Robust real-Time human hand localization by self-organizing color segmentation

Ying Wu, Qiong Liu, Thomas S. Huang

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

Abstract

This paper describes a robust tracking algorithm used to localize human hand in video sequences. The localization system relies mainly on an automatic color-based segmentation scheme combined with the motion cue. An automatic self-organizing clustering algorithm is proposed to learn the color clusters unsupervisedly in the HSI space without specifying the number of clusters in advance. The schemes of growing, pruning and merging of 1-D self-organizing map (SOM) are facilitated to find an appropriate number of clusters in the forming stage of SOM. The train- ing and segmentation in our approach is fast enough to make possible real-Time applications. This segmentation scheme is capable of tracking multiple objects of different colors simultaneously. Motion cue is employed to focus the attention of the tracking algorithm. This approach is also applied to other tasks such as human face tracking and color indexing. Our localization system implemented on a SGI O2 R10000 workstation is reliable and efficient at 20-30Hz.

Original languageEnglish (US)
Title of host publicationProceedings - International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, RATFG-RTS 1999
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages161-166
Number of pages6
ISBN (Electronic)0769503780, 9780769503783
DOIs
StatePublished - 1999
Event1999 International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, RATFG-RTS 1999 - Corfu, Greece
Duration: Sep 26 1999Sep 27 1999

Publication series

NameProceedings - International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, RATFG-RTS 1999

Other

Other1999 International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, RATFG-RTS 1999
Country/TerritoryGreece
CityCorfu
Period9/26/999/27/99

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Robust real-Time human hand localization by self-organizing color segmentation'. Together they form a unique fingerprint.

Cite this