MDECNN: A Multiscale Perception Dense Encoding Convolutional Neural Network for Multispectral Pan-Sharpening

被引:12
作者
Li, Weisheng [1 ]
Liang, Xuesong [1 ]
Dong, Meilin [1 ]
机构
[1] Chongqing Univ Posts & Telecommun, Coll Comp Sci & Technol, Chongqing 400065, Peoples R China
基金
中国国家自然科学基金;
关键词
convolutional neural network; multiscale perception; feature enhancement; comprehensive loss; dense coding; IMAGE FUSION;
D O I
10.3390/rs13030535
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
With the rapid development of deep neural networks in the field of remote sensing image fusion, the pan-sharpening method based on convolutional neural networks has achieved remarkable effects. However, because remote sensing images contain complex features, existing methods cannot fully extract spatial features while maintaining spectral quality, resulting in insufficient reconstruction capabilities. To produce high-quality pan-sharpened images, a multiscale perception dense coding convolutional neural network (MDECNN) is proposed. The network is based on dual-stream input, designing multiscale blocks to separately extract the rich spatial information contained in panchromatic (PAN) images, designing feature enhancement blocks and dense coding structures to fully learn the feature mapping relationship, and proposing comprehensive loss constraint expectations. Spectral mapping is used to maintain spectral quality and obtain high-quality fused images. Experiments on different satellite datasets show that this method is superior to the existing methods in both subjective and objective evaluations.
引用
收藏
页数:22
相关论文
共 50 条
[1]   Context-driven fusion of high spatial and spectral resolution images based on oversampled multiresolution analysis [J].
Aiazzi, B ;
Alparone, L ;
Baronti, S ;
Garzelli, A .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (10) :2300-2312
[2]  
[Anonymous], 2017, P IEEE C COMP VIS PA, DOI [DOI 10.48550/ARXIV.1705.09914, 10.1109/CVPR.2017.75]
[3]  
Azarang A, 2017, 2017 3RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (IPRIA), P1, DOI 10.1109/PRIA.2017.7983017
[4]   A variational model for P+XS image fusion [J].
Ballester, Coloma ;
Caselles, Vicent ;
Igual, Laura ;
Verdera, Joan ;
Rougé, Bernard .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 69 (01) :43-58
[5]  
Burger HC, 2012, PROC CVPR IEEE, P2392, DOI 10.1109/CVPR.2012.6247952
[6]  
CHAVEZ PS, 1989, PHOTOGRAMM ENG REM S, V55, P339
[7]   A New Adaptive Component-Substitution-Based Satellite Image Fusion by Using Partial Replacement [J].
Choi, Jaewan ;
Yu, Kiyun ;
Kim, Yongil .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (01) :295-309
[8]   DECODE: Deep Confidence Network for Robust Image Classification [J].
Ding, Guiguang ;
Guo, Yuchen ;
Chen, Kai ;
Chu, Chaoqun ;
Han, Jungong ;
Dai, Qionghai .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (08) :3752-3765
[9]   Accelerating the Super-Resolution Convolutional Neural Network [J].
Dong, Chao ;
Loy, Chen Change ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :391-407
[10]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199