Webcam-based Eye Gaze Tracking under Natural Head Movement

TL;DR

This paper presents a webcam-based eye gaze tracker that operates without prior calibration, handling natural head movements by modeling the scene as a series of 2D cases, achieving reasonable accuracy with a simple setup.

Contribution

It introduces a calibration-free gaze tracking method using a single low-resolution webcam that models 3D head movements as 2D cases to improve robustness.

Findings

Achieves mean error of 56.95x70.82 pixels with static head.

Achieves mean error of 87.18x103.86 pixels with natural head movement.

Operates without prior scene setup or camera calibration.

Abstract

This manuscript investigates and proposes a visual gaze tracker that tackles the problem using only an ordinary web camera and no prior knowledge in any sense (scene set-up, camera intrinsic and/or extrinsic parameters). The tracker we propose is based on the observation that our desire to grant the freedom of natural head movement to the user requires 3D modeling of the scene set-up. Although, using a single low resolution web camera bounds us in dimensions (no depth can be recovered), we propose ways to cope with this drawback and model the scene in front of the user. We tackle this three-dimensional problem by realizing that it can be viewed as series of two-dimensional special cases. Then, we propose a procedure that treats each movement of the user's head as a special two-dimensional case, hence reducing the complexity of the problem back to two dimensions. Furthermore, the proposed tracker is calibration free and discards this tedious part of all previously mentioned trackers. Experimental results show that the proposed tracker achieves good results, given the restrictions on it. We can report that the tracker commits a mean error of (56.95, 70.82) pixels in x and y direction, respectively, when the user's head is as static as possible (no chin-rests are used). Furthermore, we can report that the proposed tracker commits a mean error of (87.18, 103.86) pixels in x and y direction, respectively, under natural head movement.