A Network Technique Based Feature Extraction Method For Remote Sensing Images

DOI

10.2991/eers-15.2015.19How to use a DOI?

Keywords

remote sensing; complex network analysis; feature extraction; topology characteristic

Abstract

For hyperspectral remote sensing, the dataset usually contains hundreds of spectral images, which generates a rather large amount of data. To reduce the computational complexity of image analysis, feature extraction is often adapted. This paper presents a new approach for unsupervised feature extraction by transforming the hyperspectral dataset into complex networks. The networks’ statistical topological properties are investigated to evaluate remote sensing image features. The objective of the method is to find the images which can form the most representative network formation. This is a completely new criterion for feature selection. Meanwhile, the proposed technique has both an explicit physical meaning. Experimental results demonstrate that the method achieves better results with respect to traditional methods.

Copyright

© 2015, 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  - Wei Xia
PY  - 2015/09
DA  - 2015/09
TI  - A Network Technique Based Feature Extraction Method For Remote Sensing Images
BT  - Proceedings of the 2015 International Conference on Environmental Engineering and Remote Sensing
PB  - Atlantis Press
SP  - 74
EP  - 76
SN  - 2352-538X
UR  - https://doi.org/10.2991/eers-15.2015.19
DO  - 10.2991/eers-15.2015.19
ID  - Xia2015/09
ER  -