ML Anthology

Improving Superpixel Boundaries Using Information Beyond the Visual Spectrum

Keith Sullivan, Wallace E. Lawson, Donald Sofge
CVPRW 2015 pp. 105-112
doi:10.1109/CVPRW.2015.7301303 /cvprw/2015/sullivan2015cvprw-improving/

Abstract

Superpixels enable a scene to be analyzed on a larger scale, by examining regions that have a high level of similarity. These regions can change depending on how similarity is measured. Color is a simple and effective measure, but it is adversely affected in environments where the boundary between objects and the surrounding environment are difficult to detect due to similar colors and/or shadows. We extend a common superpixel algorithm (SLIC) to include near-infrared intensity information and measured distance information to help oversegmentation in complex environments. We demonstrate the efficacy of our approach on two problems: object segmentation and scene segmentation.

CVPRW Semantic Scholar

Cite

Text

Sullivan et al. "Improving Superpixel Boundaries Using Information Beyond the Visual Spectrum." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301303

Markdown

[Sullivan et al. "Improving Superpixel Boundaries Using Information Beyond the Visual Spectrum." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/sullivan2015cvprw-improving/) doi:10.1109/CVPRW.2015.7301303

BibTeX

@inproceedings{sullivan2015cvprw-improving,
  title     = {{Improving Superpixel Boundaries Using Information Beyond the Visual Spectrum}},
  author    = {Sullivan, Keith and Lawson, Wallace E. and Sofge, Donald},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2015},
  pages     = {105-112},
  doi       = {10.1109/CVPRW.2015.7301303},
  url       = {https://mlanthology.org/cvprw/2015/sullivan2015cvprw-improving/}
}