The research of gait independent of view angle has become an urgent problem to be solved for gait recognition. In this paper, we propose a gait recognition method that the subject can walk at an arbitrary angle. The gait is detected through background subtraction technique. The contour is represented by a novel approach which includes not only the spatial body contour but also the temporal information. To prove be independent of view angle, the relationship model of the walking azimuth angle and the reference view has been modeled. We transform the walking angle to the most similar canonical views angle. Three canonical views angles are adopted in this paper. The errors which come from transformation when the walk angle is far from the only canonical view will greatly be reduced. We test our method on multi-views database. The correct classification ratios show that our method is a nice try.
展开▼
