A fuzzy-based image analysis method for floodplain mapping of urban environment

摘要

One of the goals of local and provincial governments is, which face flooding disaster, to take advantage of new technologies to improve the production of flood hazard maps. This paper presents a fuzzy relation based algorithm for segmenting remotely sensed images of urban environment. Automated extraction of man-made objects such as buildings and roads using image analysis techniques for floodplain mapping and updating geographic information systems (GIS) databases is very important for disaster management plans and has been an active research topic in photogrammetry and remote sensing community. Segmentation plays an important role in the process of digital image processing towards automated extraction of GIS objects from imagery. The proposed hierarchical clustering technique is based on fuzzy equivalence relation. First, a fuzzy compatibility relation is created in term of the Euclidean distance. In general, the fuzzy compatibility relation is not necessarily a fuzzy equivalence relation. Then, the transitive closure are computed and used as the fuzzy equivalence relation to cluster a given image. Finally, image segmentation is completed by computing α-cut on fuzzy equivalence relation.