Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition

Yosuke Sato, Tetsunori Kobayashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

We propose a modified Hidden Markov Model (HMM) with a view to improving gesture recognition in the moving camera condition. We define a new gesture recognition framework in which multiple candidates of feature vectors are generated with confidence measures and the HMM is extended to deal with these multiple feature vectors. Experimental analysis comparing the proposed system with feature vectors based on DCT and the method of selecting only one candidate feature point verify the effectiveness of the technique.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages515-519
Number of pages5
Volume16
Edition2
Publication statusPublished - 2002
Externally publishedYes

Fingerprint

Gesture recognition
Hidden Markov models
Mobile robots
Cameras

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Sato, Y., & Kobayashi, T. (2002). Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition. In Proceedings - International Conference on Pattern Recognition (2 ed., Vol. 16, pp. 515-519)

Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition. / Sato, Yosuke; Kobayashi, Tetsunori.

Proceedings - International Conference on Pattern Recognition. Vol. 16 2. ed. 2002. p. 515-519.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sato, Y & Kobayashi, T 2002, Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition. in Proceedings - International Conference on Pattern Recognition. 2 edn, vol. 16, pp. 515-519.
Sato Y, Kobayashi T. Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition. In Proceedings - International Conference on Pattern Recognition. 2 ed. Vol. 16. 2002. p. 515-519
@inproceedings{15036f7ec6114b93bb01cb78d3d009f4,
title = "Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition",
abstract = "We propose a modified Hidden Markov Model (HMM) with a view to improving gesture recognition in the moving camera condition. We define a new gesture recognition framework in which multiple candidates of feature vectors are generated with confidence measures and the HMM is extended to deal with these multiple feature vectors. Experimental analysis comparing the proposed system with feature vectors based on DCT and the method of selecting only one candidate feature point verify the effectiveness of the technique.",
author = "Yosuke Sato and Tetsunori Kobayashi",
year = "2002",
language = "English",
volume = "16",
pages = "515--519",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "2",

}

TY - GEN

T1 - Extension of hidden markov models to deal with multiple candidates of observations and its application to mobile-robot-oriented gesture recognition

AU - Sato, Yosuke

AU - Kobayashi, Tetsunori

PY - 2002

Y1 - 2002

N2 - We propose a modified Hidden Markov Model (HMM) with a view to improving gesture recognition in the moving camera condition. We define a new gesture recognition framework in which multiple candidates of feature vectors are generated with confidence measures and the HMM is extended to deal with these multiple feature vectors. Experimental analysis comparing the proposed system with feature vectors based on DCT and the method of selecting only one candidate feature point verify the effectiveness of the technique.

AB - We propose a modified Hidden Markov Model (HMM) with a view to improving gesture recognition in the moving camera condition. We define a new gesture recognition framework in which multiple candidates of feature vectors are generated with confidence measures and the HMM is extended to deal with these multiple feature vectors. Experimental analysis comparing the proposed system with feature vectors based on DCT and the method of selecting only one candidate feature point verify the effectiveness of the technique.

UR - http://www.scopus.com/inward/record.url?scp=33751559701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33751559701&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33751559701

VL - 16

SP - 515

EP - 519

BT - Proceedings - International Conference on Pattern Recognition

ER -