Contour-based learning for object detection
Jamie Shotton, Andrew Blake, Roberto Cipolla · 2005
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.
Cited by 287 works. doi:10.1109/iccv.2005.63
Authors
References
- Rapid object detection using a boosted cascade of simple features
- Experiments with a new boosting algorithm
- Object class recognition by unsupervised scale-invariant learning
- Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
- Pictorial Structures for Object Recognition
- Unsupervised Learning of Models for Recognition
- "GrabCut"
- A probabilistic approach to object recognition using local photometry and global geometry
- Combined Object Categorization and Segmentation With An Implicit Shape Model
- Sharing features: efficient boosting procedures for multiclass object detection