报告题目：Imaging Spectroscopy for Earth Observation – some research perspectives
报 告 人：Dr. Jonathan Cheung-Wai Chan
主 持 人：赵永强 教授
报告简介：Imaging Spectroscopy, or sometimes termed as hyperspectral imaging, has been proven to be more effective in various challenging applications. To this date, there are no hyperspectral remote sensing satellites that carry out regular scanning (with fix revisiting period) of the Earth at global scale. However, this is going to change in the next decades with several national/international initiatives. An exemplary is EnMAP from Germany, with a full stretch from 350-2400nm. While there have been significant developments in analytical methods for hyperspectral data, the scientific communities might not be prepared for the unprecedented newly available global hyperspectral data set. Bear in mind most of the concurrent hyperspectral research are based on simulated data. I will briefly talk about recent development in future Hyperspectral missions and share some of the research direction related to this domain: data acquisition, spatial and spectral enhancement, classification, applications, etc.
Jonathan Cheung-Wai Chan received the Ph.D. Degree from the University of Hong Kong in 1999. After that, he was a research scientist with the Department of Geography, University of Maryland, at College Park, Maryland USA. From 2001 to 2005, he was with the Interuniversity Micro-Electronics Centre (IMEC), Leuven, Belgium. From 2005 to 2011, he was with the Department of Geography at Vrije Universiteit Brussel (VUB), Brussels, Belgium. From 2013 to 2014, he was a Marie Curie fellow at Fondazione Edmund Mach (FEM), Italy. He is currently a Guest Professor at the Department of Electronics and Informatics (ETRO), VUB. His research interests include land cover classification, machine learning algorithms, spectral and spatial enhancement for hyperspectral satellite images.
He has served as a regular Technical Committee member for IEEE International Geoscience and Remote Sensing Symposium. He is the Editor of Remote Sensing, and the Guest Editor of Remote Sensing, for the Special Issues: Spatial Enhancement of Hyperspectral Data and Applications. Deep Learning and Data Mining for Hyperspectral Imagery.