Indication position estimation by the homography of planes

To get a rapid estimation of the user's indication position in computer vision based noncontact human-computer interaction (HCI) system, an indication position estimation method without explicitly calculating the cameras' parameters. The homography matrix is calculated using the known points on the target plane and their corresponding points imaged by the cameras. By this homography relationship, the two lines which intersect at the indication point on the target plane are related with their corresponding lines on the image plane, thus the position of the indication point is estimated by detecting specific lines from images. Experimental results show that the average error of the homographic mapping is 0.726mm at the distance of 2.5m; meanwhile, the amplitude of errors rises by 2.6% from the center to the fringe of the screen (size of the screen is 2500mm×1800mm). The precision and consistency of this method can satisfy the requirement of most applications in human-computer interaction.

[1]  O. D. Faugeras,et al.  Camera Self-Calibration: Theory and Experiments , 1992, ECCV.

[2]  Luc Van Gool,et al.  Real-time pointing gesture recognition for an immersive environment , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[3]  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).

[4]  Janne Heikkilä,et al.  Geometric Camera Calibration Using Circular Control Points , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Olivier D. Faugeras,et al.  A theory of self-calibration of a moving camera , 1992, International Journal of Computer Vision.

[6]  Ian D. Reid,et al.  A plane measuring device , 1999, Image Vis. Comput..

[7]  Rainer Stiefelhagen,et al.  Real-Time Recognition of 3D-Pointing Gestures for Human-Machine-Interaction , 2003, DAGM-Symposium.

[8]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[9]  Katsuhiko Sakaue,et al.  Arm-pointing gesture interface using surrounded stereo cameras system , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..