adaBoost with “Keypoint Presence Features” for Real-Time Vehicle Visual Detection

This paper presents promising results for real-time vehicle visual detection, obtained with adaBoost using new original “keypoints presence features”. These weak-classifiers produce a boolean response based on presence or absence in the tested image of a “keypoint” (~ a SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as “wheel” or “side skirt”) and thus have a “semantic” meaning.

Language

  • English

Media Info

  • Media Type: CD-ROM
  • Features: Figures; Photos; References;
  • Pagination: 9p
  • Monograph Title: ITS in Daily Life

Subject/Index Terms

Filing Info

  • Accession Number: 01148193
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jan 12 2010 3:16PM