Indication Position Estimation by the Homography of Planes
To get a rapid estimation of the users indication position in computer vision based noncontact humancomputer 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.
computer vision human-computer ineraction homography matrix camera model
Dong Zhihua Zhang Zhijiang Zeng Dan
Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University Shanghai, China
国际会议
2010 2nd International Conference on Signal Processing System(2010年信号处理系统国际会议 ICSPS 2010)
大连
英文
1747-1750
2010-07-05(万方平台首次上网日期,不代表论文的发表时间)