ML Anthology

3D Object Recognition from Range Images Using Pyramid Matching

Xinju Li, Igor Guskov
ICCV 2007 pp. 1-6
doi:10.1109/ICCV.2007.4408829 /iccv/2007/li2007iccv-d/

Abstract

Recognition of 3D objects from different viewpoints is a difficult problem. In this paper, we propose a new method to recognize 3D range images by matching local surface descriptors. The input 3D surfaces are first converted into a set of local shape descriptors computed on surface patches defined by detected salient features. We compute the similarities between input 3D images by matching their descriptors with a pyramid kernel function. The similarity matrix of the images is used to train for classification using SVM, and new images can be recognized by comparing with the training set. The approach is evaluated on both synthetic and real 3D data with complex shapes.

ICCV Semantic Scholar

Cite

Text

Li and Guskov. "3D Object Recognition from Range Images Using Pyramid Matching." IEEE/CVF International Conference on Computer Vision, 2007. doi:10.1109/ICCV.2007.4408829

Markdown

[Li and Guskov. "3D Object Recognition from Range Images Using Pyramid Matching." IEEE/CVF International Conference on Computer Vision, 2007.](https://mlanthology.org/iccv/2007/li2007iccv-d/) doi:10.1109/ICCV.2007.4408829

BibTeX

@inproceedings{li2007iccv-d,
  title     = {{3D Object Recognition from Range Images Using Pyramid Matching}},
  author    = {Li, Xinju and Guskov, Igor},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2007},
  pages     = {1-6},
  doi       = {10.1109/ICCV.2007.4408829},
  url       = {https://mlanthology.org/iccv/2007/li2007iccv-d/}
}