Share Email Print

Journal of Applied Remote Sensing

Thin cloud removal from remote sensing images using multidirectional dual tree complex wavelet transform and transfer least square support vector regression
Author(s): Gensheng Hu; Xiaoyi Li; Dong Liang
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The existence of clouds affects the interpretation and utilization of remote sensing images. A thin cloud removal algorithm for cloud-contaminated remote sensing images is proposed by combining a multidirectional dual tree complex wavelet transform (M-DTCWT) with domain adaptation transfer least square support vector regression (T-LSSVR). First, M-DTCWT is constructed by using the hourglass filter bank in combination with DTCWT, which is used to decompose remote sensing images into multiscale and multidirectional subbands. Then the low-frequency subband coefficients of the cloud-free regions on target images and source domain images are used as samples for a T-LSSVR model, which can be used to predict those of the cloud regions on cloud-contaminated images. Finally, by enhancing the high-frequency coefficients and replacing the low-frequency coefficients, the thin clouds on cloud-contaminated images are removed. Experimental results show that M-DTCWT contributes to keeping the details of the ground objects of cloud-contaminated images, and the T-LSSVR model can effectively learn the contour information from multisource and multitemporal images, therefore, the proposed method achieves a good effect of thin cloud removal.

Paper Details

Date Published: 21 September 2015
PDF: 19 pages
J. Appl. Rem. Sens. 9(1) 095053 doi: 10.1117/1.JRS.9.095053
Published in: Journal of Applied Remote Sensing Volume 9, Issue 1
Show Author Affiliations
Gensheng Hu, Anhui Univ. (China)
Xiaoyi Li, Anhui Univ. (China)
Dong Liang, Anhui Univ. (China)

© SPIE. Terms of Use
Back to Top