ROBUST EYE TRACKING IN VIDEO SEQUENCE

In this paper, we present a novel method for eye tracking, in detail describing the eye contour and the visible iris center. Combining the IVT (Incremental Visual Tracking) tracker, the proposed online affine manifold model, in which the sequentially learning shape and texture are modeled in the first stage and noniterative recovering estimation in the second stage, tracks the eye contour in video sequences. After that, an adaptive black round mask is generated to match the visible iris center. Experimental results of eye tracking indicate that our tracker works well in the PC or domestic camera captured image streams with considerable head and eyeball rotation.