution of high-point cameras and the long time required for long-distance zoom positioning, they cannot simultaneously identify multiple vehicle license plates. Therefore, high-point cameras can generally only identify coarse-grained information such as vehicle images, size, and color. As a result, high-point cameras generally require vehicles to have their own communication smart devices to upload data.

[0003] Currently, high-point cameras have long zoom times, making it impossible to quickly identify detailed vehicle data such as license plate numbers, or to zoom in to locate fast-moving vehicles. Summary of the Invention

[0004] To address the aforementioned shortcomings, this invention provides a system and method for generating high-point AR video tags based on ETC data. It fully utilizes information acquired by already deployed vehicle-mounted OBU devices and roadside equipment, summarizing and reusing it to improve the coverage of high-point AR license plate tags or other detailed vehicle information, while reducing technical implementation costs and deployment costs.

[0005] This invention is achieved through the following technical solution:

[0006] A system for generating high-point AR video tags based on ETC data includes: an OBU vehicle-mounted device, an ETC roadside device, an ETC checkpoint camera, a high-point camera, and a high-point camera backend system;

[0007] The OBU (On-Board Unit) is used to send relevant vehicle information to the ETC (Electronic Toll Collection) system for data exchange.

[0008] ETC roadside equipment is used to acquire ETC data information to complete transactions and forward the vehicle's structured data to the high-point camera backend system;

[0009] ETC checkpoint camera is used to identify structured data and vehicle images of vehicles in the first lane, and uploads the structured data and vehicle images to the high-point camera backend system via fiber optic or wireless communication module.

[0010] The high-point camera backend system is used to identify vehicle features within the detection range of each ETC checkpoint camera through video. Vehicles passing through the ETC checkpoint are sorted according to their lane travel direction based on these vehicle features to obtain a vehicle information sequence. The backend system sorts the received structured data by timestamp and matches it with the vehicle information sequence identified from the video at the same timestamp. When the structured data matches a segment of the vehicle information sequence, the system obtains the vehicle pixel matrix from the high-point camera video and the license plate AR tag from the structured data.

[0011] A high-point camera is used to acquire high-point video footage and display the AR tags generated by the backend system in the video footage, which are then bound to the vehicle's pixel matrix.

[0012] Preferably, the structured data includes vehicle license plate number, vehicle size, and vehicle color.

[0013] Preferably, the vehicle features include vehicle size and vehicle color.

[0014] Preferably, vehicles are classified according to size into small cars, medium cars, large cars, and giant cars.

[0015] Preferably, image recognition is continuously performed on the high-point video footage to distinguish the pixel matrix of a single vehicle, and the pixel matrices of two consecutive frames of the video footage are subtracted. When the difference is less than or equal to a threshold, the two pixel matrices are determined to be images of the same vehicle and are labeled with the same AR tag.

[0016] This invention relates to a method for generating high-point AR video tags based on ETC data, comprising the following steps:

[0017] Send relevant vehicle information to ETC for data exchange;

[0018] When data from ETC roadside devices can be obtained, the structured data of vehicles can be acquired using the existing ETC roadside devices; when data from ETC roadside devices cannot be obtained, a first camera is installed separately for each ETC lane to identify the structured data of vehicles in the first lane.

[0019] Structured data and vehicle images are uploaded to the high-point camera backend system via fiber optic or wireless communication modules.

[0020] By identifying vehicle features within the detection range of each first camera through video recognition, vehicles passing through the ETC checkpoint are sorted according to their lane travel direction based on these vehicle features to obtain a vehicle information sequence.

[0021] The structured data is sorted according to timestamps and matched with the vehicle information sequence identified from the video at the same timestamp. When the structured data matches a segment of data in the vehicle information sequence, the vehicle pixel matrix in the video captured by the second camera and the license plate AR tag in the structured data are obtained.

[0022] The video feed from the second camera is acquired, and the AR tag is displayed in the video feed and bound to the vehicle pixel matrix.

[0023] Preferably, the structured data includes vehicle license plate number, vehicle size, and vehicle color.

[0024] Preferably, the vehicle features include vehicle size and vehicle color.

[0025] Preferably, vehicles are classified according to size into small cars, medium cars, large cars, and giant cars.

[0026] Preferably, the video frame is continuously subjected to image recognition to distinguish the pixel matrix of a single vehicle, and the pixel matrices of two consecutive frames of the video frame are subtracted. When the difference is less than or equal to a threshold, the two pixel matrices are determined to be images of the same vehicle and are labeled with the same AR tag.

