This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
We propose a novel solution to object detection, localization and pose estimation with applications in robot vision. The proposed method is especially applicable when the objects ...
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
Hough transform based object detectors learn a mapping from the image domain to a Hough voting space. Within this space, object hypotheses are formed by local maxima. The votes con...