Sketch on dynamic gesture tracking and analysis exploiting vision-based 3D interface

Woontack Woo; Namgyu Kim; Karen Wong; Makoto Tadenuma

doi:10.1117/12.411844

29 December 2000 Sketch on dynamic gesture tracking and analysis exploiting vision-based 3D interface

Woontack Woo, Namgyu Kim, Karen Wong, Makoto Tadenuma

Proceedings Volume 4310, Visual Communications and Image Processing 2001; (2000) https://doi.org/10.1117/12.411844
Event: Photonics West 2001 - Electronic Imaging, 2001, San Jose, CA, United States

Abstract

In this paper, we propose a vision-based 3D interface exploiting invisible 3D boxes, arranged in the personal space (i.e. reachable space by the body without traveling), which allows robust yet simple dynamic gesture tracking and analysis, without exploiting complicated sensor-based motion tracking systems. Vision-based gesture tracking and analysis is still a challenging problem, even though we have witnessed rapid advances in computer vision over the last few decades. The proposed framework consists of three main parts, i.e. (1) object segmentation without bluescreen and 3D box initialization with depth information, (2) movement tracking by observing how the body passes through the 3D boxes in the personal space and (3) movement feature extraction based on Laban's Effort theory and movement analysis by mapping features to meaningful symbols using time-delay neural networks. Obviously, exploiting depth information using multiview images improves the performance of gesture analysis by reducing the errors introduced by simple 2D interfaces In addition, the proposed box-based 3D interface lessens the difficulties in both tracking movement in 3D space and in extracting low-level features of the movement. Furthermore, the time-delay neural networks lessens the difficulties in movement analysis by training. Due to its simplicity and robustness, the framework will provide interactive systems, such as ATR I-cubed Tangible Music System or ATR Interactive Dance system, with improved quality of the 3D interface. The proposed simple framework also can be extended to other applications requiring dynamic gesture tracking and analysis on the fly.

Citation Download Citation

Woontack Woo, Namgyu Kim, Karen Wong, and Makoto Tadenuma "Sketch on dynamic gesture tracking and analysis exploiting vision-based 3D interface", Proc. SPIE 4310, Visual Communications and Image Processing 2001, (29 December 2000); https://doi.org/10.1117/12.411844

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available