MAAD: A Model and Dataset for "Attended Awareness" in Driving
We propose a computational model to estimate a person's attended awareness of their environment. We define attended awareness to be those parts of a potentially dynamic scene which a person has attended to in recent history and which they are still likely to be physically aware of. Our model ta...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024
|
| Online Access: | https://hdl.handle.net/1721.1/153757 |
| _version_ | 1824458198770253824 |
|---|---|
| author | Gopinath, Deepak Rosman, Guy Stent, Simon Terahata, Katsuya Fletcher, Luke Argall, Brenna Leonard, John |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Gopinath, Deepak Rosman, Guy Stent, Simon Terahata, Katsuya Fletcher, Luke Argall, Brenna Leonard, John |
| author_sort | Gopinath, Deepak |
| collection | MIT |
| description | We propose a computational model to estimate a person's attended awareness of their environment. We define attended awareness to be those parts of a potentially dynamic scene which a person has attended to in recent history and which they are still likely to be physically aware of. Our model takes as input scene information in the form of a video and noisy gaze estimates, and outputs visual saliency, a refined gaze estimate, and an estimate of the person's attended awareness. In order to test our model, we capture a new dataset with a high-precision gaze tracker including 24.5 hours of gaze sequences from 23 subjects attending to videos of driving scenes. The dataset also contains third-party annotations of the subjects' attended awareness based on observations of their scan path. Our results show that our model is able to reasonably estimate attended awareness in a controlled setting, and in the future could potentially be extended to real egocentric driving data to help enable more effective ahead-of-time warnings in safety systems and thereby augment driver performance. We also demonstrate our model's effectiveness on the tasks of saliency, gaze calibration, and denoising, using both our dataset and an existing saliency dataset. |
| first_indexed | 2024-09-23T13:15:08Z |
| format | Article |
| id | mit-1721.1/153757 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:22:05Z |
| publishDate | 2024 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1537572024-11-20T20:21:54Z MAAD: A Model and Dataset for "Attended Awareness" in Driving Gopinath, Deepak Rosman, Guy Stent, Simon Terahata, Katsuya Fletcher, Luke Argall, Brenna Leonard, John Massachusetts Institute of Technology. Department of Mechanical Engineering We propose a computational model to estimate a person's attended awareness of their environment. We define attended awareness to be those parts of a potentially dynamic scene which a person has attended to in recent history and which they are still likely to be physically aware of. Our model takes as input scene information in the form of a video and noisy gaze estimates, and outputs visual saliency, a refined gaze estimate, and an estimate of the person's attended awareness. In order to test our model, we capture a new dataset with a high-precision gaze tracker including 24.5 hours of gaze sequences from 23 subjects attending to videos of driving scenes. The dataset also contains third-party annotations of the subjects' attended awareness based on observations of their scan path. Our results show that our model is able to reasonably estimate attended awareness in a controlled setting, and in the future could potentially be extended to real egocentric driving data to help enable more effective ahead-of-time warnings in safety systems and thereby augment driver performance. We also demonstrate our model's effectiveness on the tasks of saliency, gaze calibration, and denoising, using both our dataset and an existing saliency dataset. 2024-03-14T21:28:57Z 2024-03-14T21:28:57Z 2021-10 2024-03-14T21:14:36Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/153757 Gopinath, Deepak, Rosman, Guy, Stent, Simon, Terahata, Katsuya, Fletcher, Luke et al. 2021. "MAAD: A Model and Dataset for "Attended Awareness" in Driving." en 10.1109/iccvw54120.2021.00382 Creative Commons Attribution-Noncommercial-ShareAlike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE arxiv |
| spellingShingle | Gopinath, Deepak Rosman, Guy Stent, Simon Terahata, Katsuya Fletcher, Luke Argall, Brenna Leonard, John MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title | MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title_full | MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title_fullStr | MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title_full_unstemmed | MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title_short | MAAD: A Model and Dataset for "Attended Awareness" in Driving |
| title_sort | maad a model and dataset for attended awareness in driving |
| url | https://hdl.handle.net/1721.1/153757 |
| work_keys_str_mv | AT gopinathdeepak maadamodelanddatasetforattendedawarenessindriving AT rosmanguy maadamodelanddatasetforattendedawarenessindriving AT stentsimon maadamodelanddatasetforattendedawarenessindriving AT terahatakatsuya maadamodelanddatasetforattendedawarenessindriving AT fletcherluke maadamodelanddatasetforattendedawarenessindriving AT argallbrenna maadamodelanddatasetforattendedawarenessindriving AT leonardjohn maadamodelanddatasetforattendedawarenessindriving |