University of Pavia, Italy
Linear and Non-linear Unmixing of Hyperspectral Data
Unmixing is one of the key operations to be performed on hyperspectral images. It aims at estimating the spectral signatures of the pure spectral constituents in the scene (endmembers) and their corresponding sub-pixel fractional abundances. Although the unmixing problem is inherently nonlinear (due to multiple scattering), nonlinear unmixing of hyperspectral data has been a very challenging problem. This is because nonlinear models require detailed knowledge about the physical interactions between the sunlight scattered by multiple materials. This is the reason why there are multiple methodologies aiming at improving non-linear unmixing using deep learning and information theory. This presentation will feature some of the approaches developed in this area by the team at University of Pavia together with other international researchers.
About the Speaker
Paolo Gamba is Professor at the University of Pavia, Italy, where he leads the Telecommunications and Remote Sensing Laboratory. He served as Editor-in-Chief of the IEEE Geoscience and Remote Sensing Letters from 2009 to 2013, and as Chair of the Data Fusion Committee of the IEEE Geoscience and Remote Sensing Society (GRSS) from October 2005 to May 2009. He has been elected in the GRSS AdCom since 2014, and served as GRSS President from 2019 to 2020.
He has been the organizer and Technical Chair of the biennial GRSS/ISPRS Joint Workshops on “Remote Sensing and Data Fusion over Urban Areas” from 2001 to 2015. He also served as Technical Co-Chair of the 2010, 2015 and 2020 IGARSS conferences, in Honolulu (Hawaii), Milan (Italy), and on-line, respectively.
He has been invited to give keynote lectures and tutorials in several occasions about urban remote sensing, hyperspectral data processing, data fusion, EO data for physical exposure and risk management. He published more than 140 papers in international peer-review journals and presented more than 300 research works in workshops and conferences.