Attending, Foveating and Recognizing Objects in Real World Scenes
2004 (English)In: British Machine Vision Conference (BMVC), London, UK / [ed] Andreas Hoppe, Sarah Barman, Tim Ellis, BMVA Press , 2004, 227-236 p.Conference paper (Refereed)
Recognition in cluttered real world scenes is a challenging problem. To find a particular object of interest within a reasonable time, a wide field of view is preferable. However, as we will show with practical experiments, robust recognition is easier if the object is foveated and subtends a considerable partof the visual field. In this paper a binocular system able to overcome these two conflicting requirements will be presented. The system consists of two sets of cameras, a wide field pair and a foveal one. From disparities a number of object hypotheses are generated. An attentional process based on hue and 3D size guides the foveal cameras towards the most salient regions. With the object foveated and segmented in 3D, recognition is performed using scale invariant features. The system is fully automised and runs at real-time speed.
Place, publisher, year, edition, pages
BMVA Press , 2004. 227-236 p.
Computer Vision, Active Vision, Robot Vision
IdentifiersURN: urn:nbn:se:kth:diva-51388DOI: 10.1016/j.imavis.2007.10.004ISI: 000252196500001ISBN: 1-901725-25-1OAI: oai:DiVA.org:kth-51388DiVA: diva2:464077
British Machine Vision Conference
QC 201201112012-01-112011-12-122013-11-20Bibliographically approved