CONFERENCE PROCEEDINGS
Advanced Search
Home > Journals > J. Appl. Rem. Sens. > Volume 13 > Issue 2 > Article
Open Access
2 January 2019 Restoration of remote sensing images based on nonconvex constrained high-order total variation regularization
Jianguang Zhu, Kai Li, Binbin Hao
Author Affiliations +
Funded by: National Natural Science Foundation of China (NSFC), Qindao Postdoctoral Science Foudation, China, Project of Shandong Province Higher Educational Science and Technology Program, China, Joint Innovative Center for Safe and Effective Mining Technology and Equipment of Coal Resources, Shandong Province of China and SDUST Research Fund
Journal of Applied Remote Sensing, Vol. 13, Issue 2, 022006 (January 2019). https://doi.org/10.1117/1.JRS.13.022006
Abstract
Convex total variation (TV) regularization models have been widely used in remote sensing image restoration problems; however, these models tend to produce staircase effects. We consider a nonconvex second-order TV regularization model with linear constraints for remote sensing image restoration. To solve the nonconvex second-order TV regularization model, we propose an efficient alternating minimization algorithm based on generalized iterated shrinkage algorithm and alternating direction method of multipliers. Experimental results demonstrate the effectiveness of the proposed model, which can reduce staircase effects while preserving edges. In terms of signal-to-noise ratio and structural similarity index measure, the experimental results show that our proposed model and algorithm can give better performance compared with some state-of-the-art methods.
© 2019 Society of Photo-Optical Instrumentation Engineers (SPIE) 1931-3195/2019/$25.00 © 2019 SPIE
Citation Download Citation
Jianguang Zhu, Kai Li, and Binbin Hao "Restoration of remote sensing images based on nonconvex constrained high-order total variation regularization," Journal of Applied Remote Sensing 13(2), 022006 (2 January 2019). https://doi.org/10.1117/1.JRS.13.022006
Received: 29 August 2018; Accepted: 23 October 2018; Published: 2 January 2019
JOURNAL ARTICLE
 17 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Lens.org Logo
CITATIONS
Cited by 22 scholarly publications and 1 patent.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Signal to noise ratio
Remote sensing
Image restoration
Lithium
Visualization
Algorithm development
Fourier transforms
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top