A Probabilistic Fusion Strategy Applied to Road Extraction from Multi-aspect Sar Data

In this paper, we describe an extension of an automatic road extraction procedure developed for single SAR images towards multiaspect SAR images. Extracted information from multi-aspect SAR images is not only redundant and complementary, in some cases even contradictory. Hence, multi-aspect SAR images require a careful selection within the fusion step. In this work, a fusion step based on probability theory is proposed. Before fusion, the uncertainty of each extracted line segment is assessed by means of Bayesian probability theory. The assessment is performed on attribute-level and is based on predefined probability density functions learned from training data. The prior probability varies with global context. In the first part the fusion concept is introduced in a theoretical way. The importance of local context information and the benefit of incorporating sensor geometry are discussed. The second part concentrates on the analysis of the uncertainty assessment of the line segments. Finally, some intermediate results regarding the uncertainty assessment of the line segments using real SAR images are presented. * Corresponding author.