Abstract

The most accurate remote Point of Gaze (PoG) estimation methods that allow free head movements use infrared light sources and cameras together with gaze estimation models. Current gaze estimation models were developed for desktop eye-tracking systems and assume that the relative roll between the system and the subjects’ eyes (the ’R-Roll’) is roughly constant during use. This assumption is not true for hand-held mobile-device-based eye-tracking systems. We present an analysis that shows the accuracy of estimating the PoG on screens of hand-held mobile devices depends on the magnitude of the R-Roll angle and the angular offset between the visual and optical axes of the individual viewer. We also describe a new method to determine the PoG which compensates for the effects of R-Roll on the accuracy of the POG. Experimental results on a prototype infrared smartphone show that for an R-Roll angle of , the new method achieves accuracy of approximately , while a gaze estimation method that assumes that the R-Roll angle remains constant achieves an accuracy of . The manner in which the experimental PoG estimation errors increase with the increase in the R-Roll angle was consistent with the analysis. The method presented in this paper can improve significantly the performance of eye-tracking systems on hand-held mobile-devices.

Highlights

  • Remote eye tracking systems that measure the point of gaze (PoG) have been used in many domains including the measurement of advertising efficacy [1,2], reading studies [3,4,5], and human-machine interfaces [6]

  • The method uses measurements of the R-Roll angle between the eye-tracking system and the subject’s eyes to provide more accurate PoG estimates when the mobile device is free to rotate in the hands of the user

  • Using a prototype smartphone-based eye-tracking system we showed that when the R-Roll angle is used in the calculations of the PoG the average error in the estimation of the PoG is approximately 1◦

Read more

Summary

Introduction

Remote eye tracking systems that measure the point of gaze (PoG) have been used in many domains including the measurement of advertising efficacy [1,2], reading studies [3,4,5], and human-machine interfaces [6]. Applications in these domains have been demonstrated largely on specialized, stationary and expensive eye tracking devices. Recent work has begun to bring eye-tracking technology to widely available, and less expensive mobile devices including smart phones and tablets. Key among these is the movement of the eye-tracking device relative to the subject: during the operation of a mobile eye tracker the distance between the device and the user can vary by a factor of 2–3 and the roll angle of the device relative to the user’s eyes (R-Roll) can routinely change by 90◦

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call