Hyperspectral unmixing decomposes the observed mixed spectra into a collection of constituent pure material signatures and associated fractional abundances. Because universal modeling ability neural networks, deep learning (DL) techniques are gaining prominence in solving hyperspectral analysis tasks. The autoencoder (AE) network has been extensively investigated linear blind source unmixing. H...

Hyperspectral Unmixing (HU) has received increasing attention in the past decades due to its ability of unveiling information latent in hyperspectral data. Unfortunately, most existing methods fail to take advantage of the spatial information in data. To overcome this limitation, we propose a Structured Sparse regularized Nonnegative Matrix Factorization (SS-NMF) method from the following two a...

We introduce a method for hyperspectral unmixing that incorporates wavelength dependence in addition to spatial dependence. Spatial dependence is incorporated into the model using class labels on the pixels that is assigned using spectral clustering. Wavelength dependence is introduced by correlating the errors in the unmixing regression models. We propose a non-standard alternating direction m...

In image processing, it is commonly assumed that the model ruling spectral mixture in a given hyperspectral pixel is linear. However, in many real life cases, the different objects and materials determining the observed spectral signatures overlap in the same scene, resulting in nonlinear mixture. This is particularly evident in volcanoes-related imagery, where both airborne plumes of effluents...

Title of thesis: A PERFORMANCE CHARACTERIZATION OF KERNEL-BASED ALGORITHMS FOR ANOMALY DETECTION IN HYPERSPECTRAL IMAGERY Hirsh Goldberg Master of Science, 2007 Thesis directed by: Professor Rama Chellappa Department of Electrical Engineering This thesis provides a performance comparison of linear and nonlinear subspacebased anomaly detection algorithms. Using a dual-window technique to separat...

This paper presents a nonlinear mixing model for hyperspectral image unmixing. The proposed model assumes that the pixel reflectances are post-nonlinear functions of unknown pure spectral components contaminated by an additive white Gaussian noise. The nonlinear effects are approximated by a polynomial leading to a polynomial post-nonlinear mixing model. A Bayesian algorithm is proposed to esti...

My colleagues and I are developing and evaluating a new technique for the extraction of environmental information including water-column inherent optical properties (IOPs) and shallowwater bathymetry and bottom classification from remotely-sensed hyperspectral ocean-color spectra. We address the need for rapid, automated interpretation of hyperspectral imagery. The research issues center on dev...

The distribution and abundance of flowering leafy spurge (Euphorbia esula L.) can be determined with hyperspectral remote sensing, but the availability of hyperspectral sensors is limited. Hence, the Landsat 7 Enhanced Thematic Mapper Plus (ETMþ) and System Pour d’Observation de la Terre (SPOT) 4 imagery were acquired to test the ability of these sensors to detect leafy spurge. The green:red ba...