Automatic Extraction of Saltpans on an Amendatory Saltpan Index and Local Spatial Parallel Similarity in Landsat-8 Imagery

Saltpans extraction is vital for coastal resource utilization and production management. However, it challenging to extract saltpans, even by visual inspection, because of their spatial spectral similarities with aquaculture ponds. are composed crystallization evaporation From the whole images, existing saltpans algorithms could only part i.e., Meanwhile, ponds not be efficiently extracted analysis, causing degeneration extraction. In addition, manual intervention was required. Thus, essential study automatic algorithm image. As abovementioned problems, this paper proposed a novel method an amendatory saltpan index (ASI) local parallel similarity (ASI-LSPS) extracting saltpans. To highlight in water, Hessian matrix has been exploited. Then, new reduce negative influence turbid water dams. Finally, criterion The Landsat-8 OLI images Tianjin Dongying, China, have used experiments. Experiments shown that ASI can reach at least 70% intersection over union (IOU) 78% Kappa Moreover, experiments also demonstrate ASI-LSPS 82% IOU 89% on extraction, 13% 17% better than comparing Kappa, respectively. Furthermore, advantage automaticity imagery. provide help management scientific resources.