A NOVEL INFRARED GAZE TRACKING SYSTEM BASED ON NONUNIFORM INTERPOLATION

The gaze tracking system has become an active research field for handicapped persons as well as general people in recent years. The precise mapping method plays an important role in the system. In this paper, a novel infrared gaze tracking system based on nonuniform interpolation is proposed. In this system, the eye images for the computer to analyze are extracted under two infrared light sources and a charge-coupled device camera, and the users do not require wearing any device. First, the integral projection algorithm and canny edge detection are applied to extract the pupil boundary points from the captured eye images, and then the pupil center is computed using an efficient and accurate ellipse-fitting algorithm. Finally, to estimate where the user looks, a novel mapping method based on the nonuniform interpolation algorithm is proposed. In this mapping method, the complicated geometric eyeball model and the nonlinear mapping between the pupil center coordinates and computer monitor screen coordinates do not need to be taken into account. Experimental results show that the proposed mapping method is simple, fast and more accurate. Moreover, our system is the remote eye gaze tracking system. The users do not need to wear any device, which make the users feel more comfortable.

[1]  Moshe Eizenman,et al.  Analysis of subject-dependent point-of-gaze estimation bias in the cross-ratios method , 2008, ETRA.

[2]  Jie Zhu,et al.  Subpixel eye gaze tracking , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[3]  N. Ramanauskas,et al.  Calibration of Video-Oculographical Eye-Tracking System , 2006 .

[4]  Naoki Mukawa,et al.  FreeGaze: a gaze tracking system for everyday gaze interaction , 2002, ETRA.

[5]  Myung Jin Chung,et al.  Non-intrusive eye gaze estimation using a projective invariant under head movement , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[6]  Myung Jin Chung,et al.  A novel non-intrusive eye gaze estimation using cross-ratio under large head motion , 2005, Comput. Vis. Image Underst..

[7]  Chern-Sheng Lin,et al.  POLAR COORDINATE MAPPING METHOD FOR AN IMPROVED INFRARED EYE-TRACKING SYSTEM , 2005 .

[8]  Chern-Sheng Lin,et al.  An eye-tracking and head-control system using movement increment-coordinate method , 2007 .

[9]  Myung Jin Chung,et al.  A Human-Robot Interface Using Eye-Gaze Tracking System for People with Motor Disabilities , 2001 .

[10]  Dongheng Li,et al.  Starburst: A hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[11]  Shinjiro Kawato,et al.  Just blink your eyes: a head-free gaze tracking system , 2003, CHI Extended Abstracts.

[12]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..