0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

SDRCNN: A Single-Scale Dense Residual Connected Convolutional Neural Network for Pansharpening

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2023 15 citations ? Citation count from OpenAlex, updated daily. May differ slightly from the publisher's own count. Score: 45 ? 0–100 AI score estimating relevance to the microplastics field. Papers below 30 are filtered from public browse.
Yuan Fang, Yuanzhi Cai, Lei Fan

Summary

SDRCNN is a new single-scale lightweight convolutional neural network designed for pansharpening, fusing high-resolution panchromatic and low-resolution multispectral satellite images to produce high-resolution multispectral outputs. The architecture was designed to balance spatial and spectral quality while minimizing computational cost.

Body Systems

Pansharpening is a process of fusing a high spatial resolution panchromatic image and a low spatial resolution multispectral image to create a high-resolution multispectral image. A novel single-branch, single-scale lightweight convolutional neural network, named SDRCNN, is developed in this study. By using a novel dense residual connected structure and convolution block, SDRCNN achieved a better trade-off between accuracy and efficiency. The performance of SDRCNN was tested using four datasets from the WorldView-3, WorldView-2 and QuickBird satellites. The compared methods include eight traditional methods (i.e., GS, GSA, PRACS, BDSD, SFIM, GLP-CBD, CDIF and LRTCFPan) and five lightweight deep learning methods (i.e., PNN, PanNet, BayesianNet, DMDNet and FusionNet). Based on a visual inspection of the pansharpened images created and the associated absolute residual maps, SDRCNN exhibited least spatial detail blurring and spectral distortion, amongst all the methods considered. The values of the quantitative evaluation metrics were closest to their ideal values when SDRCNN was used. The processing time of SDRCNN was also the shortest among all methods tested. Finally, the effectiveness of each component in the SDRCNN was demonstrated in ablation experiments. All of these confirmed the superiority of SDRCNN.

Sign in to start a discussion.

More Papers Like This

Article Tier 2

A new band selection framework for hyperspectral remote sensing image classification

Researchers developed a new framework for reducing data complexity in hyperspectral satellite images by combining dual band selection with a convolutional neural network, achieving over 97% classification accuracy across three benchmark datasets. This approach could improve remote sensing applications like land cover mapping and environmental monitoring.

Article Tier 2

Multiscale Dense Cross-Attention Mechanism with Covariance Pooling for Hyperspectral Image Scene Classification

Researchers developed a multiscale dense cross-attention mechanism with covariance pooling for hyperspectral image scene classification, addressing challenges of high dimensionality and feature redundancy in deep convolutional frameworks to improve classification accuracy.

Article Tier 2

From Local to Global: Efficient Dual Attention Mechanism for Single Image Super-Resolution

Researchers developed a dual attention mechanism for deep learning neural networks to improve single image super-resolution. This type of image enhancement technology could have applications in improving the detection and classification of microplastic particles in environmental images.

Article Tier 2

Applications of Deep Learning-Based Super-Resolution Networks for AMSR2 Arctic Sea Ice Images

Researchers applied deep learning-based super-resolution networks to enhance the spatial resolution of AMSR2 passive microwave satellite images of Arctic sea ice, addressing the coarse native resolution that limits detailed analysis of sea ice extent and dynamics. The approach improved image quality and enabled more precise monitoring of Arctic sea ice changes with implications for understanding climate impacts on polar ecosystems.

Article Tier 2

3D Fourier-based Global Feature Extraction for Hyperspectral Image Classification

Researchers proposed HGFNet, a hybrid deep learning architecture combining 3D convolutional local feature extraction with three complementary Fourier transform strategies for hyperspectral image classification, achieving efficient long-range spectral-spatial modeling and improved discrimination of underrepresented classes via an adaptive focal loss mechanism.

Share this paper