Viewpoint-Aware Object Detection and Pose Estimation

We describe an approach to category-level detection and viewpoint estimation for rigid 3D objects from single 2D images. In contrast to many existing methods, we directly integrate 3D reasoning with an appearance-based voting architecture. Our method relies on a nonparametric representation of a joint distribution of shape and appearance of the object class. Our voting method employs a novel parametrization of joint detection and viewpoint hypothesis space, allowing efficient accumulation of evidence. We combine this with a re-scoring and refinement mechanism, using an ensemble of view-specific Support Vector Machines. We evaluate the performance of our approach in detection and pose estimation of cars on a number of benchmark datasets.

• Type: Journal
• Year: 2011
• Where: ICCV
• Authors: Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich
• Keywords: Computer Vision, Hypothesis Space, ICCV 2011, Rigid 3D Objects, Support Vector Machines