基于SFF-W算法的潮滩边界提取研究  

Research on tidal flat boundary extraction based on SFF-W algorithm

作　　者：张斌 韩震[1,2] 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)

机构地区：[1]上海海洋大学海洋科学学院,上海201306 [2]上海河口海洋测绘工程技术研究中心,上海201306

出　　处：《海洋测绘》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)。

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.

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 

分 类 号：P229.4[天文地球—大地测量学与测量工程]