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

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 spa...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Vol. 13; no. 3; p. 535
Main Authors: Li, Weisheng, Liang, Xuesong, Dong, Meilin
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.02.2021
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Coding
comprehensive loss
Computer vision
convolutional neural network
data collection
Decomposition
Deep learning
dense coding
feature enhancement
Feature extraction
Image enhancement
Image processing
Image quality
Image reconstruction
Information processing
Mapping
Methods
multiscale perception
Neural coding
Neural networks
Perception
Principal components analysis
Remote sensing
Satellite imagery
Satellites
Sensors
Sharpening
Spatial data
Spectra
Wavelet transforms
ISSN:2072-4292, 2072-4292
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs13030535