Head Motion Detection and Compensation for Visible-Spectrum Gaze Tracking Systems

Wen Chung Kao, Ren Xiang Ying, Yi Fang Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The head motion detection and compensation mechanisms significantly improve the final system precision/accuracy of a gaze tracker. But the problem becomes more difficult for a visible-spectrum gaze track compared with the one based on an infra-ray (IR) lighting system for the lack of the IR light sources as the reference locations. This paper presents a robust detection as well as a compensation mechanism for a visible-spectrum gaze tracker by using more stable feature points on the entire head image. The limbus circle matching module dynamically adjusts the eyeball model and calculates the moving distance of the head. The experimental results show that the compensation mechanism further improves the system performance of the gaze tracker when the user moves their head.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Consumer Electronics, ICCE 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665491303
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States
Duration: 2023 Jan 62023 Jan 8

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
Volume2023-January
ISSN (Print)0747-668X

Conference

Conference2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Country/TerritoryUnited States
CityLas Vegas
Period2023/01/062023/01/08

Keywords

  • gaze tracking
  • head motion compensation
  • human-machine interface

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Head Motion Detection and Compensation for Visible-Spectrum Gaze Tracking Systems'. Together they form a unique fingerprint.

Cite this