Detecting Driver Distraction

The goal of this project was to set up an environment that could be used for data collection for the study of distracted driving with the long term goal of automatically detecting when a driver is distracted and to collect data from 50 subjects using a driving simulator. The route was designed in such a manner that the driver would encounter several hairpin turns, indicated by relevant road signs. Those turns served as places where the driver would experience high cognitive load just keeping the vehicle on the road. These were places where cellphone distractions would create a dangerous situation. The intent was to have some hairpin turns with cellphone distractions and others without, the latter serving as baselines. The goal was to record many drivers and eventually use this data to determine if their driving behavior changed during a distracting event. The database is publicly available on github: https://github.com/DialRC/DistractionDetectionDataset.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Edition: Final Report
  • Features: Figures; References;
  • Pagination: 4p

Subject/Index Terms

Filing Info

  • Accession Number: 01675128
  • Record Type: Publication
  • Contract Numbers: DTRT12GUTG11
  • Files: UTC, NTL, TRIS, ATRI, USDOT
  • Created Date: Jul 2 2018 12:14PM