Arm-pointing gesture interface using surrounded stereo cameras system

We propose an interface achieved using surrounding stereo cameras as a method of independently recognizing the intentional arm-pointing gestures of several users. The stereo cameras provide depth information maps in real time with resulting robustness against the influence of changes in lighting and users' clothing. Utilizing this, we developed a method capable of sensing intentional arm-pointing gestures that ignored unconscious arm-pointing gestures. This interface does not depend on the user's position, direction, or posture. We placed four stereo cameras in four corners of the ceiling and used this method in various lighting environments. We evaluated the arm-pointing gestures of seven subjects at multiple points and obtained reliable accuracy. Furthermore, we applied this method to the arm-pointing gesture interface of home electronics appliances using Bluetooth.

[1]  Nebojsa Jojic,et al.  Detection and estimation of pointing gestures in dense disparity maps , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[2]  Katsuhiko Sakaue,et al.  Concept of ubiquitous stereo vision and applications for human sensing , 2003, Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694).

[3]  J. Krumm,et al.  Multi-camera multi-person tracking for EasyLiving , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[4]  I. Yoda,et al.  Automatic face classifications by self-organization for face recognition , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[5]  Masanobu Yamamoto,et al.  Gesture recognition using character recognition techniques on two-dimensional eigenspace , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[6]  Masanobu Yamamoto,et al.  Scene constraints-aided tracking of human body , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).