The aim of this paper is to explore intrinsic geometric methods of recovering the three dimensional motion of a moving camera from a sequence of images. Generic similarities between the discrete approach and the differential approach are revealed through a parallel development of their analogous motion estimation theories. We begin with a brief review of the (discrete) essential matrix approach...

In the past decades, most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active object recognition. In this context, there are several unique problems to be solved, such as the fusion of views and the selection of an optimal next viewpoint. In this paper we present an approach to solve the problem of choosing opt...

In this paper, we propose a new method for synthesizing player viewpoint images from multiple view videos in tennis. Our method is divided into two key techniques: virtual-view synthesis and player’s viewpoint estimation. In the former, we divide the object tennis scene into sub regions, which are background, tennis court ground, players, and ball. For each sub region, a virtual viewpoint image...