21 July 2021
16:00 to 17:15 CET
21 July 2021
In the fields of Remote Sensing (RS), Earth Observation (EO), the number of platforms for producing remotely sensed data has sharply increased, with an ever-growing number of satellites in orbit or planned for launch, airborne missions, and new platforms for proximate sensing such as unmanned aerial vehicles (UAVs) producing very fine spatial resolution data. Fortunately, the increase in the number and heterogeneity of data sources has been paralleled by increases in computing power, by efforts to make data more open, available and interoperable, and by advances in machine learning methods for RS data analysis. Recent developments in signal processing and machine learning have led to impressive progress in the analysis of RS data, both in theory and in practice, allowing researchers to investigate complex, heterogeneous data processing scenarios with efficient algorithms and sound theoretical bases. However, in spite of many successes also observed in remote sensing, it is fair to say that state-of-the-art machine learning approaches could not be utilized to their full potential for high-dimensional, heterogeneous, and complex RS data. The main reason might be the fundamental divergence between the rapidly growing quantity and complexity of the RS data that we collect and the need for numerous high-quality training sets, which are often not available for the problems of interest.
In this fireside chat, we (Pedram Ghamisi (IARAI and HZDR), Naoto Yokoya (the University of Tokyo and RIKEN), Ronny Hänsch (DLR), and Fabio Pacifici (Maxar)) will give a short introduction to RS and some of its challenges where a tight synergy between RS and AI can offer solutions. We discuss inherent differences between (close-range) CV (e.g. images obtained by hand-held cameras) and EO tasks and why the success of many methods successfully applied in CV applications cannot be directly transferred to remote sensing data.In addition, we discuss how a strong synergy between industry, academia, and government agencies can better serve the broader remote sensing and AI community.
Pedram Ghamisi graduated with a Ph.D. in electrical and computer engineering at the University of Iceland in 2015. He works as (1) the head of the machine learning group at Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Germany and (2) visiting professor and group leader of AI4RS at the Institute of Advanced Research in Artificial Intelligence (IARAI), Austria. He is a co-founder of VasoGnosis Inc. with two branches in San Jose and Milwaukee, the USA.
He was the co-chair of IEEE Image Analysis and Data Fusion Committee (IEEE IADF) (2019-2021). Dr. Ghamisi was a recipient of the IEEE Mikio Takagi Prize for winning the Student Paper Competition at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) in 2013, the first prize of the data fusion contest organized by the IEEE IADF in 2017, the Best Reviewer Prize of IEEE Geoscience and Remote Sensing Letters in 2017, and the IEEE Geoscience and Remote Sensing Society 2020 Highest-Impact Paper Award. His research interests include interdisciplinary research on deep learning and signal processing with a sharp focus on remote sensing data. He is Associate Editor for IEEE GRSL and IEEE JSTARS. For detailed info, please see http://pedram-ghamisi.com/.
Naoto Yokoya (M.Eng. 2010, Ph.D. 2013 The University of Tokyo) is a Lecturer at the University of Tokyo and a Unit Leader at the RIKEN Center for Advanced Intelligence Project, Tokyo, Japan, where he leads the Geoinformatics Unit. His research interests include image processing, data fusion, and machine learning for understanding remote sensing images, with applications to disaster management and environmental monitoring.
He is an associate editor of IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. He was the Chair (2019-2021) and Co-Chair (2017-2019) of IEEE GRSS Image Analysis and Data Fusion Technical Committee (IADF TC).
Ronny Hänsch received his graduate degree in computer science and his Ph.D. degree in engineering from the Technische Universität Berlin, Germany, in 2007 and 2014, respectively.
He is currently with the SAR Technology department of the German Aerospace Center (DLR) in Oberpfaffenhofen, Germany, and continues to lecture at the Technical University of Berlin. From 2016-17, he was part of the Flying Faculty program at Turkish-German University, Istanbul, Turkey, where he worked as a lecturer in Computer Science. In 2017, he was the recipient of a JSPS PostDoc fellowship and a guest researcher at the Tokyo Institute of Technology, Japan. His current research interests focus on ensemble methods and deep learning for analysis of remote sensing images with a focus on synthetic aperture radar.
He was co-chair (2017-2021) and is current chair of the IEEE GRSS Image Analysis and Data Fusion (IADF) Technical Committee and co-chair of the ISPRS Working Group II/1 (Image Orientation). He serves as reviewer for major international conferences (e.g. CVPR, ICCV), as Guest Editor for IEEE JSTARS, as Associate Editor for IEEE GRSL, and as Editor in Chief for the GRSS e-Newsletter.
Fabio Pacifici, Distinguished Scientist, Maxar Technologies. He has 15 years of experience in developing innovative geospatial products, with the vision of bringing together the advancements in the satellite industry with the computer vision and artificial intelligence research communities.
He is interested in all aspects related to remote sensing, with particular emphasis on GeoAI associated to the analysis of multi-temporal images, data fusion, hyperspectral and synthetic aperture radar data analysis. He is experienced in atmospheric compensation of satellite images, radiative transfer and aerosol modeling, and calibration and validation of spaceborne optical sensors. Fabio Pacifici has authored (or co-authored) more than 100 publications including patents, book chapters, journal papers, and peer-reviewed conference proceedings.
Fabio Pacifici's volunteer experience with IEEE includes serving as VP of Technical Activities for the Geoscience and Remote Sensing Society (GRSS) and as Associate Editor for the Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS). He was the IEEE GRSS Director of Corporate Relations (2018-2020), the Editor-in-Chief of the IEEE GRSS eNewsletter (2014-2017), and Chair of the IEEE GRSS Data Fusion Technical Committee (2011-2013). He is the recipient of various international awards including the Early Career Award from IEEE GRSS in 2015, the WHISPERS Best Paper Award in 2014, the Best Reviewer Award from IEEE GRSS JSTARS in 2011, and the Best Student Paper Award at the 2009 IEEE GRSS Joint Urban Remote Sensing Event, in Shanghai, China. He also won the 2007, 2008 and 2009–2010 IEEE GRSS Data Fusion Contest.