Continuous Gaze Tracking With Implicit Saliency-Aware Calibration on Mobile Devices

TL;DR

This paper introduces vGaze, a real-time, implicit saliency-aware gaze tracking method for mobile devices that improves accuracy without requiring explicit calibration, leveraging visual saliency and historical data.

Contribution

The paper presents vGaze, a novel lightweight software for continuous gaze tracking on mobile devices that uses implicit saliency-aware calibration and historical information to enhance accuracy.

Findings

Average gaze tracking error is 1.51 cm (2.884°).

Error reduces to 0.99 cm (1.891°) with historical data.

Error further decreases to 0.57 cm (1.089°) with an indicator.

Abstract

Gaze tracking is a useful human-to-computer interface, which plays an increasingly important role in a range of mobile applications. Gaze calibration is an indispensable component of gaze tracking, which transforms the eye coordinates to the screen coordinates. The existing approaches of gaze tracking either have limited accuracy or require the user's cooperation in calibration and in turn hurt the quality of experience. We in this paper propose vGaze, continuous gaze tracking with implicit saliency-aware calibration on mobile devices. The design of vGaze stems from our insight on the temporal and spatial dependent relation between the visual saliency and the user's gaze. vGaze is implemented as a light-weight software that identifies video frames with "useful" saliency information, sensing the user's head movement, performs opportunistic calibration using only those "useful" frames, and leverages historical information for accelerating saliency detection. We implement vGaze on a commercial mobile device and evaluate its performance in various scenarios. The results show that vGaze can work at real time with video playback applications. The average error of gaze tracking is 1.51 cm (2.884 degree) which decreases to 0.99 cm (1.891 degree) with historical information and 0.57 cm (1.089 degree) with an indicator.