GazeTrak: Exploring Acoustic-based Eye Tracking on a Glass Frame
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914691859611648 |
|---|---|
| author | Li, Ke Zhang, Ruidong Chen, Boao Chen, Siyuan Yin, Sicheng Mahmud, Saif Liang, Qikang Guimbretière, François Zhang, Cheng |
| author_facet | Li, Ke Zhang, Ruidong Chen, Boao Chen, Siyuan Yin, Sicheng Mahmud, Saif Liang, Qikang Guimbretière, François Zhang, Cheng |
| contents | In this paper, we present GazeTrak, the first acoustic-based eye tracking system on glasses. Our system only needs one speaker and four microphones attached to each side of the glasses. These acoustic sensors capture the formations of the eyeballs and the surrounding areas by emitting encoded inaudible sound towards eyeballs and receiving the reflected signals. These reflected signals are further processed to calculate the echo profiles, which are fed to a customized deep learning pipeline to continuously infer the gaze position. In a user study with 20 participants, GazeTrak achieves an accuracy of 3.6° within the same remounting session and 4.9° across different sessions with a refreshing rate of 83.3 Hz and a power signature of 287.9 mW. Furthermore, we report the performance of our gaze tracking system fully implemented on an MCU with a low-power CNN accelerator (MAX78002). In this configuration, the system runs at up to 83.3 Hz and has a total power signature of 95.4 mW with a 30 Hz FPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14634 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GazeTrak: Exploring Acoustic-based Eye Tracking on a Glass Frame Li, Ke Zhang, Ruidong Chen, Boao Chen, Siyuan Yin, Sicheng Mahmud, Saif Liang, Qikang Guimbretière, François Zhang, Cheng Human-Computer Interaction In this paper, we present GazeTrak, the first acoustic-based eye tracking system on glasses. Our system only needs one speaker and four microphones attached to each side of the glasses. These acoustic sensors capture the formations of the eyeballs and the surrounding areas by emitting encoded inaudible sound towards eyeballs and receiving the reflected signals. These reflected signals are further processed to calculate the echo profiles, which are fed to a customized deep learning pipeline to continuously infer the gaze position. In a user study with 20 participants, GazeTrak achieves an accuracy of 3.6° within the same remounting session and 4.9° across different sessions with a refreshing rate of 83.3 Hz and a power signature of 287.9 mW. Furthermore, we report the performance of our gaze tracking system fully implemented on an MCU with a low-power CNN accelerator (MAX78002). In this configuration, the system runs at up to 83.3 Hz and has a total power signature of 95.4 mW with a 30 Hz FPS. |
| title | GazeTrak: Exploring Acoustic-based Eye Tracking on a Glass Frame |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2402.14634 |