A Robust Extrinsic Calibration Method f or Non-Contact Gaze Tracking in the 3-D Space
- Authors
- Kang, Mun-Cheon; Yoo, Cheol-Hwan; Uhm, Kwang-Hyun; Lee, Dae-Hong; Ko, Sung-Jea
- Issue Date
- 2018
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Calibration; gaze tracking; computer vision; human computer interaction
- Citation
- IEEE ACCESS, v.6, pp.48840 - 48849
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 6
- Start Page
- 48840
- End Page
- 48849
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/80968
- DOI
- 10.1109/ACCESS.2018.2867235
- ISSN
- 2169-3536
- Abstract
- In general, 3-D gaze tracking methods employ both a frontal-viewing camera and an eye-capturing camera facing the opposite direction to precisely estimate the point-of-regard (POR) in the 3-D space. The extrinsic calibration of these two cameras for accurate 3-D gaze tracking is a challenging task. This paper presents a robust extrinsic calibration method for non-contact gaze tracking in the 3-D space. Even in a noisy environment, the extrinsic calibration parameters are precisely estimated by minimizing the proposed cost function consisting of both the angular and Euclidean errors. Furthermore, using the estimated parameters, the 3-D POR is exactly determined based on the two-view geometry. Compared with the conventional methods, the proposed method provides superior results in experiments considering various factors such as the noise level, head movement, and camera configuration. In real experiments, we achieved an average Euclidean error of 12.6 cm and the average angular error of 0.98 degrees when estimating the 3-D coordinates of PORs that were 4-8 m away from the user.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.