Viewpoint-aware object detection and continuous pose estimation

  • Authors:
  • Daniel Glasner;Meirav Galun;Sharon Alpert;Ronen Basri;Gregory Shakhnarovich

  • Affiliations:
  • Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Israel;Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Israel;Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Israel;Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Israel;Toyota Technological Institute at Chicago, United States

  • Venue:
  • Image and Vision Computing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.