Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios

Javier Araluce; Luis M. Bergasa; Carlos Gómez-Huélamo; Rafael Barea; Elena López-Guillén; Felipe Arango; Óscar Pérez-Gil

doi:10.1007/978-3-030-62579-5_19

Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios

Javier Araluce^*
, Luis M. Bergasa
, Carlos Gómez-Huélamo
, Rafael Barea
, Elena López-Guillén
, Felipe Arango
, Óscar Pérez-Gil

^*Corresponding author for this work

University of Alcalá

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Gaze estimation is a typical approach to monitor the driver attention on the road scene. This indicator is of great importance in safe driving and in the design of the takeover control strategy for a Level 3 and Level 4 automation system. Nowadays, most of eye gaze tracking techniques are intrusive and costly, which limits their applicability over real vehicles. On the other hand, current databases used for gaze validation face the driver attention task focused on critical situations in simulation but they do not encounter actual accidents. This paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the art OpenFace 2.0 Toolkit[3] to visualise the driver attention simulation on prerecorded real traffic scenes through a heat map. The proposal has been validated by using the recent and challenging public dataset DADA2000[9] which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our system with an expensive desktop-mounted eye-tracker, obtaining on par results and showing it is a good tool for driver attention monitoring able to be used in the design of take over systems and driving scenarios awareness systems for automated vehicles.

Original language	English
Title of host publication	Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020
Editors	Luis M. Bergasa, Manuel Ocaña, Rafael Barea, Elena López-Guillén, Pedro Revenga
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	274-288
Number of pages	15
ISBN (Print)	9783030625788
DOIs	https://doi.org/10.1007/978-3-030-62579-5_19
Publication status	Published - 2021
Externally published	Yes
Event	21st International Workshop of Physical Agents, WAF 2020 - Alcalá de Henares, Madrid, Spain Duration: 19 Nov 2020 → 20 Nov 2020

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1285
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	21st International Workshop of Physical Agents, WAF 2020
Country/Territory	Spain
City	Alcalá de Henares, Madrid
Period	19/11/20 → 20/11/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Accidental scenarios
Computer vision
Driver attention
Gaze estimation
Heat map

Access to Document

10.1007/978-3-030-62579-5_19

Cite this

Araluce, J., Bergasa, L. M., Gómez-Huélamo, C., Barea, R., López-Guillén, E., Arango, F., & Pérez-Gil, Ó. (2021). Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios. In L. M. Bergasa, M. Ocaña, R. Barea, E. López-Guillén, & P. Revenga (Eds.), Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020 (pp. 274-288). (Advances in Intelligent Systems and Computing; Vol. 1285). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-62579-5_19

Araluce, Javier ; Bergasa, Luis M. ; Gómez-Huélamo, Carlos et al. / Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios. Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020. editor / Luis M. Bergasa ; Manuel Ocaña ; Rafael Barea ; Elena López-Guillén ; Pedro Revenga. Springer Science and Business Media Deutschland GmbH, 2021. pp. 274-288 (Advances in Intelligent Systems and Computing).

@inproceedings{adaa9d07cb5b42a38bf31107349522fa,

title = "Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios",

abstract = "Gaze estimation is a typical approach to monitor the driver attention on the road scene. This indicator is of great importance in safe driving and in the design of the takeover control strategy for a Level 3 and Level 4 automation system. Nowadays, most of eye gaze tracking techniques are intrusive and costly, which limits their applicability over real vehicles. On the other hand, current databases used for gaze validation face the driver attention task focused on critical situations in simulation but they do not encounter actual accidents. This paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the art OpenFace 2.0 Toolkit[3] to visualise the driver attention simulation on prerecorded real traffic scenes through a heat map. The proposal has been validated by using the recent and challenging public dataset DADA2000[9] which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our system with an expensive desktop-mounted eye-tracker, obtaining on par results and showing it is a good tool for driver attention monitoring able to be used in the design of take over systems and driving scenarios awareness systems for automated vehicles.",

keywords = "Accidental scenarios, Computer vision, Driver attention, Gaze estimation, Heat map",

author = "Javier Araluce and Bergasa, \{Luis M.\} and Carlos G{\'o}mez-Hu{\'e}lamo and Rafael Barea and Elena L{\'o}pez-Guill{\'e}n and Felipe Arango and {\'O}scar P{\'e}rez-Gil",

note = "Publisher Copyright: {\textcopyright} 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.; 21st International Workshop of Physical Agents, WAF 2020 ; Conference date: 19-11-2020 Through 20-11-2020",

