Title :
Dual-camera system for multi-level activity recognition
Author :
Bodor, Robert ; Morlok, Ryan ; Papanikolopoulos, Nikolaos
Author_Institution :
Dept. of Comput. Sci. & Eng., Minnesota Univ., Minneapolis, MN, USA
fDate :
28 Sept.-2 Oct. 2004
Abstract :
This paper describes a dual-camera system intended to accomplish the task of vision-based activity recognition at multiple resolutions. The system is comprised of a wide-angle, fixed field of view camera coupled with a computer-controlled pan/tilt/zoom-lens camera to make detailed measurements of people for activity recognition applications. We demonstrate the use of the system in both indoor and outdoor environments.
Keywords :
cameras; computer vision; control engineering computing; image recognition; computer-controlled pan/tilt/zoom-lens camera; dual-camera system; multilevel activity recognition; multiple resolution; vision-based activity recognition; Application software; Cameras; Computer crime; Computer science; Handicapped aids; Humans; Position measurement; Safety; Surveillance; Transportation;
Conference_Titel :
Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on
Print_ISBN :
0-7803-8463-6
DOI :
10.1109/IROS.2004.1389425
