ML Anthology

Viewpoint-Aware Object Detection and Pose Estimation

Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich
ICCV 2011 pp. 1275-1282
doi:10.1109/ICCV.2011.6126379 /iccv/2011/glasner2011iccv-viewpoint/

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 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.

ICCV Semantic Scholar

Cite

Text

Glasner et al. "Viewpoint-Aware Object Detection and Pose Estimation." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126379

Markdown

[Glasner et al. "Viewpoint-Aware Object Detection and Pose Estimation." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/glasner2011iccv-viewpoint/) doi:10.1109/ICCV.2011.6126379

BibTeX

@inproceedings{glasner2011iccv-viewpoint,
  title     = {{Viewpoint-Aware Object Detection and Pose Estimation}},
  author    = {Glasner, Daniel and Galun, Meirav and Alpert, Sharon and Basri, Ronen and Shakhnarovich, Gregory},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {1275-1282},
  doi       = {10.1109/ICCV.2011.6126379},
  url       = {https://mlanthology.org/iccv/2011/glasner2011iccv-viewpoint/}
}