Speaker:  Adam Charles

Title:
Sparsity based techniques for hyperspectral image analysis

Abstract:

Hyperspectral imaging (HSI) has been an invaluable tool in remote sensing applications ranging from agricultural applications to oceanic and atmospheric studies, defense applications and space exploration. HSI takes highly detailed spatial and spectral measurements of terrestrial scenes, which can be used to remotely infer which materials are present and in what quantities. This procedure of extracting material abundances, when the pure material spectra is known, is referred to as spectral unmixing. This talk will cover how sparsity based techniques can be utilized in spectral unmixing to not only uncover the material abundances but to also extract the pure material spectra from example HSI data. Additionally, this talk will cover how recent algorithms in spatial filtering algorithms based on sparse statistics can further improve spectral unmixing. 

Speaker Bio:

Adam Charles received his undergraduate and master's degree in electrical engineering from The Cooper Union for the Advancement of Science and Art. He is currently pursuing his doctorate at Georgia Tech under the guidance of Dr. Christopher Rozell in the area of signal processing, working on algorithmic development of sparsity based techniques and applications thereof.