Microwave Radiometer Data Superresolution Using Image Degradation and Residual Network

被引：19

作者：

Hu, Ting ^{[1
]}

Zhang, Feng ^{[1
]}

Li, Wei ^{[1
]}

Hu, Weidong ^{[2
]}

Tao, Ran ^{[1
]}

机构：

[1] Beijing Inst Technol, Beijing Key Lab Fract Signals & Syst, Sch Informat & Elect, Beijing 100081, Peoples R China

[2] Beijing Inst Technol, Sch Informat & Elect, Beijing Key Lab Millimeter Wave & Terahertz Techn, Beijing 100081, Peoples R China

来源：

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2019年 / 57卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Microwave radiometry; Degradation; Hybrid fiber coaxial cables; Spatial resolution; Microwave imaging; Microwave theory and techniques; Image degradation; radiometer data; residual network; superresolution (SR); SPATIAL-RESOLUTION ENHANCEMENT;

D O I：

10.1109/TGRS.2019.2923886

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Microwave radiometers are the key sensors to globally monitor environmental parameters; however, it suffers from its low and nonuniform spatial resolution. In this paper, a superresolution (SR) technique based on image degradation and residual network is proposed to enhance the spatial resolution of microwave radiometer data. Specifically, an improved degradation model is proposed to construct pairs of high-resolution (HR) and low-resolution (LR) data for training and testing. In addition, a new residual network connected by the SR main and gradient auxiliary branches in parallel is designed to achieve SR reconstructions, where eight-channel gradient maps extracted from LR data are input into the auxiliary branch to help to reconstruct. SR results are eventually generated by the trained SR network. Experiments executed on both simulated and actual data demonstrate the soundness and the superiority of the proposed SR technique.

引用

页码：8954 / 8967

页数：14

共 28 条

[11] OCEAN SURFACE WIND-SPEED MEASUREMENTS OF THE SPECIAL SENSOR MICROWAVE IMAGER (SSM/I) [J].

GOODBERLET, MA ;

SWIFT, CT ;

WILKERSON, JC .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (05) :823-828

[12]

Hanson P. C., 1998, Rank-Deficient Discrete Ill-Posed Problems

[13] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[14] A Deconvolution Technology of Microwave Radiometer Data Using Convolutional Neural Networks [J].

Hu, Weidong ;

Zhang, Wenlong ;

Chen, Shi ;

Lv, Xin ;

An, Dawei ;

Ligthart, Leo .

REMOTE SENSING, 2018, 10 (02)

[15] Conjugate Gradient Method in Hilbert and Banach Spaces to Enhance the Spatial Resolution of Radiometer Data [J].

Lenti, Flavia ;

Nunziata, Ferdinando ;

Estatico, Claudio ;

Migliaccio, Maurizio .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (01) :397-406

[16] Two-Dimensional TSVD to Enhance the Spatial Resolution of Radiometer Data [J].

Lenti, Flavia ;

Nunziata, Ferdinando ;

Migliaccio, Maurizio ;

Rodriguez, Giuseppe .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (05) :2450-2458

[17] On the Spatial Resolution Enhancement of Microwave Radiometer Data in Banach Spaces [J].

Lenti, Flavia ;

Nunziata, Ferdinando ;

Estatico, Claudio ;

Migliaccio, Maurizio .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (03) :1834-1842

[18] Learning deconvolutional deep neural network for high resolution medical image reconstruction [J].

Liu, Hui ;

Xu, Jun ;

Wu, Yan ;

Guo, Qiang ;

Ibragimov, Bulat ;

Xing, Lei .

INFORMATION SCIENCES, 2018, 468 :142-154

[19]

Long D. G., 2013, Frontiers Remote Sens. Inf. Process., V4, P255

[20] Using Deep Neural Networks for Inverse Problems in Imaging Beyond analytical methods [J].

Lucas, Alice ;

Iliadis, Michael ;

Molina, Rafael ;

Katsaggelos, Aggelos K. .

IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (01) :20-36

← 1 2 3 →