Road map extraction by multiple detectors in fine spatial resolution SAR data

This paper presents a procedure to combine and improve road map extraction techniques applied to synthetic aperture radar (SAR) data at a fine spatial resolution. The approach is based on two steps. First, we provide a prefiltering technique to reduce erroneous inputs to street detectors. Second, we combine multiple extraction results for a better characterization of the street network. The latter step is based on a feature fusion technique and may be useful in a number of ways: when applying different road extractors to the same data set, or when using different preprocessing algorithms before applying the same road extractor to the same data set, or when applying the same road extractor to more images of the same area. The fusion operators used in this work are hard or fuzzy "AND" and "OR", but also majority voting and log opinion pool are considered and compared. We show through some examples how the proposed procedure improves the results with respect to those obtained by each extractor alone and discuss future developments.