Robust dynamic motion estimation over time

Robust dynamic motion estimation over time (1991)

by Michael J. Black

Venue:	IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Citations:	86 - 10 self

Datum	Value	Source
TITLE	Robust dynamic motion estimation over time	INFERENCE
AUTHOR NAME	Michael J. Black	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; Yale University	SVM HeaderParse 0.2
AUTHOR ADDR	New Haven, CT 06520{2158	SVM HeaderParse 0.2
ABSTRACT	This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of a minimization problem. The resulting objective function is non{convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. We present a highly parallel incremental stochastic minimization algorithm which has a number of advantages over previous approaches. The incremental nature of the scheme makes it truly dynamic and permits the detection of occlusion and disocclusion boundaries. 1	SVM HeaderParse 0.2
YEAR	1991	INFERENCE
VENUE	IEEE Computer Society Conference on Computer Vision and Pattern Recognition	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	2 found	ParsCit 1.0