Real-time multi-cue mean-shift hand tracking algorithm in cluttered background

Han Wang, Hanseok Ko

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

2 Citations (Scopus)

Abstract

This paper proposes a multi-cue real-time hand tracking algorithm effective for skin color cluttered background. Traditional color based mean-shift algorithm often fails in color confusable background. To deal with this problem, we first construct a novel dynamic motion-color joint probabilistic distribution with optical flow feature based motion model to clearly distinguish the target moving object from visually similar background or other moving objects. We then apply the multi-cue mean-shift tracking by combining the motion-color joint distribution with the mean-shift iteration process. A motion detection process is also performed to avoid the target centers' erroneously shifting to color similar static background when no motion exists. Representative experiments validate that the proposed method improves the accuracy of mean-shift tracking algorithm under cluttered background environment.

Original languageEnglish
Title of host publicationProceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Pages1310-1314
Number of pages5
Volume3
DOIs
Publication statusPublished - 2011 Dec 1
Event4th International Congress on Image and Signal Processing, CISP 2011 - Shanghai, China
Duration: 2011 Oct 152011 Oct 17

Other

Other4th International Congress on Image and Signal Processing, CISP 2011
CountryChina
CityShanghai
Period11/10/1511/10/17

Fingerprint

Color
Optical flows
Skin
Experiments

Keywords

  • hand tracking
  • local motion model
  • mean-shift
  • motion-color joint distribution
  • multi-cue

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wang, H., & Ko, H. (2011). Real-time multi-cue mean-shift hand tracking algorithm in cluttered background. In Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011 (Vol. 3, pp. 1310-1314). [6100496] https://doi.org/10.1109/CISP.2011.6100496

Real-time multi-cue mean-shift hand tracking algorithm in cluttered background. / Wang, Han; Ko, Hanseok.

Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011. Vol. 3 2011. p. 1310-1314 6100496.

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

Wang, H & Ko, H 2011, Real-time multi-cue mean-shift hand tracking algorithm in cluttered background. in Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011. vol. 3, 6100496, pp. 1310-1314, 4th International Congress on Image and Signal Processing, CISP 2011, Shanghai, China, 11/10/15. https://doi.org/10.1109/CISP.2011.6100496
Wang H, Ko H. Real-time multi-cue mean-shift hand tracking algorithm in cluttered background. In Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011. Vol. 3. 2011. p. 1310-1314. 6100496 https://doi.org/10.1109/CISP.2011.6100496
Wang, Han ; Ko, Hanseok. / Real-time multi-cue mean-shift hand tracking algorithm in cluttered background. Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011. Vol. 3 2011. pp. 1310-1314
@inproceedings{fce4afedcae149649b20d3e10ed50d2c,
title = "Real-time multi-cue mean-shift hand tracking algorithm in cluttered background",
abstract = "This paper proposes a multi-cue real-time hand tracking algorithm effective for skin color cluttered background. Traditional color based mean-shift algorithm often fails in color confusable background. To deal with this problem, we first construct a novel dynamic motion-color joint probabilistic distribution with optical flow feature based motion model to clearly distinguish the target moving object from visually similar background or other moving objects. We then apply the multi-cue mean-shift tracking by combining the motion-color joint distribution with the mean-shift iteration process. A motion detection process is also performed to avoid the target centers' erroneously shifting to color similar static background when no motion exists. Representative experiments validate that the proposed method improves the accuracy of mean-shift tracking algorithm under cluttered background environment.",
keywords = "hand tracking, local motion model, mean-shift, motion-color joint distribution, multi-cue",
author = "Han Wang and Hanseok Ko",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/CISP.2011.6100496",
language = "English",
isbn = "9781424493067",
volume = "3",
pages = "1310--1314",
booktitle = "Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011",

}

TY - GEN

T1 - Real-time multi-cue mean-shift hand tracking algorithm in cluttered background

AU - Wang, Han

AU - Ko, Hanseok

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper proposes a multi-cue real-time hand tracking algorithm effective for skin color cluttered background. Traditional color based mean-shift algorithm often fails in color confusable background. To deal with this problem, we first construct a novel dynamic motion-color joint probabilistic distribution with optical flow feature based motion model to clearly distinguish the target moving object from visually similar background or other moving objects. We then apply the multi-cue mean-shift tracking by combining the motion-color joint distribution with the mean-shift iteration process. A motion detection process is also performed to avoid the target centers' erroneously shifting to color similar static background when no motion exists. Representative experiments validate that the proposed method improves the accuracy of mean-shift tracking algorithm under cluttered background environment.

AB - This paper proposes a multi-cue real-time hand tracking algorithm effective for skin color cluttered background. Traditional color based mean-shift algorithm often fails in color confusable background. To deal with this problem, we first construct a novel dynamic motion-color joint probabilistic distribution with optical flow feature based motion model to clearly distinguish the target moving object from visually similar background or other moving objects. We then apply the multi-cue mean-shift tracking by combining the motion-color joint distribution with the mean-shift iteration process. A motion detection process is also performed to avoid the target centers' erroneously shifting to color similar static background when no motion exists. Representative experiments validate that the proposed method improves the accuracy of mean-shift tracking algorithm under cluttered background environment.

KW - hand tracking

KW - local motion model

KW - mean-shift

KW - motion-color joint distribution

KW - multi-cue

UR - http://www.scopus.com/inward/record.url?scp=84862972839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862972839&partnerID=8YFLogxK

U2 - 10.1109/CISP.2011.6100496

DO - 10.1109/CISP.2011.6100496

M3 - Conference contribution

AN - SCOPUS:84862972839

SN - 9781424493067

VL - 3

SP - 1310

EP - 1314

BT - Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011

ER -