Foveated Figure-Ground Segmentation and Its Role in Recognition
2005 (English)In: BMVC 2005 - Proceedings of the British Machine Vision Conference 2005 / [ed] William Clocksin, Andrew Fitzgibbon, Philip Torr, British Machine Vision Association, BMVA , 2005, 819-828 p.Conference paper (Refereed)
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 ofa simplistic disparity method. Doing so we are able to cope with situations when the disparity range is very wide, situations that has rarely been considered, 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?
Place, publisher, year, edition, pages
British Machine Vision Association, BMVA , 2005. 819-828 p.
Computer Vision, Segmentation, Recognition
IdentifiersURN: urn:nbn:se:kth:diva-51385DOI: 10.5244/C.19.84ScopusID: 2-s2.0-84898431459ISBN: 901725-29-4OAI: oai:DiVA.org:kth-51385DiVA: diva2:464071
2005 16th British Machine Vision Conference, BMVC 2005, Oxford, United Kingdom, 5 September 2005 through 8 September 2005
QC 201201112012-01-112011-12-122015-04-10Bibliographically approved