报告题目：Multisensor and Multitemporal Data Processing for Earth Observation
报 告 人：贾秀萍
报告时间：2018年12月28日 周五 下午2:00
报告摘要：Information extraction from multisensor and multitemporal data faces challenges in data relevancy analysis and heterogeneous data modeling. Feature selection and feature extraction are critical to enhance the separability between the classes of interest. Another effective means to cope with the problem is to generate new spatial features and incorporate local information. In this talk, feature mining for finding useful features with a given application will be overviewed and discussed. In particularly, the use of Mutual Information and cluster space representation will be analyzed in detail in terms of their capacity in handling a wide range of data types and distributions.
Xiuping Jia (M’93–SM’03) received the B. Eng. degree from the Beijing University of Posts and Telecommunications, Beijing, China, in 1982 and the Ph.D. degree in electrical engineering from The University of New South Wales, Australia, in 1996. Since 1988, she has been with the School of Information Technology and Electrical Engineering, The University of New South Wales, Canberra, Australia, where she is currently an Associate Professor. Her research interests include remote sensing, machine learning and spatial data analysis. Dr Jia has more than 200 publications, including over 100 papers in leading technical journals. She is the co-author of the remote sensing textbook titled Remote Sensing Digital Image Analysis [Springer-Verlag, 3rd (1999) and 4th (2006) eds.]. She is a Subject Editor for the Journal of Soils and Sediments and an Associate Editor of the IEEE Transactions on Geoscience and Remote Sensing since 2005.