AdaBoost with "keypoint presence features" for real-time vehivle visual detection

Abstract : We present 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [12 references]  Display  Hide  Download
Contributor : Fabien Moutarde <>
Submitted on : Wednesday, October 7, 2009 - 4:16:20 PM
Last modification on : Monday, November 12, 2018 - 11:01:00 AM
Document(s) archivé(s) le : Wednesday, June 16, 2010 - 12:28:35 AM


Files produced by the author(s)


  • HAL Id : hal-00422581, version 1
  • ARXIV : 0910.1273


Taoufik Bdiri, Fabien Moutarde, Nicolas Bourdis, Bruno Steux. AdaBoost with "keypoint presence features" for real-time vehivle visual detection. 16th World Congress on Intelligent Transport Systems (ITSwc'2009), Sep 2009, Sweden. 2009. 〈hal-00422581〉



Record views


Files downloads