[0027] This invention makes full use of existing ETC checkpoints and uses emerging technologies such as AR, image recognition, and video analysis to obtain detailed information about a large number of vehicles at a low cost from a high vantage point. It also binds AR tags to the vehicle pixel matrix, enabling the high-point video to obtain AR license plate tags for all vehicles at a low cost. Information about other vehicles can also be obtained in this way. Detailed Implementation

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] A system and method for acquiring AR floating tags for vehicles at high points based on linked ETC checkpoint data. The system requires the following equipment: OBU on-board unit (OBU) tag, ETC roadside equipment, ETC checkpoint camera, high-point camera, and high-point camera backend system; among which,

[0030] OBU (On-Board Unit): Sends relevant vehicle information to ETC (Electronic Toll Collection) for data exchange.

[0031] ETC roadside equipment: acquires ETC data information to complete transactions and forwards some structured vehicle data to the high-point camera backend system.

[0032] ETC checkpoint camera: Through image recognition technology, it can quickly identify structured data and vehicle images such as license plate numbers, vehicle size, and vehicle color of vehicles in a specific lane, and upload the structured data and vehicle images to the high-point camera backend system through fiber optic or wireless communication modules.

[0033] High-point camera backend system: The backend system identifies vehicle features within the detection range of each ETC checkpoint through video, sorting vehicles passing through the ETC checkpoint according to lane travel direction and then by vehicle size and color. The backend system sorts the received structured vehicle data for a specific lane by timestamp and matches it with the vehicle information sequence identified from images at the same timestamp. When the structured data uploaded by the ETC checkpoint matches a segment of data in the vehicle sequence parsed from the video, the vehicle pixel matrix in the video can be bound to the license plate AR tag.

[0034] High-point camera: Captures video footage from high vantage points and merges the AR tags generated by the backend system with the video footage.

[0035] This invention obtains data information from existing ETC roadside devices or adds new ETC checkpoint cameras. The ETC roadside devices in different lanes will upload structured data such as vehicle license plates, vehicle dimensions, vehicle colors, timestamps, and vehicle images to the high-point camera backend system.

[0036] This invention uses a backend system to divide different lanes at ETC checkpoints and matches the corresponding license plate numbers and other detailed information of vehicles passing through the ETC checkpoints within the line of sight from a high point, based on timestamps, vehicle size, and vehicle color.

[0037] Furthermore, when data streams from ETC roadside devices can be obtained, structured data such as vehicle license plates, vehicle dimensions, and vehicle colors can be acquired using existing ETC roadside devices. When data from roadside devices cannot be obtained, an ETC camera is installed in each ETC lane. Image recognition technology is used to quickly identify structured data such as vehicle license plates, vehicle dimensions, and vehicle colors in specific lanes, and this structured data is uploaded to the high-point camera's backend system via fiber optic or wireless communication modules.

[0038] The high-point camera backend system divides the detection range of different ETC checkpoint cameras. The backend system identifies vehicle characteristics within the detection range of each ETC checkpoint through video recognition, sorts vehicles by size and color according to lane travel direction, and classifies vehicles by size into small cars, medium cars, large cars, giant cars, etc.

[0039] The backend system will receive structured vehicle data for a specific lane, sort it by timestamp, and match it with the vehicle information sequence identified from the image at the same timestamp. When the structured data uploaded by the ETC card matches a segment of data in the vehicle sequence parsed from the video, the pixel matrix of each vehicle in the video can be bound to the corresponding AR license plate label.

[0040] For example, when a vehicle leaves the ETC checkpoint direction, two large red vehicles appear in the lane, followed by a small white vehicle, and then a medium-sized blue vehicle. While there's a certain probability of color and vehicle type repeating, the random combination of vehicle order is extremely difficult to repeat and continues continuously. With the sequential combination of vehicle color types, a specific group of vehicles within the ETC checkpoint's detection range can be quickly matched. Furthermore, based on the license plate timestamp, the specific license plates of adjacent vehicles of the same color and type can be distinguished. The vehicle with the earlier timestamp is definitely the first in that combination to enter the checkpoint's detection range according to the lane's direction of travel, thus allowing for license plate assignment.

[0041] The high-point video feed continuously performs image recognition to distinguish the pixel matrix of individual vehicles. It then subtracts the pixel matrix of a vehicle from the pixel matrix of two consecutive frames of the video. If the difference is within a certain range, the two pixel matrices are determined to be images of the same vehicle, and the same AR vehicle tag is used. This allows the tag to move with the pixel array, generating a high-point AR floating tag. When a vehicle changes lanes or overtakes, the AR floating tag from the high-point camera automatically becomes invalid.

