Share Email Print

Proceedings Paper

Robust Estimation of Image Flow
Author(s): Brian G. Schunck
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Motion is a key visual cue for segmentation. A particularly difficult problem is the segmentation of objects that are camouflaged and match the background perfectly. In such situations, it is critical that the boundaries of the object be determined accurately since the outline (silhouette) will be the only visual information available for segmentation and recognition. Image flow is the velocity field in the image plane caused by the motion of the observer, objects in the scene, or apparent motion. The image flow velocity field can be used for segmentation if the motion boundaries can be accurately estimated. When an object moves against a background, the motion constraints are distorted along the boundary and the motion estimation problem is very difficult to solve. The distorted motion data would be called outliers by workers in the field of robust statistics. Recent work has been done on robust algorithms for image flow estimation and segmentation. New algorithms based on robust regression show promise in handling the difficult problems associated with discontinuities in the image flow velocity field. The results point toward better methods for handling discontinuities in other vision problems. In particular, algorithms for sensor fusion will face the task of combining information that contains outliers and discontinuities. The material presented in this paper may indicate directions for future research on sensor fusion.

Paper Details

Date Published: 1 March 1990
PDF: 12 pages
Proc. SPIE 1198, Sensor Fusion II: Human and Machine Strategies, (1 March 1990); doi: 10.1117/12.969969
Show Author Affiliations
Brian G. Schunck, University of Michigan (United States)

Published in SPIE Proceedings Vol. 1198:
Sensor Fusion II: Human and Machine Strategies
Paul S. Schenker, Editor(s)

© SPIE. Terms of Use
Back to Top