Real-time Vehicle Detection and Tracking Based on YOLOv3 Pruning Model
Mingxiu Lin, Jiayi Li, Jiaxin Zhang, Xinghui Li, Shiyao Ji, Yunli He · 2021
Real-time detection and tracking of vehicles is very important in the field of automatic driving. In this paper, a YOLOv3 network based on pruning algorithm is proposed to solve the problem of real-time vehicle detection. Through reducing the number of channels and layers in the backbone network, the computation of the model is reduced. And thus, the rate of detection is greatly increased. On the basis of vehicle detection, the real-time tracking of multiple vehicle targets is completed by using Kalman filter algorithm for prediction and Hungarian algorithm for data association. The experimental results show that compared with the original YOLOv3 network, the model size is compressed by 95% to 11.25 MB and the detection rate is doubled to 128.1 frames/s while the average accuracy is basically unchanged. The detection and tracking frame rate of the whole algorithm is 18fps, and the recall is 98.5%. The algorithm also has strong robustness on complex traffic roads, and can basically realize real-time detection and tracking of road vehicles.