Image Recognition Algorithm of Front Collision Warning System Using Monocular Camera for CA NCAP

Collision Avoidance New Car Assessment Program NCAP (CA NCAP) was issued towards reducing traffic accidents in the USA. Cost reduction is essential for spreading these systems in the market and making this program effective. A multi-function front camera system appears promising, which can realize two functions of forward collision warning (FCW) and lane departure warning (LDW) in CA NCAP by one sensor. However, obstacle recognition applying image processing is still a difficult challenge due to the severe illumination condition in general outdoor environment. Furthermore, large calculation amount is necessary for the recognition processing, which makes hardware expensive. The authors have developed efficient algorithms based on stochastic concept in order to resolve these challenges. Optical flow combined with pattern identification based on statistical probability is adopted to improve the recognition robustness. And, structural vehicle pattern classifier was designed to make adjustments easy in case of recognition errors.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; Photos; References;
  • Pagination: 10p
  • Monograph Title: 18th ITS World Congress, Orlando, 2011. Proceedings

Subject/Index Terms

Filing Info

  • Accession Number: 01484690
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jun 20 2013 8:15PM