Extracting Land Surface Water from FY/MERSI Image Based On Spectral Matching Of Discrete Particle Swarm Optimization and Linear Feature Enhancement

Land surface water is one of the most important components of surface cover and global water cycle. In this study, the standard water spectrum selected from FY/MERSI image was firstly used to calculate the water probability. Then, based on water probability, the image was roughly classified into four classes: homogeneous ground, junction of land cover, minor tributaries and other. To extract land surface water from small tributaries, the Duda’s Road Operator (DRO) was introduced to enhance the linear features, while Discrete Particle Swarm Optimization (DPSO) was applied to extract land surface water from other three classes. The results show that the method could effectively extract land surface water, especially from small tributaries, and overall accuracy (OA) and Kappa coefficient are improved compared to DPSO algorithm based on spectral matching (SMDPSO).