Segmentation of Remote Sensing Images Using Fusion-MRF Model
We propose a multilayer fusion model for adaptive segmentation and change detection of optical remote sensing image series, where trajectory analysis or direct comparison is not applicable. Our method applies unsupervised or partly supervised clustering on a fused-image series by using cross-layer similarity measure, followed by multilayer Markov random field segmentation. The resulted label map is applied for the automatic training of single layers. After the segmentation of each single layer separately, changes are detected between single label maps. The significant benefit of the proposed method has been numerically validated on remotely sensed image series with ground-truth data.
Prof. Tamás Szirányi received his Ph.D. and D.Sci. degrees in 1991 and 2001, by the Hungarian Academy of Sciences, Budapest. He was appointed to a Full Professor position in 2001 at University of Pannonia, Veszprém, Hungary and, in 2004, at the Péter Pázmány Catholic University, Budapest, Hungary. In 2014 he was appointed as full professor at Budapest University of Technology and Economics. He leads the Distributed Events Analysis Research Laboratory at the Institute for Computer Science and Control of the Hungarian Academy of Sciences. His research activities include machine perception, pattern recognition, texture and motion segmentation, Markov Random Fields and stochastic optimization, remote sensing, surveillance systems for panoramic and multiple camera systems, intelligent networked sensor systems , image quality, digital film restoration, image rendering and coding. Dr. Szirányi was the founder and past president (1997 to 2002) of the Hungarian Image Processing and Pattern Recognition Society (Hungarian section of IAPR). He was an Associate Editor of IEEE Tr. on Image Processing (2003-2009), and currently an A.E. of Elsevier’s Digital Signal Processing. He was honoured with the Master Professor award in 2001, and the Széchenyi Professorship in 1999. He is a Fellow of IAPR and of the Hungarian Academy of Engineering. He has more than 250 publications including 50 in major scientific journals.