Free-head appearance-based eye gaze estimation on mobile devices
Eye gaze tracking plays an important role in human-computer interaction applications. In recent years, many research have been performed to explore gaze estimation methods to handle free-head movement, most of which focused on gaze direction estimation. Gaze point estimation on the screen is another...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/83125 http://hdl.handle.net/10220/49121 |
| _version_ | 1811681304999100416 |
|---|---|
| author | Liu, Jigang Lee, Francis Bu Sung Rajan, Deepu |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Liu, Jigang Lee, Francis Bu Sung Rajan, Deepu |
| author_sort | Liu, Jigang |
| collection | NTU |
| description | Eye gaze tracking plays an important role in human-computer interaction applications. In recent years, many research have been performed to explore gaze estimation methods to handle free-head movement, most of which focused on gaze direction estimation. Gaze point estimation on the screen is another important application. In this paper, we proposed a two-step training network, called GazeEstimator, to improve the estimation accuracy of gaze location on mobile devices. The first step is to train an eye landmarks localization network on 300W-LP dataset [1], and the second step is to train a gaze estimation network on GazeCapture dataset [2]. Some processing operations are performed between the two networks for data cleaning. The first network is able to localize eye precisely on the image, while the gaze estimation network use only eye images and eye grids as inputs, and it is robust to facial expressions and occlusion.Compared with state-of-the-art gaze estimation method, iTracker, our proposed deep network achieves higher accuracy and is able to estimate gaze location even in the condition that the full face cannot be detected. |
| first_indexed | 2024-10-01T03:38:50Z |
| format | Conference Paper |
| id | ntu-10356/83125 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:38:50Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/831252020-03-07T11:48:45Z Free-head appearance-based eye gaze estimation on mobile devices Liu, Jigang Lee, Francis Bu Sung Rajan, Deepu School of Computer Science and Engineering 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) Eye Gaze Estimation Deep Learning Engineering::Computer science and engineering Eye gaze tracking plays an important role in human-computer interaction applications. In recent years, many research have been performed to explore gaze estimation methods to handle free-head movement, most of which focused on gaze direction estimation. Gaze point estimation on the screen is another important application. In this paper, we proposed a two-step training network, called GazeEstimator, to improve the estimation accuracy of gaze location on mobile devices. The first step is to train an eye landmarks localization network on 300W-LP dataset [1], and the second step is to train a gaze estimation network on GazeCapture dataset [2]. Some processing operations are performed between the two networks for data cleaning. The first network is able to localize eye precisely on the image, while the gaze estimation network use only eye images and eye grids as inputs, and it is robust to facial expressions and occlusion.Compared with state-of-the-art gaze estimation method, iTracker, our proposed deep network achieves higher accuracy and is able to estimate gaze location even in the condition that the full face cannot be detected. Accepted version 2019-07-04T01:51:45Z 2019-12-06T15:12:17Z 2019-07-04T01:51:45Z 2019-12-06T15:12:17Z 2019-02-01 2019 Conference Paper Liu, J., Lee, F. B. S., & Rajan, D. (2019). Free-head appearance-based eye gaze estimation on mobile devices. 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). doi:10.1109/ICAIIC.2019.8669057 https://hdl.handle.net/10356/83125 http://hdl.handle.net/10220/49121 10.1109/ICAIIC.2019.8669057 211387 en © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/ICAIIC.2019.8669057 6 p. application/pdf |
| spellingShingle | Eye Gaze Estimation Deep Learning Engineering::Computer science and engineering Liu, Jigang Lee, Francis Bu Sung Rajan, Deepu Free-head appearance-based eye gaze estimation on mobile devices |
| title | Free-head appearance-based eye gaze estimation on mobile devices |
| title_full | Free-head appearance-based eye gaze estimation on mobile devices |
| title_fullStr | Free-head appearance-based eye gaze estimation on mobile devices |
| title_full_unstemmed | Free-head appearance-based eye gaze estimation on mobile devices |
| title_short | Free-head appearance-based eye gaze estimation on mobile devices |
| title_sort | free head appearance based eye gaze estimation on mobile devices |
| topic | Eye Gaze Estimation Deep Learning Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/83125 http://hdl.handle.net/10220/49121 |
| work_keys_str_mv | AT liujigang freeheadappearancebasedeyegazeestimationonmobiledevices AT leefrancisbusung freeheadappearancebasedeyegazeestimationonmobiledevices AT rajandeepu freeheadappearancebasedeyegazeestimationonmobiledevices |