Change Detection of Remote Sensing Image Based on Deep Neural Networks

DOI

10.2991/aiie-16.2016.61How to use a DOI?

Keywords

back propagation; deep belief networks; remote sensing image; difference image; change detection

Abstract

How to improve the quality of difference image (DI) for change detection task is an important issue in remote sensing images. This paper propose a new DI creation method based on deep neural networks. Deep belief network (DBN) which is an important model in deep learning is applied, and back propagation (BP) algorithm is improved according to change detection task in our method. The modified BP algorithm tunes DBN to increase the difference on changed areas and decrease the difference on unchanged areas in DI. The change detection result is obtained through clustering analysis of DI. The experiment result shows that the proposed method can avoid the radiometric correction procedures for change detection, enhance the difference in change areas remarkably, and suppress the noise effectively compared with traditional method of DI creation methods. The change detection result is more accurate, and the Kappa values increase 25.93% averagely.

Copyright

© 2016, 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  - Yan Chu
AU  - Guo Cao
AU  - Hassan Hayat
PY  - 2016/11
DA  - 2016/11
TI  - Change Detection of Remote Sensing Image Based on Deep Neural Networks
BT  - Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016)
PB  - Atlantis Press
SP  - 262
EP  - 267
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-16.2016.61
DO  - 10.2991/aiie-16.2016.61
ID  - Chu2016/11
ER  -