ML Anthology

Multi-Scale and Snakes for Automatic Road Extraction

Helmut Mayer, Ivan Laptev, Albert Baumgartner
ECCV 1998 pp. 720-733
doi:10.1007/BFB0055700 /eccv/1998/mayer1998eccv-multi/

Abstract

This paper proposes an approach for automatic road extraction in aerial imagery which exploits the scale-space behavior of roads in combination with geometric constrained snake-based edge extraction. The approach not only has few parameters to be adjusted, but for the first time allows for a bridging of shadows and partially occluded areas using the heavily disturbed evidence in the image. The road network is constructed after extracting crossings of various shape and topology. Reasonable results are obtained which are evaluated based on ground truth.

PDF ECCV Semantic Scholar

Cite

Text

Mayer et al. "Multi-Scale and Snakes for Automatic Road Extraction." European Conference on Computer Vision, 1998. doi:10.1007/BFB0055700

Markdown

[Mayer et al. "Multi-Scale and Snakes for Automatic Road Extraction." European Conference on Computer Vision, 1998.](https://mlanthology.org/eccv/1998/mayer1998eccv-multi/) doi:10.1007/BFB0055700

BibTeX

@inproceedings{mayer1998eccv-multi,
  title     = {{Multi-Scale and Snakes for Automatic Road Extraction}},
  author    = {Mayer, Helmut and Laptev, Ivan and Baumgartner, Albert},
  booktitle = {European Conference on Computer Vision},
  year      = {1998},
  pages     = {720-733},
  doi       = {10.1007/BFB0055700},
  url       = {https://mlanthology.org/eccv/1998/mayer1998eccv-multi/}
}