TY - GEN
T1 - Edge-guided near-eye image analysis for head mounted displays
AU - Wang, Zhimin
AU - Zhao, Yuxin
AU - Liu, Yunfei
AU - Lu, Feng
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Eye tracking provides an effective way for interaction in Augmented Reality (AR) Head Mounted Displays (HMDs). Current eye tracking techniques for AR HMDs require eye segmentation and ellipse fitting under near-infrared illumination. However, due to the low contrast between sclera and iris regions and unpredictable reflections, it is still challenging to accomplish accurate iris/pupil segmentation and the corresponding ellipse fitting tasks. In this paper, inspired by the fact that most essential information is encoded in the edge areas, we propose a novel near-eye image analysis method with edge maps as guidance. Specifically, we first utilize an Edge Extraction Network (E2-Net) to predict high-quality edge maps, which only contain eyelids and iris/pupil contours without other undesired edges. Then we feed the edge maps into an Edge-Guided Segmentation and Fitting Network (ESF-Net) for accurate segmentation and ellipse fitting. Extensive experimental results demonstrate that our method outperforms current state-of-the-art methods in near-eye image segmentation and ellipse fitting tasks, based on which we present applications of eye tracking with AR HMD.
AB - Eye tracking provides an effective way for interaction in Augmented Reality (AR) Head Mounted Displays (HMDs). Current eye tracking techniques for AR HMDs require eye segmentation and ellipse fitting under near-infrared illumination. However, due to the low contrast between sclera and iris regions and unpredictable reflections, it is still challenging to accomplish accurate iris/pupil segmentation and the corresponding ellipse fitting tasks. In this paper, inspired by the fact that most essential information is encoded in the edge areas, we propose a novel near-eye image analysis method with edge maps as guidance. Specifically, we first utilize an Edge Extraction Network (E2-Net) to predict high-quality edge maps, which only contain eyelids and iris/pupil contours without other undesired edges. Then we feed the edge maps into an Edge-Guided Segmentation and Fitting Network (ESF-Net) for accurate segmentation and ellipse fitting. Extensive experimental results demonstrate that our method outperforms current state-of-the-art methods in near-eye image segmentation and ellipse fitting tasks, based on which we present applications of eye tracking with AR HMD.
KW - Augmented Reality
KW - Edge Extraction
KW - Eye tracking
KW - Human Computer Interaction (HCI)
KW - Near-eye image analysis
UR - https://www.scopus.com/pages/publications/85123484641
U2 - 10.1109/ISMAR52148.2021.00015
DO - 10.1109/ISMAR52148.2021.00015
M3 - 会议稿件
AN - SCOPUS:85123484641
T3 - Proceedings - 2021 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2021
SP - 11
EP - 20
BT - Proceedings - 2021 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2021
A2 - Marchal, Maud
A2 - Ventura, Jonathan
A2 - Olivier, Anne-Helene
A2 - Wang, Lili
A2 - Radkowski, Rafael
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2021
Y2 - 4 October 2021 through 8 October 2021
ER -