摘要
以上海市南汇潮滩为研究区域,利用2017年高分一号(GF-1)卫星的遥感影像数据为数据源,提出了基于超像素的快速聚类算法(SFFCM)与水边线法相结合的SFF-W模型,用于对潮滩边界进行提取分析。通过目视解译提取的潮滩区域与水边线法、SFFCM模型和SFF-W模型所提取的结果进行对比分析。结果表明,SFF-W模型在提取潮滩边界的方法中效果最优。SFF-W模型的总体精度和制图精度比水边线法分别提高了2.39%和10.79%,该模型能在半监督情况下准确地提取潮滩边界。并利用2019年该区域的遥感影像数据进行对比分析,本研究对于提取潮滩边界具有一定的借鉴和指导意义。
Taking Nanhui tidal flat in Shanghai as the research area and using the remote sensing image data of gaofen-1(GF-1)satellite in 2017 as the data source,this paper proposes an SFF-W model based on the combination of super-pixel fast clustering algorithm(SFFCM)and water edge method to extract and analyze the tidal flat boundary.The tidal flat area extracted by visual interpretation is compared with the results extracted by water edge method,SFFCM model and SFF-W model.The results show that SFF-W model is the best method to extract tidal flat boundary.The overall accuracy and mapping accuracy of SFF-W model are 2.39%and 10.79%higher than that of water edge method,respectively.The model can accurately extract tidal flat boundary under semi supervision.The remote sensing image data of this area in 2019 are used for comparative analysis.This study has certain reference and guiding significance for extracting tidal flat boundary.
作者
张斌
韩震
ZHANG Bin;HAN Zhen(College of Marine Science,Shanghai Ocean University,Shanghai 201306,China;Shanghai Engineering Research Center of Estuarine and Oceanographic Mapping,Shanghai 201306,China)
出处
《海洋测绘》
CSCD
北大核心
2022年第1期55-59,共5页
Hydrographic Surveying and Charting
基金
上海市科委科研计划(18DZ2253900)。
关键词
遥感影像
潮滩边界提取模型
水边线法
快速聚类算法
南汇潮滩
remote sensing images
tidal flat boundary extraction model
waterline method
fast clustering algorithm
Nanhui tidal flat
