ML Anthology

Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects

Stefan Hinterstoisser, Vincent Lepetit, Slobodan Ilic, Pascal Fua, Nassir Navab
CVPR 2010 pp. 2257-2264
doi:10.1109/CVPR.2010.5539908 /cvpr/2010/hinterstoisser2010cvpr-dominant/

Abstract

We present a method for real-time 3D object detection that does not require a time consuming training stage, and can handle untextured objects. At its core, is a novel template representation that is designed to be robust to small image transformations. This robustness based on dominant gradient orientations lets us test only a small subset of all possible pixel locations when parsing the image, and to represent a 3D object with a limited set of templates. We show that together with a binary representation that makes evaluation very fast and a branch-and-bound approach to efficiently scan the image, it can detect untextured objects in complex situations and provide their 3D pose in real-time.

CVPR Semantic Scholar

Cite

Text

Hinterstoisser et al. "Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539908

Markdown

[Hinterstoisser et al. "Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/hinterstoisser2010cvpr-dominant/) doi:10.1109/CVPR.2010.5539908

BibTeX

@inproceedings{hinterstoisser2010cvpr-dominant,
  title     = {{Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects}},
  author    = {Hinterstoisser, Stefan and Lepetit, Vincent and Ilic, Slobodan and Fua, Pascal and Navab, Nassir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {2257-2264},
  doi       = {10.1109/CVPR.2010.5539908},
  url       = {https://mlanthology.org/cvpr/2010/hinterstoisser2010cvpr-dominant/}
}