A method of hand tracking based on articulated model

Author

Zhou, Hang ; Ruan, Qiuqi

Author_Institution

Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China

Volume

2

fYear

2002

fDate

26-30 Aug. 2002

Firstpage

961

Abstract

In this paper, we discuss hand modeling, constraint analysis and associated tracking. We take advantage of several correlations between joint rotations in the hand to reduce the number of degrees of freedom in the model and provide a simple and intuitive model. In the second step, an improved tracking algorithm is proposed to detect the region of the fingers. The temporal evolution of the probability density is achieved through sampling from the prior distribution, followed by local optimization of the sample positions to obtain updated modes. It is a good precondition for gesture recognition.

Keywords

constraint theory; feature extraction; gesture recognition; image sampling; maximum likelihood estimation; motion estimation; optimisation; probability; tracking; DoF; articulated model; constraint analysis; degrees of freedom; finger region detection; gesture recognition; hand modeling; hand tracking; joint rotations; likelihood; local optimization; prior distribution; probability density; sample positions; sampling; scaled prismatic models; temporal evolution; Biological system modeling; Bones; Fingers; Humans; Information analysis; Information science; Joints; Q measurement; Tracking; Wrist;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2002 6th International Conference on

Print_ISBN

0-7803-7488-6

Type

conf

DOI

10.1109/ICOSP.2002.1179947

Filename

1179947