Superpixels and Polygons Using Simple Non-Iterative Clustering

CVPR 2017

doi:10.1109/CVPR.2017.520 /cvpr/2017/achanta2017cvpr-superpixels/

Abstract

We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks.

PDF CVPR Semantic Scholar

Cite

Text

Achanta and Susstrunk. "Superpixels and Polygons Using Simple Non-Iterative Clustering." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.520

Markdown

[Achanta and Susstrunk. "Superpixels and Polygons Using Simple Non-Iterative Clustering." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/achanta2017cvpr-superpixels/) doi:10.1109/CVPR.2017.520

BibTeX

@inproceedings{achanta2017cvpr-superpixels,
  title     = {{Superpixels and Polygons Using Simple Non-Iterative Clustering}},
  author    = {Achanta, Radhakrishna and Susstrunk, Sabine},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.520},
  url       = {https://mlanthology.org/cvpr/2017/achanta2017cvpr-superpixels/}
}