Vehicle tracking method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a vehicle tracking method and device, computer equipment and a storage medium. The method comprises the steps: acquiring vehicle driving monitoring videos sent by multiple monitoring equipment; adopting a preset target detection algorithm for a vehicle to detect the vehicle in the vehicle driving monitoring video to obtain feature information of the vehicle, wherein the feature information comprises an image in a boundingbox of the vehicle; extracting vehicle features (featuremaps) from the detection frame image, and carrying out AMOC-RNN time sequence feature fusion to obtain a vehicle feature set collected by each monitoring device; performing similarity comparison on the vehicle features in the vehicle feature set collected by a plurality of monitoring devices installed on the same geographical line; and identifying the same vehicle in the plurality of monitoring devices according to a similarity comparison result so as to track the vehicle. For re-identification and tracking of a plurality of vehicles monitored by a plurality of monitoring devices on a road, a tracking result can be fed back in real time.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, in particular, a vehicle tracking method, device, computer equipment, and storage medium. Background technique [0002] Although the traffic video surveillance system has been able to bring supervision without dead ends, however, in the video, some emergencies and illegal vehicles are driving at high speed and cannot be located at any time. Under the video surveillance screen, they cannot be observed and retrieved by the naked eye on the screen and reported in time. Therefore, the traffic department cannot receive the notification at the first time, resulting in information lag between the escaped traffic accident or the hidden danger of traffic accidents and the traffic management department. When the same vehicle appears in different cameras along the route, it can only be compared manually. It is impossible to send relevant staff to the scene to intercept or track the ...

AI Technical Summary

Problems solved by technology

[0002] Although the traffic video surveillance system has been able to bring supervision without dead ends, however, in the video, some emergencies and illegal vehicles are driving at high speed and cannot be located at any time. Under the video surveillance screen, they cannot be observed and retrieved by the naked eye on the screen and reported in time. , the traffic department cannot receive the notification at the first time, resulting in information lag between the escaped traffic accident or the hidden danger of traffic accidents and the traffic management department

When the same vehicle appears in different cameras along the route, it can only be compared manually

It is impossible to send relevant staff to the scene to intercept or track at the first time

For example, a suspicious vehicle is speeding on a highway extending in all directions, and the direction of travel cannot be determined

If the location of the vehicle cannot be compared in time through the video surveillance screens of different locations, it will lead to information lag

Images