Object segregation and local gist vision using low-level geometry

Martins, J. C.; Rodrigues, J. M. F.; du Buf, J. M. H.

Publication

Object segregation and local gist vision using low-level geometry

2009Conference object

dc.contributor.author	Martins, J. C.
dc.contributor.author	Rodrigues, J. M. F.
dc.contributor.author	du Buf, J. M. H.
dc.date.accessioned	2011-12-06T13:40:49Z
dc.date.available	2011-12-06T13:40:49Z
dc.date.issued	2009
dc.date.updated	2011-12-05T16:58:21Z
dc.description.abstract	Multi-scale representations of lines, edges and keypoints on the basis of simple, complex, and end-stopped cells can be used for object categorisation and recognition. These representations are complemented by saliency maps of colour, texture, disparity and motion information, which also serve to model extremely fast gist vision in parallel with object segregation. We present a low-level geometry model based on a single type of self-adjusting grouping cell, with a circular array of dendrites connected to edge cells located at several angles. Different angles between active edge cells allow the grouping cell to detect geometric primitives like corners, bars and blobs. Such primitives forming different configurations can then be grouped to identify more complex geometry, like object shapes, without much additional effort. The speed of the model permits it to be used for fast gist vision, assuming that edge cells respond to transients in colour, texture, disparity and motion. The big advantage of combining this information at a low level is that local (object) gist can be extracted first, ie, which types of objects are about where in a scene, after which global (scene) gist can be processed at a semantic level.
dc.identifier.citation	Martins, J.C.; Rodrigues, J.; du Buf, J.M.H. Object segregation and local gist vision using low-level geometry, Trabalho apresentado em ECVP 2009, In Proc. 32th European Conference on Visual Perception (ECVP2009) , Regensburg, Germany, 2009.	por
dc.identifier.other	AUT: JRO00913; DUB00865;
dc.identifier.uri	http://hdl.handle.net/10400.1/881
dc.language.iso	eng	por
dc.peerreviewed	no	por
dc.subject	Visão humana	por
dc.title	Object segregation and local gist vision using low-level geometry	por
dc.type	conference object
dspace.entity.type	Publication
person.familyName	Rodrigues
person.familyName	du Buf
person.givenName	Joao
person.givenName	Hans
person.identifier.ciencia-id	8A19-98F7-9914
person.identifier.orcid	0000-0002-3562-6025
person.identifier.orcid	0000-0002-4345-1237
person.identifier.rid	M-5125-2013
person.identifier.scopus-author-id	55807461600
person.identifier.scopus-author-id	6604075916
rcaap.rights	openAccess	por
rcaap.type	conferenceObject	por
relation.isAuthorOfPublication	683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isAuthorOfPublication	cfad5636-2c77-4db0-a3a0-d7eb97ce6bee
relation.isAuthorOfPublication.latestForDiscovery	cfad5636-2c77-4db0-a3a0-d7eb97ce6bee