A Deep Learning Approach for Vehicle and Driver Detection on Highway

Abstract

The technology of the detection for vehicle and driver is a popular spot in these ten years. In particular, the driver detection is still a troubled question in the study of public security. In our paper, an algorithm based on YOLOv3 and support vector machine (SVM) is proposed for realizing the detection of vehicles on highway, as well as the detection and binary classification of people in the vehicles, so as to achieve the purpose of distinguishing drivers and passengers and form a one-to-one correspondence between vehicles and drivers. The effectiveness of the algorithm is verified under various complicated highway conditions. Compared with other advanced vehicle and driver detection technologies, the model has a good performance and is robust to road blocking, different attitudes and extreme lighting.