Title :
An Approach to Event Recognition for Visual Surveillance Systems
Author :
Cui, Yaohuan ; Lee, Changwoo
Author_Institution :
Kunsan Int. Univ., Kunsan
Abstract :
In this paper, we propose a new vision based method to recognize the entering and exiting events from video sequences via motion analysis. Without sensors, the proposed approach is invariant to body shape and clothing as a combination of edge detection, motion history image and geometrical characteristic of the human shape in MHI sequences. The proposed method includes several applications such as access control in visual surveillance and computer vision fields.
Keywords :
computer vision; edge detection; image motion analysis; image sequences; video surveillance; MHI sequences; edge detection; event recognition; geometrical characteristic; human shape; motion analysis; video sequence; visual surveillance system; Clothing; History; Humans; Image edge detection; Image sensors; Motion analysis; Sensor phenomena and characterization; Shape; Surveillance; Video sequences;
Conference_Titel :
Future Generation Communication and Networking Symposia, 2008. FGCNS '08. Second International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-3430-5
Electronic_ISBN :
978-0-7695-3546-3
DOI :
10.1109/FGCNS.2008.36
