Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Clustering in image space for place recognition and visual annotations forhuman-robot interaction
Autore:
Martinez, AM; Vitria, J;
Indirizzi:
Purdue Univ, Robot Vis Lab, Sch Elect & Comp Engn Dept, W Lafayette, IN 47907 USA Purdue Univ W Lafayette IN USA 47907 Engn Dept, W Lafayette, IN 47907 USA Univ Autonoma Barcelona, Ctr Vis Comp, E-08193 Barcelona, Spain Univ Autonoma Barcelona Barcelona Spain E-08193 E-08193 Barcelona, Spain
Titolo Testata:
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
fascicolo: 5, volume: 31, anno: 2001,
pagine: 669 - 682
SICI:
1083-4419(200110)31:5<669:CIISFP>2.0.ZU;2-3
Fonte:
ISI
Lingua:
ENG
Soggetto:
EM ALGORITHM; MOBILE ROBOT; HUMAN FACES; VISION; MODEL;
Keywords:
computer vision; expectation-maximization EM algorithm; genetic algorithm (GA); mobile robot navigation; pattern recognition; user-robot interaction;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
41
Recensione:
Indirizzi per estratti:
Indirizzo: Martinez, AM Purdue Univ, Robot Vis Lab, Sch Elect & Comp Engn Dept, W Lafayette, IN 47907 USA Purdue Univ W Lafayette IN USA 47907 Lafayette, IN 47907 USA
Citazione:
A.M. Martinez e J. Vitria, "Clustering in image space for place recognition and visual annotations forhuman-robot interaction", IEEE SYST B, 31(5), 2001, pp. 669-682

Abstract

The most classical way of attempting to solve the vision-guided navigationproblem for autonomous robots corresponds to the use of three-dimensional (3-D) geometrical descriptions of the scene; what is known as model-based approaches. However, these approaches do not facilitate the user's task because they require that geometrically precise models of the 3-D environment be given by the user. In this paper, we propose the use of "annotations" posted on some type of blackboard or "descriptive" map to facilitate this user-robot interaction. We show that, by using this technique, user commands can be as simple as "go to label 5. "To build such a mechanism, new approaches for vision-guided mobile robot navigation have to be found. We show that this can be achieved by using mixture models within an appearance-based paradigm. Mixture models are more useful in practice than other pattern recognition methods such as principal component analysis (PCA) or Fisher discriminant analysis (FDA)-also known as linear discriminant analysis (LDA), because they can represent nonlinear subspaces. However, given the fact that mixture models are usually learned using the expectation-maximization (EM) algorithm which is a gradient ascent technique, the system cannot always converge to a desired final solution, due to the local maxima problem. To resolve this, a genetic version of the EM algorithm is used. We then show the capabilities of this latest approach on a navigation task that uses the above described "annotations."

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 04/04/20 alle ore 21:27:38