Study on Driver Distraction Detection Using Pattern Recognition for the Reduction of Traffic Accidents

In order to reduce the number of the traffic accident, it may be effective to focus on human factors in the traffic accident. Distraction is one of the key human factor which results in traffic accidents. A driving support system which is optimized for the individual driver’s state and which detects driver’s distraction and a lack of driver awareness of the road traffic environment, in combination with information about the vehicle surroundings, may be an effective means of preventing a traffic accident. In this study, the authors reproduced driver’s cognitive distraction by means of imposing mental loads to the subjects on a driving simulator. By using a stereo camera system, we tracked the driver’s physiological information such as gaze and head rotation directions, and also measured the intervals between R-waves (hereafter, RRI: R-R Interval) in an ECG waveform. Then we extracted pattern recognition features such as the standard deviation of the gaze direction angle and head rotation angle and heart rate RRI. The authors established a detection methodology for driver’s cognitive distraction by means of using the AdaBoost, which is capable of faster and higher accuracy pattern recognition.


  • English

Media Info

  • Media Type: CD-ROM
  • Features: Figures; References; Tables;
  • Pagination: 8p
  • Monograph Title: ITS in Daily Life

Subject/Index Terms

Filing Info

  • Accession Number: 01150268
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Feb 3 2010 11:43AM