Accurate Regression-Based 3D Gaze Estimation Using Multiple Mapping Surfaces

Zhonghua Wan; Caihua Xiong; Quanlin Li; Wenbin Chen; Kelvin Kian Loong Wong; Shiqian Wu

doi:10.1109/ACCESS.2020.3023448

IEEE Access (Jan 2020)

Accurate Regression-Based 3D Gaze Estimation Using Multiple Mapping Surfaces

Zhonghua Wan,
Caihua Xiong,
Quanlin Li,
Wenbin Chen,
Kelvin Kian Loong Wong,
Shiqian Wu

Affiliations

Zhonghua Wan: ORCiD; State Key Laboratory of Digital Manufacturing Equipment and Technology, Institute of Rehabilitation and Medical Robotics, Huazhong University of Science and Technology, Wuhan, China
Caihua Xiong: ORCiD; State Key Laboratory of Digital Manufacturing Equipment and Technology, Institute of Rehabilitation and Medical Robotics, Huazhong University of Science and Technology, Wuhan, China
Quanlin Li: State Key Laboratory of Digital Manufacturing Equipment and Technology, Institute of Rehabilitation and Medical Robotics, Huazhong University of Science and Technology, Wuhan, China
Wenbin Chen: ORCiD; State Key Laboratory of Digital Manufacturing Equipment and Technology, Institute of Rehabilitation and Medical Robotics, Huazhong University of Science and Technology, Wuhan, China
Kelvin Kian Loong Wong: School of Information Science and Engineering, Institute of Robotics and Intelligent Systems, Wuhan University of Science and Technology, Wuhan, China
Shiqian Wu: ORCiD; School of Information Science and Engineering, Institute of Robotics and Intelligent Systems, Wuhan University of Science and Technology, Wuhan, China

DOI: https://doi.org/10.1109/ACCESS.2020.3023448
Journal volume & issue: Vol. 8
pp. 166460 – 166471

Abstract

Read online

Accurate 3D gaze estimation using a simple setup remains a challenging issue for head-mounted eye tracking. Current regression-based gaze direction estimation methods implicitly assume that all gaze directions intersect at one point called the eyeball pseudo-center. The effect of this implicit assumption on gaze estimation is unknown. In this paper, we find that this assumption is approximate based on a simulation of all intersections of gaze directions, and it is conditional based on a sensitivity analysis of the assumption in gaze estimation. Hence, we propose a gaze direction estimation method with one mapping surface that satisfies conditions of the assumption by configuring one mapping surface and achieving a high-quality calibration of the eyeball pseudo-center. This method only adds two additional calibration points outside the mapping surface. Furthermore, replacing the eyeball pseudo-center with an additional calibrated surface, we propose a gaze direction estimation method with two mapping surfaces that further improves the accuracy of gaze estimation. This method improves accuracy on the state-of-the-art method by 20 percent (from a mean error of 1.84 degrees to 1.48 degrees) on a public dataset with a usage range of 1 meter and by 17 percent (from a mean error of 2.22 degrees to 1.85 degrees) on a public dataset with a usage range of 2 meters.

Published in IEEE Access

ISSN: 2169-3536 (Online)
Publisher: IEEE
Country of publisher: United States
LCC subjects: Technology: Electrical engineering. Electronics. Nuclear engineering
Website: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

About the journal

Abstract

Keywords