Abstract. An N-dimensional image is divided into "object" and "background" segments using a graph cut approach. A graph is formed by connecting all pairs of nei...
An approach to recognise and segment 9 elementary gestures from a video input is proposed and it can be applied to continuous sign recognition. An isolated gesture is recognised b...
This paper presents a system that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squattin...
Object classification in far-field video sequences is a challenging problem because of low resolution imagery and projective image distortion. Most existing far-field classificati...
Abstract. We introduce a novel implicit approach for single object segmentation in 3D images. The boundary surface of this object is assumed to contain two known curves (the constr...