We present a novel categorical object detection scheme that uses only local contour-based features. A two-stage, partially supervised learning architecture is proposed: a rudimentary detector is learned from a very small set of segmented images and applied to a larger training set of un-segmented images; the second stage bootstraps these detections to learn an improved classifier while explicitly training against clutter. The detectors are learned with a boosting algorithm which creates a location-sensitive classifier using a discriminative set of features from a randomly chosen dictionary of contour fragments. We present results that are very competitive with other state-of-the-art object detection schemes and show robustness to object articulations, clutter, and occlusion. Our major contributions are the application of boosted local contour-based features for object detection in a partially supervised learning framework, and an efficient new boosting procedure for simultaneously selecting features and estimating per-feature parameters.
Contour-based learning for object detection
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 503-510 Vol. 1
2005-01-01
860803 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Contour-Based Learning for Object Detection
British Library Conference Proceedings | 2005
|Contour based object detection using part bundles
British Library Online Contents | 2010
|Object Detection by Contour Segment Networks
British Library Conference Proceedings | 2006
|