Model-based recognition of an object typically involves matching dense 3D range data. The computational cost is directly affected by the amount of data of which a transformation n...
We address the problem of object recognition in computer vision. We represent each model and the scene in the form of Attributed Relational Graph. A multiple region representation...
Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estima...
In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...