Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Object recognition in image sequences with cellular neural networks
Autore:
Milanova, M; Buker, U;
Indirizzi:
Univ Gesamthsch Paderborn, Heinz Nixdorf Inst, Dept Elect Engn, D-33095 Paderborn, Germany Univ Gesamthsch Paderborn Paderborn Germany D-33095 5 Paderborn, Germany
Titolo Testata:
NEUROCOMPUTING
fascicolo: 1-4, volume: 31, anno: 2000,
pagine: 125 - 141
SICI:
0925-2312(200003)31:1-4<125:ORIISW>2.0.ZU;2-4
Fonte:
ISI
Lingua:
ENG
Soggetto:
ASSOCIATIVE MEMORIES; PATTERN-RECOGNITION; ALGORITHM; MODEL;
Keywords:
cellular neural networks; associative memory; object recognition; image sequences; optical flow;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
26
Recensione:
Indirizzi per estratti:
Indirizzo: Buker, U Univ Gesamthsch Paderborn, Heinz Nixdorf Inst, Dept Elect Engn, D-33095 Paderborn, Germany Univ Gesamthsch Paderborn Paderborn Germany D-33095 rn, Germany
Citazione:
M. Milanova e U. Buker, "Object recognition in image sequences with cellular neural networks", NEUROCOMPUT, 31(1-4), 2000, pp. 125-141

Abstract

In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in animage sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series of features for the whole image sequence. These features show several object specificcharacteristics and are used for a classification step in an object recognition system. Therefore, the feature vectors of an object set are learnt and recalled by an associative memory based on the paradigm of cellular neural networks (CNN). (C) 2000 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 13/07/20 alle ore 07:57:11