Multi-feature fusion gaze estimation based on attention mechanism

Zhangfang Hu; Yanling Xia; Yuan Luo; Lan Wang

doi:10.1117/12.2602019

9 October 2021 Multi-feature fusion gaze estimation based on attention mechanism

Zhangfang Hu, Yanling Xia, Yuan Luo, Lan Wang

Proceedings Volume 11897, Optoelectronic Imaging and Multimedia Technology VIII; 118970Z (2021) https://doi.org/10.1117/12.2602019
Event: SPIE/COS Photonics Asia, 2021, Nantong, JS, China

Conference Poster

Abstract

The variable head pose and low-quality eye images in natural scenes can lead to low accuracy of gaze estimation. In this paper, we propose a multi-feature fusion gaze estimation model based on the attention mechanism. First, face and eye feature extractors based on the group convolution channel and spatial attention mechanism (GCCSAM) are designed to use channel and spatial information to adaptively select and enhance important features in face images and two eye images, and suppress information irrelevant to gaze estimation. Then we design two feature fusion networks to fuse the features of face, two eyes and pupil center position, thus avoiding the effects of two-eye asymmetry and inaccurate head pose estimation on gaze estimation. The average angular error of the proposed method is 4.1° on MPIIGaze and 5.2° on EyeDiap. Compared with the current mainstream methods, our method effectively improves the accuracy and robustness of gaze estimation in natural scenes.

Conference Presentation

Citation Download Citation

Zhangfang Hu, Yanling Xia, Yuan Luo, and Lan Wang "Multi-feature fusion gaze estimation based on attention mechanism", Proc. SPIE 11897, Optoelectronic Imaging and Multimedia Technology VIII, 118970Z (9 October 2021); https://doi.org/10.1117/12.2602019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available