year = "2021",

doi = "10.1007/978-3-030-62579-5\_19",

language = "English",

isbn = "9783030625788",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "274--288",

editor = "Bergasa, \{Luis M.\} and Manuel Oca{\~n}a and Rafael Barea and Elena L{\'o}pez-Guill{\'e}n and Pedro Revenga",

booktitle = "Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020",

address = "Germany",

}

Araluce, J, Bergasa, LM, Gómez-Huélamo, C, Barea, R, López-Guillén, E, Arango, F & Pérez-Gil, Ó 2021, Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios. in LM Bergasa, M Ocaña, R Barea, E López-Guillén & P Revenga (eds), Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020. Advances in Intelligent Systems and Computing, vol. 1285, Springer Science and Business Media Deutschland GmbH, pp. 274-288, 21st International Workshop of Physical Agents, WAF 2020, Alcalá de Henares, Madrid, Spain, 19/11/20. https://doi.org/10.1007/978-3-030-62579-5_19

Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios. / Araluce, Javier; Bergasa, Luis M.; Gómez-Huélamo, Carlos et al.
Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020. ed. / Luis M. Bergasa; Manuel Ocaña; Rafael Barea; Elena López-Guillén; Pedro Revenga. Springer Science and Business Media Deutschland GmbH, 2021. p. 274-288 (Advances in Intelligent Systems and Computing; Vol. 1285).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios

AU - Araluce, Javier

AU - Bergasa, Luis M.

AU - Gómez-Huélamo, Carlos

AU - Barea, Rafael

AU - López-Guillén, Elena

AU - Arango, Felipe

AU - Pérez-Gil, Óscar

PY - 2021

Y1 - 2021

N2 - Gaze estimation is a typical approach to monitor the driver attention on the road scene. This indicator is of great importance in safe driving and in the design of the takeover control strategy for a Level 3 and Level 4 automation system. Nowadays, most of eye gaze tracking techniques are intrusive and costly, which limits their applicability over real vehicles. On the other hand, current databases used for gaze validation face the driver attention task focused on critical situations in simulation but they do not encounter actual accidents. This paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the art OpenFace 2.0 Toolkit[3] to visualise the driver attention simulation on prerecorded real traffic scenes through a heat map. The proposal has been validated by using the recent and challenging public dataset DADA2000[9] which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our system with an expensive desktop-mounted eye-tracker, obtaining on par results and showing it is a good tool for driver attention monitoring able to be used in the design of take over systems and driving scenarios awareness systems for automated vehicles.

AB - Gaze estimation is a typical approach to monitor the driver attention on the road scene. This indicator is of great importance in safe driving and in the design of the takeover control strategy for a Level 3 and Level 4 automation system. Nowadays, most of eye gaze tracking techniques are intrusive and costly, which limits their applicability over real vehicles. On the other hand, current databases used for gaze validation face the driver attention task focused on critical situations in simulation but they do not encounter actual accidents. This paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the art OpenFace 2.0 Toolkit[3] to visualise the driver attention simulation on prerecorded real traffic scenes through a heat map. The proposal has been validated by using the recent and challenging public dataset DADA2000[9] which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our system with an expensive desktop-mounted eye-tracker, obtaining on par results and showing it is a good tool for driver attention monitoring able to be used in the design of take over systems and driving scenarios awareness systems for automated vehicles.

KW - Accidental scenarios

KW - Computer vision

KW - Driver attention

KW - Gaze estimation

KW - Heat map

UR - https://www.scopus.com/pages/publications/85097397904

U2 - 10.1007/978-3-030-62579-5_19

DO - 10.1007/978-3-030-62579-5_19

M3 - Conference contribution

AN - SCOPUS:85097397904

SN - 9783030625788

T3 - Advances in Intelligent Systems and Computing

SP - 274

EP - 288

BT - Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020

A2 - Bergasa, Luis M.

A2 - Ocaña, Manuel

A2 - Barea, Rafael

A2 - López-Guillén, Elena

A2 - Revenga, Pedro

PB - Springer Science and Business Media Deutschland GmbH

T2 - 21st International Workshop of Physical Agents, WAF 2020

Y2 - 19 November 2020 through 20 November 2020

ER -

Araluce J, Bergasa LM, Gómez-Huélamo C, Barea R, López-Guillén E, Arango F et al. Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios. In Bergasa LM, Ocaña M, Barea R, López-Guillén E, Revenga P, editors, Advances in Physical Agents II - Proceedings of the 21st International Workshop of Physical Agents WAF 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 274-288. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-62579-5_19

Integrating OpenFace 2.0 Toolkit for Driver Attention Estimation in Challenging Accidental Scenarios

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this