Abstract
Geoinformation derived from Earth observation satellite data is indispensable for many scientific, governmental and planning tasks. Cartography, geophysics, resource management, civil security, disaster relief, as well as for planning and decision support are just a few examples. Therefore, the European Commission operates the Copernicus program that guarantees the future free access to remote sensing data delivered by Sentinels, a new fleet of ESA satellites. Germany also operates Earth observation satellites with so far the highest technical quality, including the current TerraSAR-X and TanDEM-X and the future EnMAP, DESIS and Tandem-L missions.
Can modern signal processing and machine learning algorithms improve information retrieval from remote sensing data, and hence take advantage of this precious satellite infrastructure more efficiently? In this seminar, several modern signal processing and machine learning concepts, including compressive sensing, nonlocal filters, robust estimators and deep learning, are proposed for solving diverse scientific problems in remote sensing including radar and optical (multispectral and hyperspectral) technologies. A particular focus will be put on data fusion, which has shown an ever-growing relationship with remote sensing. The presented concepts are not only supposed to substantially improve information retrieval from existing sensors but also contribute to the preparation and the design of the next-generation Earth observation satellite missions. In addition, a showcasing geoscience application – global urban mapping – will be highlighted.
Biography
Xiaoxiang Zhu is the professor for Signal Processing in Earth Observation (SiPEO, www.sipeo.bgu.tum.de) at Technical University of Munich (TUM) and the German Aerospace Center (DLR), Germany. She is also the founding head of the department of EO Data Science in DLR’s Earth Observation Center (officially starts from April 2018).
Zhu received the Master (M.Sc.) degree, her doctor of engineering (Dr.-Ing.) degree and her “Habilitation” in the field of signal processing from TUM in 2008, 2011 and 2013, respectively. She was a guest scientist or visiting professor at the Italian National Research Council (CNR-IREA), Naples, Italy, Fudan University, Shanghai, China, the University of Tokyo, Tokyo, Japan and University of California, Los Angeles, United States in 2009, 2014, 2015 and 2016, respectively. Her main research interests are remote sensing and Earth observation, signal processing, machine learning and data science, with a special application focus on global urban mapping.
Xiaoxiang Zhu is an associate editor of IEEE TGRS and SPIE JARS and the author of 200 scientific publications, among them about 150 full-paper-peer-reviewed and 10 paper awards. She has received several important scientific awards, for example the Heinz Maier-Leibnitz-Preis of the German Research Foundation (DFG) in 2015, Innovators under 35 of Technology Review Germany in 2015, IEEE GRSS Early Career Award in 2016, ERC Starting Grant in 2017 and Helmholtz Excellence Professorship in 2018 etc.
>> Personal Page
