ML Anthology

Min-Cut Based Segmentation of Point Clouds

Aleksey Golovinskiy, Thomas A. Funkhouser
ICCVW 2009 pp. 39-46
doi:10.1109/ICCVW.2009.5457721 /iccvw/2009/golovinskiy2009iccvw-mincut/

Abstract

We present a min-cut based method of segmenting objects in point clouds. Given an object location, our method builds a k-nearest neighbors graph, assumes a background prior, adds hard foreground (and optionally background) constraints, and finds the min-cut to compute a foreground-background segmentation. Our method can be run fully automatically, or interactively with a user interface. We test our system on an outdoor urban scan, quantitatively evaluate our algorithm on a test set of about 1000 objects, and compare to several alternative approaches.

PDF ICCVW Semantic Scholar

Cite

Text

Golovinskiy and Funkhouser. "Min-Cut Based Segmentation of Point Clouds." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457721

Markdown

[Golovinskiy and Funkhouser. "Min-Cut Based Segmentation of Point Clouds." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/golovinskiy2009iccvw-mincut/) doi:10.1109/ICCVW.2009.5457721

BibTeX

@inproceedings{golovinskiy2009iccvw-mincut,
  title     = {{Min-Cut Based Segmentation of Point Clouds}},
  author    = {Golovinskiy, Aleksey and Funkhouser, Thomas A.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {39-46},
  doi       = {10.1109/ICCVW.2009.5457721},
  url       = {https://mlanthology.org/iccvw/2009/golovinskiy2009iccvw-mincut/}
}