Viewpoint-aware object detection and continuous pose estimation

Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich

Research output: Contribution to journalArticlepeer-review


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 parameterization 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. Finally we introduce the "Weizmann Cars ViewPoint" (WCVP) dataset, a benchmark for evaluating continuous pose estimation. (C) 2012 Elsevier B.V. All rights reserved.
Original languageEnglish
Pages (from-to)923-933
Number of pages11
JournalImage and Vision Computing
Issue number12
StatePublished - Dec 2012


Dive into the research topics of 'Viewpoint-aware object detection and continuous pose estimation'. Together they form a unique fingerprint.

Cite this