CN-121982659-A - Vehicle information identification method and device, electronic equipment and storage medium

CN121982659ACN 121982659 ACN121982659 ACN 121982659ACN-121982659-A

Abstract

The application provides a vehicle information identification method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of receiving a vehicle image sent by target shooting equipment arranged at a target bayonet; the method comprises the steps of carrying out image analysis on a vehicle image to obtain first vehicle information of a target vehicle in the vehicle image, wherein the first vehicle information comprises a license plate number, a vehicle type, a driving lane and current time of the target vehicle, determining an effective recognition area of a target shooting device on a vehicle driving road, obtaining second vehicle information of a logic vehicle recognized by a road vibration sensing device in the effective recognition area under the current time, wherein the second vehicle information comprises an estimated vehicle type and an estimated lane of the logic vehicle, determining the target logic vehicle in the logic vehicle according to the first vehicle information and the second vehicle information, and binding the license plate number with the target logic vehicle. The application can improve the accuracy and reliability of vehicle information identification and reduce the identification cost of vehicle information.

Inventors

MA TENGFEI
DONG ZHIYONG
ZHAO PENG
CUI YONGHUI

Assignees

武汉理工光科股份有限公司

Dates

Publication Date: 20260505
Application Date: 20251230

Claims (10)

1. The vehicle information identification method is characterized by being applied to a multi-source perception data fusion system, wherein the multi-source perception data fusion system comprises a road surface vibration perception device and a visual perception device; the road vibration sensing device is used for identifying vehicle information according to road vibration, and the visual sensing device comprises shooting equipment arranged on a bayonet on a road on which the vehicle runs; The method comprises the following steps: receiving a vehicle image sent by target shooting equipment arranged at a target bayonet; image analysis is carried out on the vehicle image to obtain first vehicle information of a target vehicle in the vehicle image, wherein the first vehicle information comprises a license plate number, a vehicle type, a driving lane and current time of the target vehicle; Determining an effective identification area of the target shooting equipment on the running road surface of the vehicle; Acquiring second vehicle information of the logic vehicle identified by the road surface vibration sensing device in the effective identification area at the current time, wherein the second vehicle information comprises an estimated vehicle type and an estimated lane of the logic vehicle; And identifying a target logic vehicle in the logic vehicles according to the first vehicle channel information and the second vehicle channel information, and binding the license plate number with the target logic vehicle.
2. The vehicle information identification method according to claim 1, wherein the logical vehicle includes a plurality of the logical vehicles, and the identifying the target logical vehicle from the first lane information and the second lane information includes: respectively calculating the difference value between the estimated lane of each logic vehicle and the driving lane; taking the logic vehicle with the smallest difference value as a candidate logic vehicle; Taking the candidate logic vehicle as the target logic vehicle in the case that the number of the candidate logic vehicles is 1; comparing the estimated vehicle type of each candidate logic vehicle with the vehicle types respectively under the condition that the number of the candidate logic vehicles is larger than 1; and determining the target logic vehicle in the candidate logic vehicles according to the comparison result.
3. The vehicle information identification method according to claim 1 or 2, characterized in that in a case where the road surface vibration sensing device does not identify the logical vehicle in the effective identification area at the present time, the method further includes: And generating a new logic vehicle in the road surface vibration sensing device according to the first vehicle information, wherein the road surface vibration sensing device identifies the vehicle information of the new logic vehicle.
4. The vehicle information identification method according to claim 1, characterized in that the determining of the effective identification area of the target photographing apparatus on the vehicle running surface includes: acquiring an absolute mileage stake mark of the target bayonet on the vehicle driving road surface, wherein the absolute mileage stake mark represents the distance from the target bayonet to the starting point of the vehicle driving road surface; And determining the effective identification area according to the absolute mileage stake marks and the shooting range of the target shooting equipment.
5. The method according to claim 4, wherein the road surface vibration sensing device includes an optical fiber laid under a road surface on which the vehicle is traveling, the optical fiber including a plurality of grid numbers, and the acquiring the second vehicle information of the logical vehicle recognized by the road surface vibration sensing device at the present time and in the effective recognition area includes: Establishing a mapping relation table of the absolute mileage stake marks of each grid number and the vehicle running road surface; Determining a target grid number corresponding to the effective identification area in the mapping relation table; Detecting whether vibration information sent by the target grid number is received or not in the current time; And acquiring the second vehicle information according to the vibration information when the vibration information is received.
6. The vehicle information identification method according to claim 1, characterized by further comprising, before the acquisition of the second vehicle information of the logical vehicle identified by the road surface vibration sensing device at the current time and within the effective identification area: Rounding the current time according to a preset duration; The obtaining second vehicle information of the logic vehicle identified by the road surface vibration sensing device in the effective identification area at the current time includes: and acquiring the second vehicle information which is recognized by the road surface vibration sensing device in the effective recognition area under the current time after rounding.
7. The vehicle information identification method according to claim 1, characterized by further comprising, after binding the license plate number with the target logical vehicle: Correcting the target estimated vehicle type corresponding to the target logic vehicle according to the vehicle type; And correcting the target estimated lane corresponding to the target logic vehicle according to the driving lane.
8. The vehicle information identification device is characterized by being applied to a multi-source perception data fusion system, wherein the multi-source perception data fusion system comprises a road surface vibration perception device and a visual perception device; the road vibration sensing device is used for identifying vehicle information according to road vibration, and the visual sensing device comprises shooting equipment arranged on a bayonet on a road on which the vehicle runs; The vehicle information identification device comprises a receiving module, an analysis module, a determination module, an acquisition module and an identification module; The receiving module is used for receiving a vehicle image sent by target shooting equipment arranged at a target bayonet; The analysis module is used for carrying out image analysis on the vehicle image to obtain first vehicle information of a target vehicle in the vehicle image, wherein the first vehicle information comprises license plate numbers, vehicle types, driving lanes and current time of the target vehicle; the determining module is used for determining an effective identification area of the target shooting equipment on the vehicle driving road surface; the acquisition module is used for acquiring second vehicle information of the logic vehicle which is identified by the road surface vibration sensing device at the current time and in the effective identification area, wherein the second vehicle information comprises an estimated vehicle type and an estimated lane of the logic vehicle; The identification module is used for identifying a target logic vehicle in the logic vehicles according to the first vehicle road information and the second vehicle road information, and binding the license plate number with the target logic vehicle.
9. An electronic device comprising a processor and a memory, wherein the memory is configured to store instructions, the processor configured to invoke the instructions in the memory, to cause the electronic device to perform the vehicle information identification method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions which, when run on an electronic device, cause the electronic device to perform the vehicle information identification method of any one of claims 1 to 7.

