The problem of Simultaneous Localization And Mapping (SLAM) originally arose from the robotics community and is closely related to the problems of camera motion estimation and stru...
We present a fast and robust system for estimating structure
and motion using a stereo pair, with straight lines as
features. Our first set of contributions are efficient algorit...
While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
Abstract. Structure-from-motion (SfM) is an important computer vision problem and largely relies on the quality of feature tracking. In image sequences, if disjointed tracks caused...