In this paper, we propose an efficient method for tracking multiple objects, which deals with occlusion situations in an image. We use Shape from silhouettes method to reconstruct...
Koichiro Deguchi, Koji Hamasaki, Taira Nakajima, T...
Abstract. Using silhouettes in uncontrolled environments typically requires handling occlusions as well as changing or cluttered backgrounds, which limits the applicability of most...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
Tracking people using movie sequences is not straightforward because of the human body's articulation and the complexity of a person's movements. In this paper we show ho...
We explore the use of clouds as a form of structured lighting to capture the 3D structure of outdoor scenes observed over time from a static camera. We derive two cues that relate ...