Description

Vehicle information identification method and device, electronic equipment and storage medium Technical Field The application relates to the technical field of intelligent traffic and optical fiber sensing, in particular to a vehicle information identification method, a device, electronic equipment and a storage medium. Background Along with the rapid development of the vehicle-road cooperation and automatic driving technology, the intelligent expressway has higher requirements on the global, all-weather and high-precision traffic perception capability. The current mainstream perception scheme mainly relies on a road side view and radar system (such as a high-definition camera, a laser radar and a millimeter wave radar) to detect, identify and track a vehicle target by transmitting and receiving electromagnetic waves or analyzing image information. However, the scheme has obvious limitations in large-scale application, namely, 1, the cost is high, the purchase, deployment, maintenance and data processing costs of the high-performance radar and the high-definition camera are high, continuous full coverage is difficult to realize in a long-distance expressway network, 2, the environment is sensitive, the perception performance is obviously influenced by severe weather such as illumination, rain, snow, fog, dust and the like, the visibility is reduced or the signal attenuation is easy to cause false alarm and the false alarm rate is easy to rise, 3, the monitoring blind area is limited by the detection distance and the visual angle, long-distance seamless tracking is difficult to realize, and the perception blind area is easy to appear in complex road sections such as overpasses, tunnels and the like. Therefore, a new vehicle information identification method is needed to solve the above-mentioned problems. Disclosure of Invention In view of the above, the present application provides a vehicle information identification method, apparatus, electronic device, and storage medium, which can improve accuracy and reliability of vehicle information identification, and can reduce identification cost of vehicle information. The first aspect of the embodiment of the application provides a vehicle information identification method which is applied to a multi-source perception data fusion system, wherein the multi-source perception data fusion system comprises a road vibration perception device and a visual perception device, the road vibration perception device is used for identifying vehicle information according to road vibration, the visual perception device comprises shooting equipment of a bayonet arranged on a vehicle driving road, the method comprises the steps of receiving a vehicle image sent by target shooting equipment arranged on a target bayonet, carrying out image analysis on the vehicle image to obtain first vehicle information of a target vehicle in the vehicle image, the first vehicle information comprises a license plate number, a vehicle type, a driving lane and current time of the target vehicle, determining an effective identification area of the target shooting equipment on the vehicle driving road, obtaining second vehicle information of a logic vehicle identified by the road vibration perception device in the effective identification area under the current time, wherein the second vehicle information comprises the estimated vehicle type and the lane of the logic vehicle, identifying the target license plate number in the vehicle image according to the first road information and the second road information, and binding the target vehicle in the logic vehicle with the logic vehicle. In one possible implementation manner, the logic vehicles comprise a plurality of logic vehicles, the step of identifying target logic vehicles in the logic vehicles according to the first lane information and the second lane information comprises the steps of calculating the difference value between the estimated lane and the driving lane of each logic vehicle respectively, taking the logic vehicle with the smallest difference value as a candidate logic vehicle, taking the candidate logic vehicle as the target logic vehicle when the number of the candidate logic vehicles is 1, comparing the estimated vehicle type of each candidate logic vehicle with the vehicle type respectively when the number of the candidate logic vehicles is greater than 1, and determining the target logic vehicle in the candidate logic vehicles according to the comparison result. In one possible implementation, in the case that the road vibration sensing device does not recognize the logic vehicle in the effective recognition area at the current time, the method further includes generating a new logic vehicle in the road vibration sensing device according to the first vehicle information, wherein the road vibration sensing device recognizes the vehicle information of the new logic vehicle. In one possible implementation manner, the determining the