‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification
Accurate, robust, inexpensive gaze tracking in the car can help keep a driver safe by facilitating the more effective study of how to improve (i) vehicle interfaces and (ii) the design of future advanced driver assistance systems. In this study, the authors estimate head pose and eye pose from monoc...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2016-06-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2015.0296 |
_version_ | 1797684936548810752 |
---|---|
author | Lex Fridman Joonbum Lee Bryan Reimer Trent Victor |
author_facet | Lex Fridman Joonbum Lee Bryan Reimer Trent Victor |
author_sort | Lex Fridman |
collection | DOAJ |
description | Accurate, robust, inexpensive gaze tracking in the car can help keep a driver safe by facilitating the more effective study of how to improve (i) vehicle interfaces and (ii) the design of future advanced driver assistance systems. In this study, the authors estimate head pose and eye pose from monocular video using methods developed extensively in prior work and ask two new interesting questions. First, how much better can they classify driver gaze using head and eye pose versus just using head pose? Second, are there individual‐specific gaze strategies that strongly correlate with how much gaze classification improves with the addition of eye pose information? The authors answer these questions by evaluating data drawn from an on‐road study of 40 drivers. The main insight of the study is conveyed through the analogy of an ‘owl’ and ‘lizard’ which describes the degree to which the eyes and the head move when shifting gaze. When the head moves a lot (‘owl’), not much classification improvement is attained by estimating eye pose on top of head pose. On the other hand, when the head stays still and only the eyes move (‘lizard’), classification accuracy increases significantly from adding in eye pose. The authors characterise how that accuracy varies between people, gaze strategies, and gaze regions. |
first_indexed | 2024-03-12T00:37:02Z |
format | Article |
id | doaj.art-4c5b48973559425bac5bcba6f65199bb |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:37:02Z |
publishDate | 2016-06-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-4c5b48973559425bac5bcba6f65199bb2023-09-15T09:26:55ZengWileyIET Computer Vision1751-96321751-96402016-06-0110430831410.1049/iet-cvi.2015.0296‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classificationLex Fridman0Joonbum Lee1Bryan Reimer2Trent Victor3Massachusetts Institute of Technology (MIT)CambridgeMassachusetts02142USAMassachusetts Institute of Technology (MIT)CambridgeMassachusetts02142USAMassachusetts Institute of Technology (MIT)CambridgeMassachusetts02142USASAFERChalmers University of TechnologyGothenburgSE‐412 96SwedenAccurate, robust, inexpensive gaze tracking in the car can help keep a driver safe by facilitating the more effective study of how to improve (i) vehicle interfaces and (ii) the design of future advanced driver assistance systems. In this study, the authors estimate head pose and eye pose from monocular video using methods developed extensively in prior work and ask two new interesting questions. First, how much better can they classify driver gaze using head and eye pose versus just using head pose? Second, are there individual‐specific gaze strategies that strongly correlate with how much gaze classification improves with the addition of eye pose information? The authors answer these questions by evaluating data drawn from an on‐road study of 40 drivers. The main insight of the study is conveyed through the analogy of an ‘owl’ and ‘lizard’ which describes the degree to which the eyes and the head move when shifting gaze. When the head moves a lot (‘owl’), not much classification improvement is attained by estimating eye pose on top of head pose. On the other hand, when the head stays still and only the eyes move (‘lizard’), classification accuracy increases significantly from adding in eye pose. The authors characterise how that accuracy varies between people, gaze strategies, and gaze regions.https://doi.org/10.1049/iet-cvi.2015.0296head pose pattern estimationeye pose pattern estimationdriver gaze classificationinexpensive gaze trackingvehicle interfacesfuture advanced driver assistance systems |
spellingShingle | Lex Fridman Joonbum Lee Bryan Reimer Trent Victor ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification IET Computer Vision head pose pattern estimation eye pose pattern estimation driver gaze classification inexpensive gaze tracking vehicle interfaces future advanced driver assistance systems |
title | ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification |
title_full | ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification |
title_fullStr | ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification |
title_full_unstemmed | ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification |
title_short | ‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification |
title_sort | owl and lizard patterns of head pose and eye pose in driver gaze classification |
topic | head pose pattern estimation eye pose pattern estimation driver gaze classification inexpensive gaze tracking vehicle interfaces future advanced driver assistance systems |
url | https://doi.org/10.1049/iet-cvi.2015.0296 |
work_keys_str_mv | AT lexfridman owlandlizardpatternsofheadposeandeyeposeindrivergazeclassification AT joonbumlee owlandlizardpatternsofheadposeandeyeposeindrivergazeclassification AT bryanreimer owlandlizardpatternsofheadposeandeyeposeindrivergazeclassification AT trentvictor owlandlizardpatternsofheadposeandeyeposeindrivergazeclassification |