Models for gaze tracking systems
Journal on Image and Video Processing
Taxonomic study of polynomial regressions applied to the calibration of video-oculographic systems
Proceedings of the 2008 symposium on Eye tracking research & applications
Models for gaze tracking systems
Journal on Image and Video Processing
Homography normalization for robust gaze estimation in uncalibrated setups
Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications
Robust optical eye detection during head movement
Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications
Error characterization and compensation in eye tracking systems
Proceedings of the Symposium on Eye Tracking Research and Applications
A single-camera remote eye tracker
PIT'06 Proceedings of the 2006 international tutorial and research conference on Perception and Interactive Technologies
Study of Polynomial Mapping Functions in Video-Oculography Eye Trackers
ACM Transactions on Computer-Human Interaction (TOCHI)
The effect of mapping function on the accuracy of a video-based eye tracker
Proceedings of the 2013 Conference on Eye Tracking South Africa
Learning gaze biases with head motion for head pose-free gaze estimation
Image and Vision Computing
| Hi-index | 0.00 |
We describe a system designed to monitor the gaze of a user working naturally at a computer workstation. The system consists of three cameras situated between the keyboard and the monitor. Free head movements are allowed within a three-dimensional volume approximately 40 centimeters in diameter. Two fixed, wide-field "face" cameras equipped with active-illumination systems enable rapid localization of the subject's pupils. A third steerable "eye" camera has a relatively narrow field of view, and acquires the images of the eyes which are used for gaze estimation. Unlike previous approaches which construct an explicit three-dimensional representation of the subject's head and eye, we derive mappings for steering control and gaze estimation using a procedure we call implicit calibration. Implicit calibration is performed by collecting a "training set" of parameters and associated measurements, and solving for a set of coefficients relating the measurements back to the parameters of interest. Preliminary data on three subjects indicate an median gaze estimation error of ap-proximately 0.8 degree.