Fast ellipse fitting based pupil tracking design for human-computer interaction applications
暂无分享,去创建一个
In this paper, fast ellipse fitting based pupil tracking design is studied for human-computer interaction applications. The proposed scheme uses the two-stage Random Sample Consensus (RANSAC) based fast ellipse fittings. At the first stage, the binaried pupil contour based ellipse model is applied to select the possible candidate points on Canny filtered edges. At the second stage, the Canny edge based ellipse model by the selected candidate edge points is calculated to increase the fitting accuracy further. Under keeping the similar detection rate and pupil tracking accuracy, the core functions of the proposed fast ellipse fitting based design speed up more 4 times and 10 times than those of the previous work by software implementations with 4-core and 1-core CPU's computers, respectively.
[1] Neil A. Dodgson,et al. Robust real-time pupil tracking in highly off-axis images , 2012, ETRA.
[2] Siyuan Chen,et al. Efficient and Robust Pupil Size and Blink Estimation From Near-Field Video Sequences for Human–Machine Interaction , 2014, IEEE Transactions on Cybernetics.
[3] Robert C. Bolles,et al. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.