Real-Time Traffic Vehicle Tracking Based on Improved MoG Background Extraction and Motion Segmentation

摘要：

A new method for real-time detection and tracking of multiple moving vehicles from traffic video is proposed. This method first uses MoG and texture based model to extract foreground from the scene, then detect moving targets using a modified version of timed motion history image (tMHI), and finally uses Kalman prediction filter to track these targets, which the full moving trajectories of the targets are obtained. Experiments on the real traffic scenes show that the method has good real-time performance and robustness against disturbance factors for outdoor traffic surveillance. Besides, it greatly improves the effects for detection in case of vehicle occlusion.

作者: Zhenshen Qu Mengmeng Yu Junxue Liu

作者单位: Harbin Insitute of Technology,Harbin,150080 China.Zhenshen Qu is the corresponding author. Harbin Insitute of Technology.He is now with theHik Vision Company,Hangzhou,310012 China

会议类型: 国际会议

会议名称: The 3rd International Symposium on Systems and Control in Aeronautics and Astronautics(第三届航空航天系统与控制国际会议 ISSCAA 2010)

会议地点: 哈尔滨

会议语种:英文

页码: 654-657

在线出版日期: 2010-01-08（万方平台首次上网日期，不代表论文的发表时间）