Title :
How to fuse optical and radar imagery?
Author :
Palubinskas, Gintautas
Author_Institution :
German Aerosp. Center DLR, Remote Sensing Technol. Inst., Wessling, Germany
Abstract :
Information extraction from multi-sensor remote sensing imagery is an important and challenging task for many applications such as urban area mapping and change detection. There exist a lot of publications on this topic, but quite often they follow the same strategy: put all data into one stack and search for the best classifier for one particular example. Transfer of the results to other examples quite often fails. Especially during optical and radar data fusion different aspects and factors such as different acquisition geometries, incommensurable nature of features and many other parameters should be accounted for. In this paper we shall present a general workflow for optical and radar/SAR data fusion and discuss the main problems occurring when applying it for classification applications.
Keywords :
feature extraction; geophysical image processing; image classification; image fusion; remote sensing by radar; synthetic aperture radar; terrain mapping; SAR; acquisition geometry; change detection; classification application; data fusion; information extraction; multisensor remote sensing imagery; optical imagery; radar imagery; urban area mapping; Adaptive optics; Laser radar; Optical imaging; Optical sensors; Synthetic aperture radar; Multi-sensor fusion; change detection; classification; co-registration; orthorectification;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International
Conference_Location :
Munich
Print_ISBN :
978-1-4673-1160-1
Electronic_ISBN :
2153-6996
DOI :
10.1109/IGARSS.2012.6351072