An Eye-Tracker-Based 3D Point-of-Gaze Estimation Method Using Head Movement

Wudthipong Pichitwong,Kosin Chamnongthai

doi:10.1109/access.2019.2929195

Wudthipong Pichitwong, Kosin Chamnongthai

Open Access

https://doi.org/10.1109/access.2019.2929195

Copy DOI

Abstract

Eye trackers are currently used to sense the positions of both the centers of the pupils and the point-of-gaze (POG) position on a screen, in keeping with the original objective for which they were designed; however, it remains difficult to measure the positions of three-dimensional (3D) POGs. This paper proposes a method for 3D gaze estimation by using head movement, pupil position data, and POGs on a screen. The method assumes that a person, usually unintentionally, moves his or her head a short distance such that multiple straight lines can be drawn from the center point between the two pupils to the POG. When the person is continuously focusing on a given 3D POG while moving, these lines represent the lines of sight that intersect at a 3D POG. That 3D POG can, therefore, be found from the intersection of several lines of sight formed by head movements. To evaluate the performance of the proposed method, experimental equipment was constructed, and experiments with five male and five female participants were performed in which the participants looked at nine test points in a 3D space for approximately 20 s each. The experimental results reveal that the proposed method can measure 3D POGs with average distance errors of 13.36 cm, 7.58 cm, 5.72 cm, 3.97 cm, and 3.52 cm for head movement distances of 1 cm, 2 cm, 3 cm, 4 cm, and 5 cm, respectively.

Highlights

Human gaze estimation has recently played important roles in many fields, such as gaming, marketing, driver-behavior analysis, navigation, advertising, and human-computer interaction (HCI)
An eye tracker for reading the 2D POG on a screen was selected as the sensor mounted in front of the participant, charge-coupled device (CCD) cameras were used for calibration, and equipment with nine test points on nine poles and a fixed stand for face positioning were constructed for observing and measuring the gazes of the participants
This paper proposed a method of 3D point-of-gaze (POG) estimation using head movements as well as 3D pupil position data and 2D POGs on a virtual screen obtained by an eye tracker

Summary

Introduction

Human gaze estimation has recently played important roles in many fields, such as gaming, marketing, driver-behavior analysis, navigation, advertising, and human-computer interaction (HCI). In games, using gaze to represent player intentions is helpful for shifting the player’s view in a virtual reality environment without requiring head movement. The customer gaze is useful for learning customer interests, and gaze analyses may indicate an effective merchandise layout in a shop or guide product design. Gaze is considered a key analytical tool for investigating the behaviors of car drivers and pilots and has led to efficient improvements in black box data. Impaired individuals who have no ability to speak can utilize gaze-based commands to navigate wheelchairs and chat, while gaze analysis can assist people in driving cars safely. Gaze estimation algorithms for objects in 3D must be studied to

Results

Discussion

Conclusion