A statistical upper body model for 3D static and dynamic gesture recognition from stereo sequences

Author

Nefian, Ara V. ; Grzeszczuk, Radek ; Eruhimov, Victor

Author_Institution

Microprocessor Res. Labs., Intel Corp., Santa Clara, CA, USA

Volume

3

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

286

Abstract

This paper describes a hidden Markov model-based static and dynamic 3D gesture recognition system. The shape and position of the hands, segmented and tracked using a novel 3D statistical model for the upper body in stereo sequences, are used as observation vectors. The upper body model allows for accurate 3D localization of the hands in the presence of partial occlusions, self occlusions and different illumination conditions. The accuracy of our approach is reflected by the performance of our 3D gesture based editing system, that reaches 96% over 12 dynamic gestures and four static gestures

Keywords

gesture recognition; hidden Markov models; image segmentation; image sequences; parameter estimation; statistical analysis; stereo image processing; 3D dynamic gesture recognition; 3D gesture based editing system; 3D localization; 3D static gesture recognition; 3D statistical model; HMM; arm segmentation; hand segmentation; head segmentation; hidden Markov model; illumination conditions; observation vectors; parameter estimation; partial occlusions; self occlusions; statistical upper body model; stereo sequences; torso segmentation; upper body model; Application software; Cameras; Hidden Markov models; Humans; Image segmentation; Lighting; Microprocessors; Pixel; Robustness; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.958107

Filename

958107