The Community for Technology Leaders
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (2001)
Kauai, Hawaii
Dec. 8, 2001 to Dec. 14, 2001
ISSN: 1063-6919
ISBN: 0-7695-1272-0
pp: 1026
M.S. Lee , Philips Research
D. Weinshall , Philips Research
E. Cohen-Solal , Philips Research
ABSTRACT
Pointing at planar surfaces such as TV and computer monitors or projection screens can be a useful mode of interaction between humans and machines. To a large extent what seems to hinder the use of vision in such practical applications is the difficulty of the computational task, which is typically dened as 3-D reconstruction from uncalibrated 2-D images of a non-static scene. We describe below two designs where, using one or two cameras, the target of pointing on a at monitor or screen is identied without 3-D inference, using only image morphing and line intersection. This is accomplished by registering the images with the target plane. When used to identify a pointing target on a surface hiden from the camera (e.g., a computer monitor which supports the camera itself as in most PC congurations), we add aperture(s) coplanar with the target surface in front of the camera(s). We describe experimental results showing a fully automated procedure for pointing target detection with high accuracy. The simplicity of our method anditsrobustness, as well as the relative accuracy of our results, can make pointing a practical means of human-machine interaction.
INDEX TERMS
null
CITATION

D. Weinshall, M. Lee and E. Cohen-Solal, "A Computer Vision System for On-Screen Item Selection by Finger Pointing," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001(CVPR), Kauai, Hawaii, 2001, pp. 1026.
doi:10.1109/CVPR.2001.990643
88 ms
(Ver 3.3 (11022016))