Object Detection Via Boosted Deformable Features
It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this paper, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. The authors introduce using deformable features with boosted ensembles. A deformable feature adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. They empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.