Road Extraction Using an Improved Snake Model and CART

DOI

10.2991/ceis-16.2016.75How to use a DOI?

Keywords

road extraction; GVF-Snake; classification; CART

Abstract

Road Extraction from remote sensing images has been an important research topic. It is difficult to extract the road quickly and reliably due to the complexity of the road features. In this paper, an improved GVF-Snake algorithm as a segmentation method automatically labels training samples to reduce the complexity of the manual labeling data, and a Classification and Regression Tree method is used to extract the roads from remote sensing images by classification. The experiments indicate that the proposed method can efficiently and automatically extract the roads from remote sensing images.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yi-Nan Lu
AU  - Zhe Zhang
AU  - Xiao-Ni Liu
AU  - Yun-Fan Du
PY  - 2016/11
DA  - 2016/11
TI  - Road Extraction Using an Improved Snake Model and CART
BT  - Proceedings of the 2016 International Conference on Computer Engineering and Information Systems
PB  - Atlantis Press
SP  - 372
EP  - 375
SN  - 2352-538X
UR  - https://doi.org/10.2991/ceis-16.2016.75
DO  - 10.2991/ceis-16.2016.75
ID  - Lu2016/11
ER  -