A method of carried object detection based on key posture of silhouette

Abstract

In this paper, we present a novel carried object detection method based on the key postures which is extracted through locating the key point on the gait cycle curve. The key postures which are conducive to detect the carried object are the silhouettes in sequence. Different carried type is corresponding to the different key postures. For each key posture, the deviation between the reference axis and the center line and the variance of the lower-limb width are adopted to represent features. We test our method on two databases. The results show that the method based on key postures can not only reduce the computation, but also represent features very accurately, and our method is effective.