DocumentCode :
2028988
Title :
Person tracking by integrating optical flow and uniform brightness regions
Author :
Yamane, Tsuyoshi ; Shirai, Yoshiaki ; Miura, Jun
Author_Institution :
Dept. of Computer-Controlled Mech. Syst., Osaka Univ., Japan
Volume :
4
fYear :
1998
fDate :
16-20 May 1998
Firstpage :
3267
Abstract :
This paper describes a method to track a person by integrating two cues, optical flow and uniform brightness regions, where optical flow cannot be obtained. This method works even if tracking with either optical flow or uniform brightness regions may fail. The proposed method has been implemented on a real time image processor with multiple DSPs and successfully tracked a target person using real image sequences
Keywords :
brightness; computer vision; feature extraction; image segmentation; image sequences; motion estimation; object recognition; optical tracking; real-time systems; feature extraction; image processor; image segmentation; image sequences; optical flow; person tracking; real time systems; uniform brightness regions; Brightness; Cameras; Image motion analysis; Image sequences; Integrated optics; Mechanical systems; Motion detection; Optical computing; Optical filters; Target tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation, 1998. Proceedings. 1998 IEEE International Conference on
Conference_Location :
Leuven
ISSN :
1050-4729
Print_ISBN :
0-7803-4300-X
Type :
conf
DOI :
10.1109/ROBOT.1998.680942
Filename :
680942
Link To Document :
بازگشت