Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 2003.07e
- /
- Pages.1883-1886
- /
- 2003
Silhouette-based Gait Recognition for Variable Viewpoint
시점 변화에 강인한 실루엣 기반 게이트 인식
Abstract
Gait is defined as "a manor of walking". It can used as a biometric measure to recognize known persons. Gait is an idiosyncratic feature determined by an individual's weight, stride length, and posture combined with characteristic motion. but its feature extracted from images varies with the viewpoint. In this paper, we propose a gait recognition method using a planer homography, which is robust for viewpoint variation. We represent an individual as key-silhouettes. And we endow key-silhouettes with weight calculated using the characteristic of PCA. Experimental result shows that proposed method is robust for viewpoint variation as images synthesised same viewpoint.
Keywords