Abstract | ||
---|---|---|
In the eye gaze tracking problem, the goal is to determine where on a monitor screen a computer user is looking - the gaze point. Existing systems generally have one of two lim- itations: either the head must remain fixed in front of a sta- tionary camera, or, to allow for head motion, the user must wear an obtrusive device. We introduce a 3D eye tracking system where head motion is allowed without the need for markers or worn devices. We use a pair of stereo systems: a wide angle stereo system detects the face and steers an active narrow FOV stereo system to track the eye at high resolution. For high resolution tracking, the eye is modeled in 3D, including the corneal ball, pupil and fovea. In this paper, we discuss the calibration of the stereo systems, the eye model, eye detection and tracking, and we close with an evaluation of the accuracy of the estimated gaze point on the monitor. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/CVPR.2003.1211502 | CVPR |
Keywords | Field | DocType |
face recognition,motion estimation,object detection,stereo image processing,target tracking,3D eye model,3D eye tracking system,active narrow FOV stereo system,active stereo head,computer user,corneal ball,eye gaze tracking,face detection,fovea,gaze point estimation,head motion,high resolution tracking,monitor screen,pupil,stereo system calibration,wide angle stereo system | Computer vision,Object detection,Gaze,Computer graphics (images),Stereopsis,Computer science,Eye tracking on the ISS,Pupil,Eye tracking,Artificial intelligence,Face detection,Motion estimation | Conference |
Volume | ISSN | Citations |
2 | 1063-6919 | 86 |
PageRank | References | Authors |
5.27 | 10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Beymer David | 1 | 420 | 87.32 |
Myron Flickner | 2 | 913 | 179.69 |