[0042] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of a method for generating high-point AR video tags based on ETC data.

[0043] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a method for generating high-point AR video tags based on ETC data.

[0044] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, or improvements made without departing from the spirit and scope of the present invention are also within the scope of protection of the present invention.

Claims

1. A system for generating high-point AR video tags based on ETC data, characterized in that, include: OBU on-board unit, ETC roadside unit, ETC checkpoint camera, high-point camera and high-point camera back-end system; The OBU (On-Board Unit) is used to send relevant vehicle information to the ETC (Electronic Toll Collection) system for data exchange. ETC roadside equipment is used to acquire ETC data information to complete transactions and forward the vehicle's structured data to the high-point camera backend system; ETC checkpoint camera is used to identify structured data and vehicle images of vehicles in the first lane, and uploads the structured data and vehicle images to the high-point camera backend system via fiber optic or wireless communication module. The high-point camera backend system is used to identify vehicle features within the detection range of each ETC checkpoint camera through videos captured by high-point cameras. Vehicles passing through the ETC checkpoint are sorted according to their lane travel direction and the vehicle features to obtain a vehicle information sequence. The backend system sorts the received structured data by timestamp and matches it with the vehicle information sequence identified from videos at the same timestamp. When the structured data matches a segment of the vehicle information sequence, the system obtains the vehicle pixel matrix from the high-point camera video and the license plate AR tag from the structured data. A high-point camera is used to acquire high-point video footage and display the AR tags generated by the backend system in the video footage, which are then bound to the vehicle's pixel matrix.

2. The system for generating high-point AR video tags based on ETC data according to claim 1, characterized in that, The structured data includes vehicle license plate number, vehicle size, and vehicle color.

3. The system for generating high-point AR video tags based on ETC data according to claim 1, characterized in that, The vehicle characteristics include vehicle size and vehicle color.

4. The system for generating high-point AR video tags based on ETC data according to claim 3, characterized in that, Based on vehicle size, they are classified into small cars, medium cars, large cars, and giant cars.

5. The system for generating high-point AR video tags based on ETC data according to claim 1, characterized in that, The system continuously performs image recognition on high-angle video footage to distinguish the pixel matrix of individual vehicles. It also subtracts the pixel matrices of two consecutive frames of the video footage. If the difference is less than or equal to a threshold, the two pixel matrices are determined to be images of the same vehicle and are labeled with the same AR tag.

6. A method for generating high-point AR video tags based on ETC data, characterized in that, Includes the following steps: Send relevant vehicle information to ETC for data exchange; When data from ETC roadside devices is available, structured vehicle data can be obtained using existing ETC roadside devices. When data from ETC roadside equipment cannot be obtained, a separate first camera is installed in each ETC lane to identify the structured data of vehicles in the first lane; Structured data and vehicle images are uploaded to the high-point camera backend system via fiber optic or wireless communication modules. The system identifies vehicle features within the detection range of each first camera by capturing video from a high-point camera. Vehicles passing through the ETC checkpoint are sorted according to their lane travel direction based on these vehicle features to obtain a vehicle information sequence. The structured data is sorted according to timestamps and matched with the vehicle information sequence identified from the video at the same timestamp. When the structured data matches a segment of data in the vehicle information sequence, the vehicle pixel matrix in the video captured by the second camera and the license plate AR tag in the structured data are obtained. The video feed from the second camera is acquired, and the AR tag is displayed in the video feed and bound to the vehicle pixel matrix.

7. The method for generating high-point AR video tags based on ETC data according to claim 6, characterized in that, The structured data includes vehicle license plate number, vehicle size, and vehicle color.

8. The method for generating high-point AR video tags based on ETC data according to claim 6, characterized in that, The vehicle characteristics include vehicle size and vehicle color.

9. The method for generating high-point AR video tags based on ETC data according to claim 8, characterized in that, Based on vehicle size, they are classified into small cars, medium cars, large cars, and giant cars.

10. The method for generating high-point AR video tags based on ETC data according to claim 6, characterized in that, The video footage is continuously subjected to image recognition to distinguish the pixel matrix of a single vehicle. The pixel matrices of two consecutive frames of the video footage are subtracted. If the difference is less than or equal to a threshold, the two pixel matrices are determined to be images of the same vehicle and are labeled with the same AR tag.