A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening
This work addresses the domain-specific problem of enhancing spatial resolution in remote sensing images, which is incremental as it builds on existing CNN architectures with multi-scale and residual learning.
The paper tackled the problem of pan-sharpening in remote sensing imagery by proposing a multi-scale and multi-depth convolutional neural network (MSDCNN), which achieved superior results in both quantitative and visual assessments compared to state-of-the-art methods.
Pan-sharpening is a fundamental and significant task in the field of remote sensing imagery processing, in which high-resolution spatial details from panchromatic images are employed to enhance the spatial resolution of multi-spectral (MS) images. As the transformation from low spatial resolution MS image to high-resolution MS image is complex and highly non-linear, inspired by the powerful representation for non-linear relationships of deep neural networks, we introduce multi-scale feature extraction and residual learning into the basic convolutional neural network (CNN) architecture and propose the multi-scale and multi-depth convolutional neural network (MSDCNN) for the pan-sharpening of remote sensing imagery. Both the quantitative assessment results and the visual assessment confirm that the proposed network yields high-resolution MS images that are superior to the images produced by the compared state-of-the-art methods.