DocumentCode :
495245
Title :
Camshift-Based Real-Time Multiple Vehicle Tracking for Visual Traffic Surveillance
Author :
Liu, Zhe ; Chen, Yangzhou ; Li, Zhenlong
Author_Institution :
Res. Center of Intell. Transp. Syst., Beijing Univ. of Technol., Beijing, China
Volume :
5
fYear :
2009
fDate :
March 31 2009-April 2 2009
Firstpage :
477
Lastpage :
482
Abstract :
This paper presents methods for vision-based detection and tracking of vehicles in monocular image sequences of traffic scenes recorded by a stationary camera. The goal of this research is to develop suitable methods for automatic visual traffic surveillance to perform detection, tracking and traffic parameter estimation of multiple vehicles in real time as well as tackle environment illumination changes and vehicle occlusion. Each of detected vehicles is assigned a camshift tracker which can quickly and exactly track object with different size and shape. Experimental results from traffic scenes demonstrate the effectiveness and robustness of the methods.
Keywords :
cameras; computer vision; image sequences; object detection; parameter estimation; real-time systems; road traffic; road vehicles; surveillance; tracking; automatic visual traffic surveillance; camshift-based real-time multiple vehicle tracking; monocular image sequence; stationary camera; traffic parameter estimation; vehicle detection; vision-based detection; Cameras; Image sequences; Layout; Lighting; Object detection; Parameter estimation; Robustness; Shape; Surveillance; Vehicle detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
Type :
conf
DOI :
10.1109/CSIE.2009.423
Filename :
5170581
Link To Document :
بازگشت