Paper Info
Title
Foveated Figure-Ground Segmentation and Its Role in Recognition
Abstract
Figure-ground segmentation and recognition are two interrelated processes. In this paper we present a method for foveated segmentation and evaluate it in the context of a binocular real-time recognition system. Segmentation is solved as a binary labeling problem using priors derived from the results of a simplistic disparity method. Doing so we are able to cope with situations when the disparity range is very wide, situations that has rarely been con- sidered, but appear frequently for narrow-field camera sets. Segmentation and recognition are then integrated into a system able to locate, attend to and recognise objects in typical cluttered indoor scenes. Finally, we try to answer two questions: is recognition really helped by segmentation and what is the benefit of multiple cues for recognition?
Year
DOI
Venue
2005
10.5244/C.19.84
BMVC
Keywords
Field
DocType
computer science,real time
Computer vision,Scale-space segmentation,Pattern recognition,Recognition system,Computer science,Segmentation,Figure–ground,Segmentation-based object categorization,Artificial intelligence,Prior probability,Binary number,Labeling Problem
Conference
Citations 
PageRank 
References 
8
0.66
15
Authors
2
Name
Order
Citations
PageRank
Mårten Björkman120213.90
Jan-Olof Eklundh21125376.36