Gaze Estimation Approach Using Deep Differential Residual Network

被引:9
|
作者
Huang, Longzhao [1 ]
Li, Yujie [1 ]
Wang, Xu [1 ]
Wang, Haoyu [1 ]
Bouridane, Ahmed [2 ]
Chaddad, Ahmad [1 ,3 ]
机构
[1] Guilin Univ Elect Technol, Sch Artificial Intelligence, Jinji Rd, Guilin 541004, Peoples R China
[2] Northumbria Univ, Fac Engn & Environm, Newcastle Upon Tyne NE1 8ST, Tyne & Wear, England
[3] Ecole Technol Super, Lab Imagery Vis & Artificial Intelligence, 1100 Rue Notre Dame O, Montreal, PQ H3C 1K3, Canada
基金
中国国家自然科学基金;
关键词
gaze estimation; gaze calibration; noise image; differential residual network; EYE GAZE;
D O I
10.3390/s22145462
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Gaze estimation, which is a method to determine where a person is looking at given the person's full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with angular-error of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Gaze Estimation Using Residual Neural Network
    Wong, En Teng
    Yean, Seanglidet
    Hu, Qingyao
    Lee, Bu Sung
    Liu, Jigang
    Deepu, Rajan
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS WORKSHOPS (PERCOM WORKSHOPS), 2019, : 411 - 414
  • [2] A Differential Approach for Gaze Estimation
    Liu, Gang
    Yu, Yu
    Mora, Kenneth A. Funes
    Odobez, Jean-Marc
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (03) : 1092 - 1099
  • [3] Age and Gender Estimation using Deep Residual Learning Network
    Lee, Seok Hee
    Hosseini, Sepidehsadat
    Kwon, Hyuk Jin
    Moon, Jaewon
    Koo, Hyung Il
    Cho, Nam Ik
    [J]. 2018 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY (IWAIT), 2018,
  • [4] GFNet: Gaze Focus Network using Attention for Gaze Estimation
    Hu, Daosong
    Huang, Kai
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 2399 - 2404
  • [5] Age and Gender Estimation of Asian Faces Using Deep Residual Network
    Hoang Nguyen
    Hieu Trung Huynh
    [J]. FUTURE DATA AND SECURITY ENGINEERING (FDSE 2019), 2019, 11814 : 274 - 286
  • [6] Eye-Gaze Estimation using a Deep Capsule-based Regression Network
    Bernard, Vivien
    Wannous, Hazem
    Vandeborre, Jean-Philippe
    [J]. 2021 INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), 2021, : 29 - 34
  • [7] Customer Gaze Estimation in Retail Using Deep Learning
    Senarath, Shashimal
    Pathirana, Primesh
    Meedeniya, Dulani
    Jayarathna, Sampath
    [J]. IEEE Access, 2022, 10 : 64904 - 64919
  • [8] Appearance-Based Gaze Estimation Method Using Static Transformer Temporal Differential Network
    Li, Yujie
    Huang, Longzhao
    Chen, Jiahui
    Wang, Xiwen
    Tan, Benying
    [J]. MATHEMATICS, 2023, 11 (03)
  • [9] Customer Gaze Estimation in Retail Using Deep Learning
    Senarath, Shashimal
    Pathirana, Primesh
    Meedeniya, Dulani
    Jayarathna, Sampath
    [J]. IEEE ACCESS, 2022, 10 : 64904 - 64919
  • [10] Gaze Estimation via a Differential Eyes' Appearances Network with a Reference Grid
    Gu, Song
    Wang, Lihui
    He, Long
    He, Xianding
    Wang, Jian
    [J]. ENGINEERING, 2021, 7 (06) : 777 - 786