Removing thin cloud on single remote sensing image based on SWF

Abstract

Satellite remote sensing image is often covered with thin cloud. In this paper, support vector value filter is used to decompose thin cloud-contaminated remote sensing image into multi-resolution subband coefficients. Through suppressing the low frequency coefficients, thin cloud is removed effectively and ground object information is preserved sufficiently. Comparing with other thin cloud removal methods, support vector value filter has advantages of good generalization and strongly catching singularity ability. Experiments show that the proposed method can effectively recover the ground object information of remote sensing image covered with thin cloud and obtain ideal cloud-free image.

Cite this paper

@article{Wan2016RemovingTC, title={Removing thin cloud on single remote sensing image based on SWF}, author={Mingzhu Wan and X . H . Li}, journal={2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS)}, year={2016}, pages={397-400} }