Monocular 3D gaze estimation using feature discretization and attention mechanism

被引:0
|
作者
Sha, Tong [1 ]
Sun, Jinglin [1 ]
Pun, Siohang [2 ]
Liu, Yu [1 ]
机构
[1] Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China
[2] Univ Macau, Inst Microelect, Macau 999078, Peoples R China
关键词
A;
D O I
10.1007/s11801-023-2203-1
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Gaze estimation has become an important field of image and information processing. Estimating gaze from full-face images using convolutional neural network (CNN) has achieved fine accuracy. However, estimating gaze from eye images is very challenging due to the less information contained in eye images than in full-face images, and it's still vital since eye-image-based methods have wider applications. In this paper, we propose the discretization-gaze network (DGaze-Net) to optimize monocular three-dimensional (3D) gaze estimation accuracy by feature discretization and attention mechanism. The gaze predictor of DGaze-Net is optimized based on feature discretization. By discretizing the gaze angle into K bins, a classification constraint is added to the gaze predictor. In the gaze predictor, the gaze angle is pre-applied with a binned classification before regressing with the real gaze angle to improve gaze estimation accuracy. In addition, the attention mechanism is applied to the backbone to enhance the ability to extract eye features related to gaze. The proposed method is validated on three gaze datasets and achieves encouraging gaze estimation accuracy.
引用
收藏
页码:301 / 306
页数:6
相关论文
共 50 条
  • [1] Monocular 3D gaze estimation using feature discretization and attention mechanism
    Tong Sha
    Jinglin Sun
    Siohang Pun
    Yu Liu
    [J]. Optoelectronics Letters, 2023, 19 : 301 - 306
  • [2] Monocular 3D gaze estimation using feature discretization and attention mechanism
    SHA Tong
    SUN Jinglin
    PUN Siohang
    LIU Yu
    [J]. Optoelectronics Letters, 2023, 19 (05) : 301 - 306
  • [3] 3D Gaze Estimation Based on Facial Feature Tracking
    Man, Yi
    Zhao, Xinbo
    Zhang, Ke
    [J]. INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2012), 2013, 8768
  • [4] A 3D Gaze Estimation Method Based on Facial Feature Tracking
    Zhao, Xinbo
    Zou, Xiaochun
    Chi, Zheru
    [J]. 2012 INTERNATIONAL CONFERENCE ON COMPUTERIZED HEALTHCARE (ICCH), 2012, : 13 - 16
  • [5] Accuracy of Monocular Gaze Tracking on 3D Geometry
    Wang, Xi
    Lindlbauer, David
    Lessig, Christian
    Alexa, Marc
    [J]. EYE TRACKING AND VISUALIZATION: FOUNDATIONS, TECHNIQUES, AND APPLICATIONS, ETVIS 2015, 2017, : 169 - 184
  • [6] Multi-feature fusion gaze estimation based on attention mechanism
    Hu, Zhangfang
    Xia, Yanling
    Luo, Yuan
    Wang, Lan
    [J]. OPTOELECTRONIC IMAGING AND MULTIMEDIA TECHNOLOGY VIII, 2021, 11897
  • [7] Boosting Monocular 3D Human Pose Estimation With Part Aware Attention
    Xue, Youze
    Chen, Jiansheng
    Gu, Xiangming
    Ma, Huimin
    Ma, Hongbing
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 4278 - 4291
  • [8] 3D gaze estimation and interaction
    Ki, Jeongseok
    Kwon, Yong-Moo
    [J]. 2008 3DTV-CONFERENCE: THE TRUE VISION - CAPTURE, TRANSMISSION AND DISPLAY OF 3D VIDEO, 2008, : 353 - 356
  • [9] SPATIO-TEMPORAL ATTENTION GRAPH FOR MONOCULAR 3D HUMAN POSE ESTIMATION
    Zhang, Lijun
    Shao, Xiaohu
    Li, Zhenghao
    Zhou, Xiang-Dong
    Shi, Yu
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 1231 - 1235
  • [10] 3D Hand Pose Estimation From Monocular RGB With Feature Interaction Module
    Guo, Shaoxiang
    Rigall, Eric
    Ju, Yakun
    Dong, Junyu
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (08) : 5293 - 5306