Gaze Estimation Approach Using Deep Differential Residual Network
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, t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5462 |
| _version_ | 1797415814485245952 |
|---|---|
| author | Longzhao Huang Yujie Li Xu Wang Haoyu Wang Ahmed Bouridane Ahmad Chaddad |
| author_facet | Longzhao Huang Yujie Li Xu Wang Haoyu Wang Ahmed Bouridane Ahmad Chaddad |
| author_sort | Longzhao Huang |
| collection | DOAJ |
| description | 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 <i>angular-error</i> 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. |
| first_indexed | 2024-03-09T05:55:00Z |
| format | Article |
| id | doaj.art-21afbfca24a24525ab750d1b4e78e82c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:55:00Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-21afbfca24a24525ab750d1b4e78e82c2023-12-03T12:14:03ZengMDPI AGSensors1424-82202022-07-012214546210.3390/s22145462Gaze Estimation Approach Using Deep Differential Residual NetworkLongzhao Huang0Yujie Li1Xu Wang2Haoyu Wang3Ahmed Bouridane4Ahmad Chaddad5School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, ChinaSchool of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, ChinaSchool of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, ChinaSchool of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, ChinaFaculty of Engineering and Environment, Northumbria University, Newcastle NE18ST, UKSchool of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, ChinaGaze 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 <i>angular-error</i> 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.https://www.mdpi.com/1424-8220/22/14/5462gaze estimationgaze calibrationnoise imagedifferential residual network |
| spellingShingle | Longzhao Huang Yujie Li Xu Wang Haoyu Wang Ahmed Bouridane Ahmad Chaddad Gaze Estimation Approach Using Deep Differential Residual Network Sensors gaze estimation gaze calibration noise image differential residual network |
| title | Gaze Estimation Approach Using Deep Differential Residual Network |
| title_full | Gaze Estimation Approach Using Deep Differential Residual Network |
| title_fullStr | Gaze Estimation Approach Using Deep Differential Residual Network |
| title_full_unstemmed | Gaze Estimation Approach Using Deep Differential Residual Network |
| title_short | Gaze Estimation Approach Using Deep Differential Residual Network |
| title_sort | gaze estimation approach using deep differential residual network |
| topic | gaze estimation gaze calibration noise image differential residual network |
| url | https://www.mdpi.com/1424-8220/22/14/5462 |
| work_keys_str_mv | AT longzhaohuang gazeestimationapproachusingdeepdifferentialresidualnetwork AT yujieli gazeestimationapproachusingdeepdifferentialresidualnetwork AT xuwang gazeestimationapproachusingdeepdifferentialresidualnetwork AT haoyuwang gazeestimationapproachusingdeepdifferentialresidualnetwork AT ahmedbouridane gazeestimationapproachusingdeepdifferentialresidualnetwork AT ahmadchaddad gazeestimationapproachusingdeepdifferentialresidualnetwork |