Tracking and Calculating Speed of Mixing Vehicles Using YOLOv4 and DeepSORT

Abstract

Today, strong development of socio-economic has promoted participation in traffic. As a result, traffic management is becoming more and more difficult. To effectively solve the problem, artificial intelligence (AI) applications are applied for the improvement of urban traffic management and administration. Therefore, we propose an intelligent algorithm for monitoring and detecting vehicles. We use data collected from cameras and apply deep learning technology to track objects in the paper. The proposed algorithm uses YOLOv4 combined with DeepSORT for tracking and calculating the speed of detected vehicles. Results show that the proposed algorithm improves accuracy up to 95% which is suitable to apply for real applications.