讲座人：Prof. Dr. Wolfgang Förstner，ISPRS院士，德国伯恩大学摄影测绘系主任、教授
Abstract: Though the notion 'image segmentation' is not uniquely defined nor are there generally accepted criteria for a good segmentation it is an important mid-level step in image analysis. The talk discusses the basic problems with performing bottom up image segmentation and describes an efficient algorithm for partitioning images or triangulated surfaces. Goal driven segmentation is based on the task, which avoids some of the conceptual drawbacks of generic segmentation. An example for such a semantic segmentation procedure is described and demonstrated.
Wolfgang Förstner is Professor of Photogrammetry and Chair of the Department of Photogrammetry at Bonn University, Germany. He studied Geodesy until 1971 and received his PhD degree from the University of Stuttgart, Germany in 1976. From 1990-2012 he chaired the Department of Photogrammetry at Bonn University. His fields of interest are digital photogrammetry, statistical methods of image analysis, analysis of image sequences, semantic modelling, machine learning and geographic information systems. He published more than 130 scientific papers, supervised approximately 70 Bachelor and Master Theses and more than 30 PhD Theses. He was Vice President of the German Association for Pattern Recognition (DAGM) (1994-2001), President of ISPRS Technical Commission III on Photogrammetric Computer Vision (2004-2008), and Chair of the ISPRS Intercommission Working Group III/VII on Pattern Recognition in Remote Sensing (2008-2012). He served as Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (2008-2012). He became Fellow of the International Society of Photogrammetry and Remote Sensing ISPRS) in 2010. He received the Carl Pulfrich Award in 1987, the ISPRS Cassinis Award in 2000, and the ASPRS Fairchild Award in 2005. He obtained honorary doctorates from the Leibniz University of Hannover, Germany and the Technical University of Graz, Austria in 2011.