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

Aburaed, Nour; Alkhatib, Mohammed Q.; Marshall, Stephen; Zabalza, Jaime; Ahmad, Hussain

doi:10.1109/igarss46834.2022.9883578

Cited by 6 publications

(4 citation statements)

References 18 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study, an encoder-decoder architecture design inspired by 2D-UNET 2 was also utilized to enhance HSI spatially. 22 The proposed network exhibits two symmetrical sides, where the encoder extracts features through a series of 3D convolution and pooling, and the decoder side reconstructs the target enhanced HSI by inverting these operations in 3D as well. Furthermore, there are internal residual connections between encoder units and decoder units, as well as external residual connections across encoders and decoders to improve information exchange between the layers.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Complex-valued neural network for hyperspectral single image super resolution

Aburaed

Alkhatib²,

Zabalza³

et al. 2023

Hyperspectral Imaging and Applications II

Self Cite

View full text Add to dashboard Cite

Remote sensing applications are nowadays widely spread in various industrial fields, such as mineral and water exploration, geo-structural mapping, and natural hazards analysis. These applications require that the performance of image processing tasks, such as segmentation, object detection, and classification, to be of high accuracy. This can be achieved with relative ease if the given image has high spatial resolution as well as high spectral resolution. However, due to sensor limitations, spatial and spectral resolutions have an inherently inverse relationship and cannot be achieved simultaneously. Hyperspectral Images (HSI) have high spectral resolution, but suffer from low spatial resolution, which hinders utilizing them to their full potential. One of the most widely used approaches to enhance spatial resolution is Single Image Super Resolution (SISR) techniques. In the recent years, Deep Convolutional Neural Networks (DCNNs) have been widely used for HSI enhancement, as they have shown superiority over other traditional methods. Nonetheless, researches still aspire to enhance HSI quality further while overcoming common challenges, such as spectral distortions. Research has shown that properties of natural images can be easily captured using complex numbers. However, this has not been thoroughly investigated from the perspective of HSI SISR. In this paper, we propose a variation of a Complex Valued Neural Network (CVNN) architecture for HSI spatial enhancement. The benefits of approaching the problem from a frequency domain perspective will be answered and the proposed network will be compared to its real counterpart and other stateof-the-art approaches. The evaluation and comparison will be recorded qualitatively by visual comparison, and quantitatively using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Spectral Angle Mapper (SAM). The project can be access at: https://github.com/NourO93/3D_CCVNN_Hyperspectral.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This network is dubbed 3D Residual UNET (3D-RUNET). 22 The literature is rich with other similar examples. [23][24][25][26] All the aforementioned DCNNs process HSI in the spatial domain.…”

Section: Related Workmentioning

confidence: 99%

Complex-valued neural network for hyperspectral single image super resolution

Aburaed

Alkhatib²,

Zabalza³

et al. 2023

Hyperspectral Imaging and Applications II

Self Cite

View full text Add to dashboard Cite

show abstract

“…An advanced version of UNet called RUNet was devised by (Hu et al, 2019). However, it was built for the purpose of enhancing images using Single Image Super Resolution rather than segmentation (Aburaed et al, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

“…SE has the potential to boost the performance of DL models that are popularly used for semantic segmentation, such as UNet. Additionally, the advanced version of UNet, called Robust UNet (RUNet), which was devised for Single Image Super Resolution (SISR) (Hu et al, 2019, Aburaed et al, 2022, is repurposed for semantic segmentation. Thus, SE is embedded into UNet, called SE-UNet, and embedded into RUNet, called SE-RUNet, to test its efficiency.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Remote Sensing Imagery Using an Enhanced Encoder-Decoder Architecture

Aburaed,

Al-Saad,

Alkhatib

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Semantic segmentation is one of most the important computer vision tasks for the analysis of aerial imagery in many remote sensing applications, such as resource surveys, disaster detection, and urban planning. This area of research still faces unsolved challenges, especially in cluttered environments and complex sceneries. This study presents a repurposed Robust UNet (RUNet) architecture for semantic segmentation, and embeds the architecture with attention mechanism in order to enhance feature extraction and construction of segmentation maps. The attention mechanism is achieved using Squeeze-and-Excitation (SE) block. The resulting network is referred to as SE-RUNet. SE is also tested with the classical UNet, termed SE-UNet, to verify the efficiency of introducing SE. The proposed approach is trained and tested using “Semantic Segmentation of Aerial Imagery” dataset. The results are evaluated using Accuracy, Precision, Recall, F-score and mean Intersection over Union (mIoU) metrics. Comparative evaluation and experimental results show that using SE to embed attention mechanism into UNet and RUNet significantly improves the overall performance.

show abstract