太阳成8722(中国)有限公司-GREEN NO.1

标题：Compressed Sensing-Based Inpainting of Aqua Moderate Resolution Imaging Spectroradiometer Band 6 Using Adaptive Spectrum-Weighted Sparse Bayesian Dictionary Learning作者：Shen, Huanfeng; Li, Xinghua; Zhang, Liangpei; Tao, Dacheng; Zeng, Chao

来源出版物：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 卷：52 期：2 页：894-906 DOI：10.1109/TGRS.2013.2245509 出版年：FEB 2014

摘要：Because of malfunction or noise in 15 out of the 20 detectors, band 6 (1.628-1.652 mu m) of the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor aboard the Aqua satellite contains large areas of dead pixel stripes. Therefore, the corresponding high-level products of MODIS are corrupted by this periodic phenomenon. This paper proposes an improved Bayesian dictionary learning algorithm based on the burgeoning compressed sensing theory to solve this problem. Compared with other state-of-the-art methods, the proposed method can adaptively exploit the spectral relations of band 6 and other spectra. The performance of the proposed method is demonstrated by experiments on both simulated Terra and real Aqua images.

入藏号：WOS:000328941300009

文献类型：Article

语种：English

作者关键词：Aqua Moderate Resolution Imaging Spectroradiometer (MODIS); band 6; Bayesian dictionary learning; compressed sensing (CS); image inpainting

扩展关键词：ORTHOGONAL MATCHING PURSUIT; SIGNAL RECOVERY; IMAGES; MODIS; RECONSTRUCTION; ALGORITHM; PDE

通讯作者地址：Shen, Huanfeng;Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

电子邮件地址：shenhf@whu.edu.cn; lixinghua5540@sina.com.cn; zlp62@public.wh.hb.cn; dacheng.tao@gmail.com; zengchaozc@hotmail.com

地址：

[Shen, Huanfeng; Li, Xinghua] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Zhang, Liangpei; Zeng, Chao] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Peoples R China.

[Tao, Dacheng] Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia.

研究方向：Geochemistry & Geophysics; Engineering; Remote Sensing

ISSN：0196-2892