In vehicle detection and tracking methods based on roadside cameras, due to factors such as motion blur, vehicle occlusion, and target scale changes in the video, problems such as missed detection, false detection, and low positioning accuracy may occur during vehicle detection and tracking. This paper proposes to use the improved target detection model YOLOv5s as the target detector, then combined with the classical Deep SORT target tracking method, to achieve end-to-end vehicle detection and tracking. By integrating the attention mechanism with the detection network, and modifying the loss function, the ability of the model to extract features is strengthened, and the final vehicle detection accuracy is 96.7%. During tracking, the vehicle IDs are reduced to 28 times and the operating speed reaches 32 Hz.
Vehicle recognition and tracking method based on roadside perception
Third International Conference on Computer Science and Communication Technology (ICCSCT 2022) ; 2022 ; Beijing,China
Proc. SPIE ; 12506
2022-12-28
Conference paper
Electronic Resource
English
Roadside parking vehicle track recognition method and system based on multi-sensor perception
European Patent Office | 2021
|Method for vehicle supervision based on roadside equipment, roadside equipment and vehicle
European Patent Office | 2022
|Method for evaluating traffic participant perception capability based on roadside perception system
European Patent Office | 2022
|