ML Anthology

Local PotentialWell Space Embedding

Yani Ioannou, Limin Shang, Robin Harrap, Michael A. Greenspan
ICCVW 2009 pp. 1726-1732
doi:10.1109/ICCVW.2009.5457491 /iccvw/2009/ioannou2009iccvw-local/

Abstract

Potential Well Space Embedding (PWSE) has been shown to be an effective global method to recognize segmented objects in range data. Here Local PWSE is proposed as an extension of PWSE. LPWSE features are generated by iterating ICP to the local minima of a multiscale registration model at each point. The locations of the local minima are then used to generate feature vectors, which can be matched against a preprocessed database of such features to determine correspondences between images and models. The method has been implemented and tested on real data, and has been found to be effective at recognizing sparse segmented (self-)occluded range images. A classification accuracy of 92% is achieved with 3750 points, dropping to 78% at 500 points, on 50 randomly sub-sampled sparse views of 5 objects.

ICCVW Semantic Scholar

Cite

Text

Ioannou et al. "Local PotentialWell Space Embedding." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457491

Markdown

[Ioannou et al. "Local PotentialWell Space Embedding." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/ioannou2009iccvw-local/) doi:10.1109/ICCVW.2009.5457491

BibTeX

@inproceedings{ioannou2009iccvw-local,
  title     = {{Local PotentialWell Space Embedding}},
  author    = {Ioannou, Yani and Shang, Limin and Harrap, Robin and Greenspan, Michael A.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {1726-1732},
  doi       = {10.1109/ICCVW.2009.5457491},
  url       = {https://mlanthology.org/iccvw/2009/ioannou2009iccvw-local/}
}