Abstract

We present Active Random Forests, a novel framework to address active vision problems. State of the art focuses on best view- ing parameters selection based on single view classifiers. We propose a multi-view classifier where the decision mechanism of optimally chang- ing viewing parameters is inherent to the classification process. This has many advantages: a) the classifier exploits the entire set of captured im- ages and does not simply aggregate probabilistically per view hypothe- ses; b) actions are based on learnt disambiguating features from all views and are optimally selected using the powerful voting scheme of Random Forests and c) the classifier can take into account the costs of actions. The proposed framework is applied to the task of autonomously unfold- ing clothes by a robot, addressing the problem of best viewpoint selection in classification, grasp point and pose estimation of garments. We show great performance improvement compared to state of the art methods.