Hyperspectral W-Net: Exploratory Unsupervised Hyperspectral Image Segmentation
Date of Award
5-5-2024
Degree Name
M.S. in Electrical Engineering
Department
Department of Electrical and Computer Engineering
Advisor/Chair
Vijayan Asari
Abstract
Remote sensing techniques are capable of capturing large scenes of data over several sensing domains. Hyperspectral imagery (HSI), often accompanied with lIDAR and orthoimagery sensors during collection, can provide deeper contextual information for a wide range of applications in many different fields. Complex characteristics across spectral bands in addition to high-dimensionality of HSI data present challenges to accurate classification. Generally, dimensionality reduction of the input hyperspectral data cube is performed through multi-phase analytical algorithms as a pre-processing step before further analysis to include machine learning networks. These networks commonly rely on labeled training data for segmentation. Annotating ground truth aerial data can prove to be a cumbersome endeavor that may require specific expertise for accurate assessment. This inspires exploratory research for useful unsupervised feature-learning approaches that can withdraw essential information from HSI data to map scenes without labeled data thereby providing a start-to-finish scene segmentation process.
Keywords
Hyperspectral, U-Net, W-Net, Autoencoder, latent space, latent representation, classification, segmentation, convolutional neural network, CNN, remote sensing
Rights Statement
Copyright 2024, author
Recommended Citation
Steiner, Adam J., "Hyperspectral W-Net: Exploratory Unsupervised Hyperspectral Image Segmentation" (2024). Graduate Theses and Dissertations. 7607.
https://ecommons.udayton.edu/graduate_theses/7607
