THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
Seeing Behind Occlusion |
pdf 226 KB
ps.gz 177 KB
ps 1.17 MB
@TechReport{Ballard:TR94,
author = {Dana H. Ballard and Rajesh P.N. Rao},
title = {Seeing Behind Occlusion},
institution = {Comp. Sci. Dept. University of Rochester},
year = {1994},
number = {487},
address = {Rochester NY},
month = {February},
abstract = {
The location of objects in images is difficult owing to the view variance of
geometric features but can be determined by developing view-insensitive
descriptions of the intensities local to image points. View-insensitive
descriptions are achieved in this work by describing points in terms of the
responses of steerable filters at multiple scales. Owing to the use of multiple
scales, the vector for each point is, for all practical purposes, unique, and
thus can be easily matched to other instances of the point in other images. We
show that this method can be extended to handle the case where the area near a p
oint of interest is partially occluded. The method uses a description of the
occluder in the form of a template that can be obtained easily via active vision
systems using a method such as disparity filtering. }
}