Share Email Print

Proceedings Paper

Uncertainty reduction: a framework for the integration of visual motion
Author(s): George T. Chou
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Motion uncertainty arises whenever there is ambiguity in local velocity vector assignment, such as along a straight contour or in a textureless region. Motion uncertainty can be quantified by computing the entropy of the corresponding velocity probability distribution. We propose a new framework for the integration of visual motion where the objective is the reduction of motion uncertainty. Based on this approach, we have developed a model that searches for the proper extent of motion integration in order to minimize motion entropy. By modeling our task as a multi-stage stochastic optimization problem, the control structure for motion integration can be inferred through dynamic programming. Results from initial experiments demonstrate that our model is capable of analyzing image sequences containing the aperture problem and textureless regions.

Paper Details

Date Published: 6 October 1994
PDF: 10 pages
Proc. SPIE 2355, Sensor Fusion VII, (6 October 1994); doi: 10.1117/12.189058
Show Author Affiliations
George T. Chou, MIT Media Lab. (United States)

Published in SPIE Proceedings Vol. 2355:
Sensor Fusion VII
Paul S. Schenker, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?