A connectionist approach for visual perception of motion
Identifieur interne : 006B54 ( Main/Merge ); précédent : 006B53; suivant : 006B55A connectionist approach for visual perception of motion
Auteurs : Claudio Castellanos S Chez ; Bernard Girau ; Frédéric AlexandreSource :
English descriptors
- KwdEn :
Abstract
Modeling visual perception of motion by connectionist networks offers various areas of research for the development of real-time models of dynamic perception-action. In this paper we present the bases of a bio-inspired connectionist approach that is part of our development of neural networks applied to autonomous robotics. Our model of visual perception of motion is based on a causal adaptation of spatiotemporal Gabor lters. We use our causal spatiotemporal lters within a modular and strongly localized architecture that performs a shunting inhibition mechanism. This model has been evaluated on arti cial as well as natural image sequences.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003E11
- to stream Crin, to step Curation: 003E11
- to stream Crin, to step Checkpoint: 000679
Links to Exploration step
CRIN:castellanos_sanchez04bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="450">A connectionist approach for visual perception of motion</title></titleStmt><publicationStmt><idno type="RBID">CRIN:castellanos_sanchez04b</idno><date when="2004" year="2004">2004</date><idno type="wicri:Area/Crin/Corpus">003E11</idno><idno type="wicri:Area/Crin/Curation">003E11</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003E11</idno><idno type="wicri:Area/Crin/Checkpoint">000679</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000679</idno><idno type="wicri:Area/Main/Merge">006B54</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">A connectionist approach for visual perception of motion</title><author><name sortKey="Castellanos S Chez, Claudio" sort="Castellanos S Chez, Claudio" uniqKey="Castellanos S Chez C" first="Claudio" last="Castellanos S Chez">Claudio Castellanos S Chez</name></author><author><name sortKey="Girau, Bernard" sort="Girau, Bernard" uniqKey="Girau B" first="Bernard" last="Girau">Bernard Girau</name></author><author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>bio-inspired neural networks</term><term>gabor filters</term><term>optical flow</term><term>perception of motion</term><term>shunting inhibition</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2251">Modeling visual perception of motion by connectionist networks offers various areas of research for the development of real-time models of dynamic perception-action. In this paper we present the bases of a bio-inspired connectionist approach that is part of our development of neural networks applied to autonomous robotics. Our model of visual perception of motion is based on a causal adaptation of spatiotemporal Gabor lters. We use our causal spatiotemporal lters within a modular and strongly localized architecture that performs a shunting inhibition mechanism. This model has been evaluated on arti cial as well as natural image sequences.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 006B54 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 006B54 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= CRIN:castellanos_sanchez04b
|texte= A connectionist approach for visual perception of motion
}}
| This area was generated with Dilib version V0.6.33. |  |