Going Deeper with Dense Connectedly Convolutional Neural Networks for Multispectral Pansharpening
Autor: | Bai Zongwen, Li Ma, Jonathan Cheung-Wai Chan, Ying Li, Wang Dong |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
010504 meteorology & atmospheric sciences
Computer science Science Multispectral image 0211 other engineering and technologies 02 engineering and technology Overfitting Residual 01 natural sciences Convolutional neural network Convolution 021101 geological & geomatics engineering 0105 earth and related environmental sciences Image fusion business.industry Pattern recognition Panchromatic film Feature (computer vision) images fusion General Earth and Planetary Sciences cnns Artificial intelligence multispectral pansharpening business residual learning dense block |
Zdroj: | Remote Sensing, Vol 11, Iss 22, p 2608 (2019) Remote Sensing Volume 11 Issue 22 Pages: 2608 |
ISSN: | 2072-4292 |
Popis: | In recent years, convolutional neural networks (CNNs) have shown promising performance in the field of multispectral (MS) and panchromatic (PAN) image fusion (MS pansharpening). However, the small-scale data and the gradient vanishing problem have been preventing the existing CNN-based fusion approaches from leveraging deeper networks that potentially have better representation ability to characterize the complex nonlinear mapping relationship between the input (source) and the targeting (fused) images. In this paper, we introduce a very deep network with dense blocks and residual learning to tackle these problems. The proposed network takes advantage of dense connections in dense blocks that have connections for arbitrarily two convolution layers to facilitate gradient flow and implicit deep supervision during training. In addition, reusing feature maps can reduce the number of parameters, which is helpful for reducing overfitting that resulted from small-scale data. Residual learning is explored to reduce the difficulty for the model to generate the MS image with high spatial resolution. The proposed network is evaluated via experiments on three datasets, achieving competitive or superior performance, e.g. the spectral angle mapper (SAM) is decreased over 10% on GaoFen-2, when compared with other state-of-the-art methods. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |