Thin Cloud-fog Cover Removed from Remote Sensing Imagery Based on Stationary Wavelet Transformation

DOI

10.2991/csss-14.2014.14How to use a DOI?

Keywords

stationary wavelet transform; thin cloud-fog cover; nonlinear gray-scale transformation; remote sensing imagery

Abstract

A new method based on stationary wavelet transformation and nonlinear gray-scale transformation was proposed to weaken the thin cloud-fog cover of remote sensing imagery in this paper, which can not only to weak the cover of thin cloud-fog effectively with enhanced image resolution but also to preserve the true spectral characteristics of the original imagery and get better classification result. The experimental data was a window of SPOT5 with heavy thin cloud-fog cover acquired from Zhuhai, China. There were comparative experiments with other two existing methods: homomorphism filter and a approach based on Laplacian enhancement and histogram shifts. PSNR, average absolute deviation and spectral correlation coefficient were used to evaluate the effect. Furthermore, supervised classification is applied to all the processed images to demonstrate the effectiveness of our integrated method. The results show that the proposed method in this paper performs better. Besides, the spatial details are persisted as more as possible.

Copyright

© 2014, 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  - He Hui
AU  - Chen Hai
PY  - 2014/06
DA  - 2014/06
TI  - Thin Cloud-fog Cover Removed from Remote Sensing Imagery Based on Stationary Wavelet Transformation
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 59
EP  - 63
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.14
DO  - 10.2991/csss-14.2014.14
ID  - Hui2014/06
ER  -