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

Taoufik Bdiri (1) , Fabien Moutarde (1) , Nicolas Bourdis (1) , Bruno Steux (1)

1 CAOR - Centre de Robotique

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

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. ⟨hal-00422581⟩