PROBABILISTIC MODELS OF VISUAL APPEARANCE FOR OBJECT IDENTITY, CLASS, AND POSE INFERENCE

The topic of object recognition is a central challenge of computer vision. In addition to being studied as a scientific problem in its own right, it also counts many direct practical applications. We specifically consider robotic applications involving the ma-nipulation, and grasping of everyday objects, in the typical situations that would be encountered by personal service robots. Visual object recognition, in the large sense, is then paramount to provide a robot the sensing capabilities for scene understanding, the localization of objects of interests and the planning of actions such as the grasping of such objects. This thesis presents a number of methods that tackle the related tasks of object de-tection, localization, recognition, and pose estimation in 2D images, of both specific objects and of object categories. We aim at providing techniques that are the most generally applicable, by considering those different tasks as different sides of a same problem, and by not focusing on a specific type of image information or image fea-tures. We first address the use of 3D models of objects for continuous pose estimation