Multimodal classification with deformable part-based models for urban cartography

Data from satellite and aerial images are now widely used by everyone. These images contain information from different frequency bands that help to characterize areas of interest. In this paper we study a framework for object detection in aerial image based on discriminatively-trained models trained on multimodal data. Specifically, we investigate a method to merge outputs of large margin classifiers trained on images from different sensors: we use the ranking ability of these classifiers to learn a probabilistic model.