Unsupervised Object Pose Classification from Short Video Sequences

We address the problem of recognizing the pose of an object category from video sequences capturing the object under small camera movements. This scenario is relevant in applications such as robotic object manipulation or autonomous navigation. We introduce a new algorithm where wemodel an object category as a collection of non parametric probability densities capturing appearance and geometrical variability within a small area of the viewing sphere for different object instances. By regarding the set of frames of the video as realizations of such probability densities, we cast the problem of object pose classification as the one of matching probably density functions in testing and training. Our experimental results on both synthesized and real world data show promising results toward the goal of accurate and efficient pose classification of object categories from video sequences.