SISR of Hyperspectral Remote Sensing Imagery Using 3D Encoder-Decoder RUNet Architecture

Single Image Super Resolution (SISR) refers to the spatial enhancement of an image from a single Low Resolution (LR) observation. This topic is of particular interest to remote sensing community, especially in the area of Hyperspectral Imagery (HSI) due to their high spectral resolution but limited...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Geoscience and Remote Sensing Symposium proceedings s. 1516 - 1519
Hlavní autoři: Aburaed, Nour, Alkhatib, Mohammed Q., Marshall, Stephen, Zabalza, Jaime, Ahmad, Hussain Al
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 17.07.2022
Témata:
3D Convolution
3D-RUNet
Convolution
Decoding
Feature extraction
Hyperspectral
Mirrors
Object detection
Remote Sensing
Sensors
Single Image Super Resolution
Three-dimensional displays
ISSN:2153-7003
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Single Image Super Resolution (SISR) refers to the spatial enhancement of an image from a single Low Resolution (LR) observation. This topic is of particular interest to remote sensing community, especially in the area of Hyperspectral Imagery (HSI) due to their high spectral resolution but limited spatial resolution. Enhancing the spatial resolution of HSI is a pre-requisite that boosts the accuracy of other image processing tasks, such as object detection and classification. This paper deals with SISR of HSI through the 3D expansion of Robust UNet (RUNet). The network is developed, trained, and tested over two datasets, and compared against the original 2D-RUNet and other state-of-the-art approaches. Quantitative and qualitative evaluation show the superiority of 3D-RUNet and its ability to preserve the spectral fidelity of the enhanced HSI.
ISSN:2153-7003
DOI:10.1109/IGARSS46834.2022.9883578