Real-Time Human Motion Classification with Visual Information.
Shigeyoshi Hiratsuka, Kohtaro Ohba, Shinya KAJIKAWA, Hikaru Inooka · TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C · 1998
This paper describes a real-time system to classify several human motions using the principle component analysis, i.e. eigen space method. In this paper, we proposed to utilize the silhouette images instead of original black/white images, which can solve the drawback of the original eigen space technique. And also to make a stable correspondence between dictionary points and input points in the eigen space, a spline function had been used. Experimental results show the validity of this proposed method.