In this paper, we address the task of tracking groups of people in surveillance scenarios. This is a major challenge in computer vision, since groups are structured entities, subj...
Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient modeseekin...
This paper studies automatic segmentation of multiple
motions from tracked feature points through spectral embedding
and clustering of linear subspaces. We show that
the dimensi...
This paper describes a new method for determining correspondence between points on pairs of surfaces based on shape using a combination of geodesic distance and surface curvature....
Yongmei Wang, Bradley S. Peterson, Lawrence H. Sta...
An efficient algorithmic solution to the classical five-point relative pose problem is presented. The problem is to find the possible solutions for relative camera motion between ...