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...
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...
This paper proposes a new registration algorithm, Covariance Driven Correspondences (CDC), that depends fundamentally on the estimation of uncertainty in point correspondences. Th...
Poor visibility conditions due to murky water, bad weather, dust and smoke severely impede the performance of vision systems. Passive methods have been used to restore scene contr...
Mohit Gupta, Srinivasa G. Narasimhan, Yoav Y. Sche...
Model-based 3D tracker estimate the position, rotation, and joint angles of a given model from video data of one or multiple cameras. They often rely on image features that are tr...