DAMS: Dilated Attention with Multi-Stream Learning for Super-Resolution of Hyperspectral Remote Sensing Images

Hyperspectral super-resolution (SR) can effectively enhance the spatial resolution of hyperspectral images, holding significant application value. Nevertheless, existing methods tend to overlook global information and some detailed aspects of hyperspectral images, resulting in limitations in feature...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Geoscience and Remote Sensing Symposium proceedings S. 8995 - 8998
Hauptverfasser: Li, Sheng, Xu, Ruoqing, Su, Yuanchao, Gao, Lianru, Sun, Xu, Ren, Longfei, Zhu, Zhiqing
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 07.07.2024
Schlagworte:
Autoencoder
Convolutional neural networks
Dams
Deep Leaning
Feature extraction
Hyperspectral imaging
Hyperspectral Remote Sensing
Spatial resolution
super-resolution
Superresolution
ISSN:2153-7003
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Hyperspectral super-resolution (SR) can effectively enhance the spatial resolution of hyperspectral images, holding significant application value. Nevertheless, existing methods tend to overlook global information and some detailed aspects of hyperspectral images, resulting in limitations in feature extraction. In addressing this issue, we propose a Dilated Attention With Multi-Stream Learning (DAMS) network to facilitate the fusion of hyperspectral and multispectral images. The network comprises three autoencoders, incorporating dilated residual multipath feature extraction for high-resolution multispectral images and a dense convolutional neural network for low-resolution hyperspectral images. Notably, no prior knowledge of point spread function (PSF) and spectral response function (SRF) is required. Experimental results with DAMS showcase its advantages over other super-resolution fusion methods, demonstrating robust performance across diverse datasets with varying PSF and SRF.
ISSN:2153-7003
DOI:10.1109/IGARSS53475.2024.10642583