Contact  |  Chinese  |  CAS
 Home  About RADI People Research News Cooperation Education Resources Data Services
Location:Home > News > News Updates
105th RADI Academic Forum Focuses on Challenges of Data Fusion for Global Urban Remote Sensing
 Date: 2015-10-15  Page Views:

Paolo Gamba, Associate Professor of Telecommunications at the University of Pavia, Italy, was invited to give an academic lecture on the Challenges of Data Fusion for Global Urban Remote Sensing at the 105th Earth Observation and Digital Earth Academic Forum of RADI on September 20, which was presided by Prof. ZHANG Bing, Deputy Director of RADI.

Prof.Paolo Gamba began the lecture with the introduction of the goal of global urban remote sensing, and then he mentioned challenges that may be solved using data fusion. The lecture focused on the general framework of data fusion in urban areas, and the selection and merging of multi-scale features. The lecture put forward that the goal of global urban remote sensing was to understand processes behind urbanization, and to monitor, forecast, control the trends for land use transformation. Thus, the degradation of the environment can be prevented.

Aiming at the challenges of data availability, processing and diversity, he presented the framework of geospatial data fusion and the idea of joint mapping with different resolutions and different spectral bands. In the multi-scale feature fusion, information must be reconciled so that features extracted at one scale match with their generalization at coarse scales and, at the same time, help infer more refined features at finer spatial resolutions. The lecture also mentioned the feature selection approach of active learning, and three feature merging approaches, which two probability-based approaches of Maximum A Posteriori Markov Random Fields and Multi-scale Hidden Markov Models and the approach of Multi-scale Hierarchical (Binary) Decision Tree.

Urban mapping of Xuzhou and Atlanta were taken as real instances to illustrate the fusion analysis using SAR data and multispectral data.

Prof.Paolo Gamba concluded three advantages of fusion. Firstly, multi-scale fusion reduced problems of different spatial resolutions and adapted to different applications. Secondly, feature fusion reduced the diversity of spectral and spatial features of urban areas. Thirdly, multi-sensor data fusion may solve the problem of the limited data availability. Urban remote sensing at the global level opened many new possibilities and applications.

Paolo Gamba is Associate Professor of Telecommunications at the University of Pavia, Italy, where he also leads the Telecommunications and Remote Sensing Laboratory. He has published 115 journal papers, over 30 books or chapters, and more than 260 conference papers. He works for multiple committees in four professional institutes, and he also serves as editor of several academic journals. 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 from 2005 to 2009. He served as Member or Chair of multiple international conferences, and also as Technical Co-Chair of the 2010 and 2015 IEEE Geoscience and Remote Sensing Symposium.

[ Top ]  
Copyright © 2013 by the Institute of Remote Sensing and Digital Earth
No.9 Dengzhuang South Road, Haidian District, Beijing 100094, China Tel:86-10-82178008 Fax:86-10-82178009