OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results
This paper summarizes the OpenEDS 2020 Challenge dataset, the proposed baselines, and results obtained by the top three winners of each competition: (1) Gaze prediction Challenge, with the goal of predicting the gaze vector 1 to 5 frames into the future based on a sequence of previous eye images, an...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4769 |
| _version_ | 1827686875251343360 |
|---|---|
| author | Cristina Palmero Abhishek Sharma Karsten Behrendt Kapil Krishnakumar Oleg V. Komogortsev Sachin S. Talathi |
| author_facet | Cristina Palmero Abhishek Sharma Karsten Behrendt Kapil Krishnakumar Oleg V. Komogortsev Sachin S. Talathi |
| author_sort | Cristina Palmero |
| collection | DOAJ |
| description | This paper summarizes the OpenEDS 2020 Challenge dataset, the proposed baselines, and results obtained by the top three winners of each competition: (1) Gaze prediction Challenge, with the goal of predicting the gaze vector 1 to 5 frames into the future based on a sequence of previous eye images, and (2) Sparse Temporal Semantic Segmentation Challenge, with the goal of using temporal information to propagate semantic eye labels to contiguous eye image frames. Both competitions were based on the OpenEDS2020 dataset, a novel dataset of eye-image sequences captured at a frame rate of 100 Hz under controlled illumination, using a virtual-reality head-mounted display with two synchronized eye-facing cameras. The dataset, which we make publicly available for the research community, consists of 87 subjects performing several gaze-elicited tasks, and is divided into 2 subsets, one for each competition task. The proposed baselines, based on deep learning approaches, obtained an average angular error of 5.37 degrees for gaze prediction, and a mean intersection over union score (mIoU) of 84.1% for semantic segmentation. The winning solutions were able to outperform the baselines, obtaining up to 3.17 degrees for the former task and 95.2% mIoU for the latter. |
| first_indexed | 2024-03-10T09:24:49Z |
| format | Article |
| id | doaj.art-8780f5e3534f4105b680853ad5547b99 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:24:49Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8780f5e3534f4105b680853ad5547b992023-11-22T04:55:49ZengMDPI AGSensors1424-82202021-07-012114476910.3390/s21144769OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and ResultsCristina Palmero0Abhishek Sharma1Karsten Behrendt2Kapil Krishnakumar3Oleg V. Komogortsev4Sachin S. Talathi5Department of Mathematics and Informatics, Universitat de Barcelona, 08007 Barcelona, SpainEye Tracking Department, Facebook Reality Labs Research, Redmond, WA 98052, USAFacebook Reality Labs, Menlo Park, CA 94025, USAFacebook Reality Labs, Menlo Park, CA 94025, USAEye Tracking Department, Facebook Reality Labs Research, Redmond, WA 98052, USAEye Tracking Department, Facebook Reality Labs Research, Redmond, WA 98052, USAThis paper summarizes the OpenEDS 2020 Challenge dataset, the proposed baselines, and results obtained by the top three winners of each competition: (1) Gaze prediction Challenge, with the goal of predicting the gaze vector 1 to 5 frames into the future based on a sequence of previous eye images, and (2) Sparse Temporal Semantic Segmentation Challenge, with the goal of using temporal information to propagate semantic eye labels to contiguous eye image frames. Both competitions were based on the OpenEDS2020 dataset, a novel dataset of eye-image sequences captured at a frame rate of 100 Hz under controlled illumination, using a virtual-reality head-mounted display with two synchronized eye-facing cameras. The dataset, which we make publicly available for the research community, consists of 87 subjects performing several gaze-elicited tasks, and is divided into 2 subsets, one for each competition task. The proposed baselines, based on deep learning approaches, obtained an average angular error of 5.37 degrees for gaze prediction, and a mean intersection over union score (mIoU) of 84.1% for semantic segmentation. The winning solutions were able to outperform the baselines, obtaining up to 3.17 degrees for the former task and 95.2% mIoU for the latter.https://www.mdpi.com/1424-8220/21/14/4769gaze predictionsemantic segmentationgaze estimationvideo oculographyvirtual reality |
| spellingShingle | Cristina Palmero Abhishek Sharma Karsten Behrendt Kapil Krishnakumar Oleg V. Komogortsev Sachin S. Talathi OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results Sensors gaze prediction semantic segmentation gaze estimation video oculography virtual reality |
| title | OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results |
| title_full | OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results |
| title_fullStr | OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results |
| title_full_unstemmed | OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results |
| title_short | OpenEDS2020 Challenge on Gaze Tracking for VR: Dataset and Results |
| title_sort | openeds2020 challenge on gaze tracking for vr dataset and results |
| topic | gaze prediction semantic segmentation gaze estimation video oculography virtual reality |
| url | https://www.mdpi.com/1424-8220/21/14/4769 |
| work_keys_str_mv | AT cristinapalmero openeds2020challengeongazetrackingforvrdatasetandresults AT abhisheksharma openeds2020challengeongazetrackingforvrdatasetandresults AT karstenbehrendt openeds2020challengeongazetrackingforvrdatasetandresults AT kapilkrishnakumar openeds2020challengeongazetrackingforvrdatasetandresults AT olegvkomogortsev openeds2020challengeongazetrackingforvrdatasetandresults AT sachinstalathi openeds2020challengeongazetrackingforvrdatasetandresults |