Vision-based human interface with user-centered frame

This paper presents a vision-based human-computer interface system that enables the user to move a target object in 3D CG world by moving his/her hand. Unlike conventional systems, the system does not need any camera calibration. In addition, it uses a user-centered frame so that the user can control the object by hand motions matched with human intuition. For example, the user can move the object forward by moving his/her hand forward even if he/she has changed his/her body position. The system is based on the multiple view affine invariance theory. It calculates hand positions as invariant coordinates in the basis derived from four points on the user's body. Actual system implementation and experimental results show the usefulness of the system.<<ETX>>

[1]  J J Koenderink,et al.  Affine structure from motion. , 1991, Journal of the Optical Society of America. A, Optics and image science.

[2]  Yasuhito Suenaga,et al.  Real-Time Detection of Pointing Actions for a Glove-Free Interface , 1992, MVA.

[3]  F. Kishino,et al.  Cooperative work environment using virtual workspace , 1992, CSCW '92.

[4]  Roberto Cipolla,et al.  Robust structure from motion using motion parallax , 1993, 1993 (4th) International Conference on Computer Vision.

[5]  D. W. Thompson,et al.  Three-dimensional model matching from an unconstrained viewpoint , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[6]  Roberto Cipolla,et al.  Towards 3D Object Model Acquisition and Recognition using 3D Affine Invariants , 1993, BMVC.

[7]  Alex Pentland,et al.  Space-time gestures , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.