ML Anthology

Image Detection Under Varying Illumination and Pose

Margarita Osadchy, Daniel Keren
ICCV 2001 pp. 668-673
doi:10.1109/ICCV.2001.937690 /iccv/2001/osadchy2001iccv-image/

Abstract

This paper focuses on the detection of objects with Lambertian surface under both varying dlumination and pose We offer to apply a novel detection method that proceeds by modeling the d@erent illuminations from a small number of images in the training set, this automatically voids the illumination effects, allowing fast dlumination invariant detection, without having to create a large training set It is demonstrated that the method ‘~ts in ” nicely with previous work about the modeling oj the set of object appearances under varying illumination In the experiments, an object was correctly detected under image plane rotations in a 45-degrees range, and a wide variety of dl~erent illuminations 1.

PDF ICCV Semantic Scholar

Cite

Text

Osadchy and Keren. "Image Detection Under Varying Illumination and Pose." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937690

Markdown

[Osadchy and Keren. "Image Detection Under Varying Illumination and Pose." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/osadchy2001iccv-image/) doi:10.1109/ICCV.2001.937690

BibTeX

@inproceedings{osadchy2001iccv-image,
  title     = {{Image Detection Under Varying Illumination and Pose}},
  author    = {Osadchy, Margarita and Keren, Daniel},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {668-673},
  doi       = {10.1109/ICCV.2001.937690},
  url       = {https://mlanthology.org/iccv/2001/osadchy2001iccv-image/}
}