Eye Tracking for Everyone
From scientific research to commercial applications, eye tracking is an important tool across many domains. Despite its range of applications, eye tracking has yet to become a pervasive technology. We believe that we can put the power of eye tracking in everyone's palm by building eye tracking...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/111782 https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0003-1462-2313 https://orcid.org/0000-0003-0212-5643 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1826202106361544704 |
|---|---|
| author | Kellnhofer, Petr Bhandarkar, Suchendra Khosla, Aditya Kannan, Harini D. Matusik, Wojciech Torralba, Antonio |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Kellnhofer, Petr Bhandarkar, Suchendra Khosla, Aditya Kannan, Harini D. Matusik, Wojciech Torralba, Antonio |
| author_sort | Kellnhofer, Petr |
| collection | MIT |
| description | From scientific research to commercial applications, eye tracking is an important tool across many domains. Despite its range of applications, eye tracking has yet to become a pervasive technology. We believe that we can put the power of eye tracking in everyone's palm by building eye tracking software that works on commodity hardware such as mobile phones and tablets, without the need for additional sensors or devices. We tackle this problem by introducing GazeCapture, the first large-scale dataset for eye tracking, containing data from over 1450 people consisting of almost 2:5M frames. Using GazeCapture, we train iTracker, a convolutional neural network for eye tracking, which achieves a significant reduction in error over previous approaches while running in real time (10-15fps) on a modern mobile device. Our model achieves a prediction error of 1.71cm and 2.53cm without calibration on mobile phones and tablets respectively. With calibration, this is reduced to 1.34cm and 2.12cm. Further, we demonstrate that the features learned by iTracker generalize well to other datasets, achieving state-of-the-art results. |
| first_indexed | 2024-09-23T12:01:58Z |
| format | Article |
| id | mit-1721.1/111782 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:01:58Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1117822022-10-01T07:44:38Z Eye Tracking for Everyone Kellnhofer, Petr Bhandarkar, Suchendra Khosla, Aditya Kannan, Harini D. Matusik, Wojciech Torralba, Antonio Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Media Laboratory Khosla, Aditya Kellnhofer, Petr Kannan, Harini D. Matusik, Wojciech Torralba, Antonio From scientific research to commercial applications, eye tracking is an important tool across many domains. Despite its range of applications, eye tracking has yet to become a pervasive technology. We believe that we can put the power of eye tracking in everyone's palm by building eye tracking software that works on commodity hardware such as mobile phones and tablets, without the need for additional sensors or devices. We tackle this problem by introducing GazeCapture, the first large-scale dataset for eye tracking, containing data from over 1450 people consisting of almost 2:5M frames. Using GazeCapture, we train iTracker, a convolutional neural network for eye tracking, which achieves a significant reduction in error over previous approaches while running in real time (10-15fps) on a modern mobile device. Our model achieves a prediction error of 1.71cm and 2.53cm without calibration on mobile phones and tablets respectively. With calibration, this is reduced to 1.34cm and 2.12cm. Further, we demonstrate that the features learned by iTracker generalize well to other datasets, achieving state-of-the-art results. 2017-10-04T15:28:49Z 2017-10-04T15:28:49Z 2016-12 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-8851-1 1063-6919 http://hdl.handle.net/1721.1/111782 Krafka, Kyle et al. “Eye Tracking for Everyone.” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30 2016, Las Vegas, Neveda, USA, Institute of Electrical and Electronics Engineers (IEEE), December 2016: 2176-2184 © 2016 Institute of Electrical and Electronics Engineers (IEEE) https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0003-1462-2313 https://orcid.org/0000-0003-0212-5643 https://orcid.org/0000-0003-4915-0256 en_US http://dx.doi.org/10.1109/CVPR.2016.239 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT Web Domain |
| spellingShingle | Kellnhofer, Petr Bhandarkar, Suchendra Khosla, Aditya Kannan, Harini D. Matusik, Wojciech Torralba, Antonio Eye Tracking for Everyone |
| title | Eye Tracking for Everyone |
| title_full | Eye Tracking for Everyone |
| title_fullStr | Eye Tracking for Everyone |
| title_full_unstemmed | Eye Tracking for Everyone |
| title_short | Eye Tracking for Everyone |
| title_sort | eye tracking for everyone |
| url | http://hdl.handle.net/1721.1/111782 https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0003-1462-2313 https://orcid.org/0000-0003-0212-5643 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT kellnhoferpetr eyetrackingforeveryone AT bhandarkarsuchendra eyetrackingforeveryone AT khoslaaditya eyetrackingforeveryone AT kannanharinid eyetrackingforeveryone AT matusikwojciech eyetrackingforeveryone AT torralbaantonio eyetrackingforeveryone |