- 期刊
Vehicle Flow Counting System Based on Traffic Surveillance Video
摘要
With the rapid development of intelligent traffic surveillance systems, traffic monitoring has become automatic and intelligent. Traffic flow detection is an important part of Intelligent Transportation System (ITS), and it plays an important role in traffic management and monitoring. In this paper, we propose and implement a traffic surveillance system for vehicle flow detection and counting. The system we proposed consists of three parts: target detection, target tracking and target counting. Based on background modeling, we detect the foreground target and Mean-shift color histogram matching algorithm has been adopted to track the target. Then we set the detection line to count the target in the region of interest (ROI). The experiment results show that our proposed system has good performance and high accuracy in real traffic video.