Online Driver Distraction Detection Using Long Short-Term Memory

Abstract

Lane-keeping assistance systems for vehicles may be more acceptable to users if the assistance was adaptive to the driver's state. To adapt systems in this way, a method for detection of driver distraction is needed. Thus, we propose a novel technique for online detection of driver's distraction, modeling the long-range temporal context of driving and head tracking data. We show that long short-term memory (LSTM) recurrent neural networks enable a reliable subject-independent detection of inattention with an accuracy of up to 96.6%. Thereby, our LSTM framework significantly outperforms conventional approaches such as support vector machines (SVMs).

Original document

The different versions of the original document can be found in:

• http://hdl.handle.net/10044/1/13933 under the license http://www.rioxx.net/licenses/all-rights-reserved

• http://xplorestaging.ieee.org/ielx5/6979/5779921/05732698.pdf?arnumber=5732698,

http://dx.doi.org/10.1109/tits.2011.2119483

• https://dblp.uni-trier.de/db/journals/tits/tits12.html#WollmerBSSFMT11,

https://ieeexplore.ieee.org/document/5732698,

http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ieee-000005732698,

https://trid.trb.org/view/1107952,

http://ieeexplore.ieee.org/document/5732698,

https://doi.org/10.1109/TITS.2011.2119483,

https://dl.acm.org/doi/10.1109/TITS.2011.2119483,

https://dx.doi.org/10.1109/TITS.2011.2119483,

https://spiral.imperial.ac.uk/handle/10044/1/13933,

[=citjournalarticle_363092_38 https://www.safetylit.org/citations/index.php?fuseaction=citations.viewdetails&citationIds[]=citjournalarticle_363092_38],

https://academic.microsoft.com/#/detail/2166880842

• https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/73306,

https://doi.org/10.1109/TITS.2011.2119483