Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Range image segmentation using a relaxation oscillator network
Autore:
Liu, XW; Wang, DLL;
Indirizzi:
Ohio State Univ, Dept Comp & Informat Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 nformat Sci, Columbus, OH 43210 USA Ohio State Univ, Ctr Cognit Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 Cognit Sci, Columbus, OH 43210 USA
Titolo Testata:
IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 3, volume: 10, anno: 1999,
pagine: 564 - 573
SICI:
1045-9227(199905)10:3<564:RISUAR>2.0.ZU;2-8
Fonte:
ISI
Lingua:
ENG
Soggetto:
VISUAL-CORTEX; RECOGNITION; MAP; CAT;
Keywords:
LEGION; oscillatory correlation; pulse-coupled neural networks; range image segmentation; relaxation oscillator;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
47
Recensione:
Indirizzi per estratti:
Indirizzo: Liu, XW Ohio State Univ, Dept Comp & Informat Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 Sci, Columbus, OH 43210 USA
Citazione:
X.W. Liu e D.L.L. Wang, "Range image segmentation using a relaxation oscillator network", IEEE NEURAL, 10(3), 1999, pp. 564-573

Abstract

A locally excitatory globally inhibitory oscillator network (LEGION) is constructed and applied to range image segmentation, where each oscillator has excitatory lateral connections to the oscillators in its local neighborhood as well as a connection with a global inhibitor, A feature vector, consisting of depth, surface normal, and mean and Gaussian curvatures, is associated with each oscillator and is estimated from local windows at its corresponding pixel location. A context-sensitive method is applied in order to obtain more reliable and accurate estimations. The lateral connection between two oscillators is established based on a similarity measure of their feature vectors, The emergent behavior of the LEGION network gives rise to segmentation. Due to the flexible representation through phases, our method needs no assumption about the underlying structures in image data and no prior knowledge regarding the number of regions. More importantly, the network is guaranteed to converge rapidly under general conditions. These unique properties may lead to a real-time approach for range image segmentation in machine perception.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 02/07/20 alle ore 20:19:20