Otsu法、区域生长法及形态学相结合的遥感图像海岸线提取  

Coastline extraction of remote sensing image by combining Otsu,regional growth method with morphology

作　　者：张锦 赖祖龙[1] 孙杰[1] ZHANG Jin;LAI Zulong;SUN Jie(School of Geography and Information Engineering,China University of Geosciences,Wuhan 430074,China)

机构地区：[1]中国地质大学地理与信息工程学院,湖北武汉430074

出　　处：《测绘通报》2020年第10期89-92,共4页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(41671450)。

摘　　要：针对现有的海岸线提取方法精度低,无法满足处理各种传感器卫星图像及对线性多样复杂的海岸线提取的需求,本文提出了一种将Otsu法、区域生长法及形态学相结合的遥感图像海岸线提取方法。并且通过试验证明,该海岸线提取方法可以充分发挥Otsu、区域生长法及形态学方法在提取海岸线方面的各自优势,大大提高了海岸线的提取精度。并利用该方法对两种不同的卫星图像数据进行海岸线提取,验证了该方法在不同条件下均有良好的适用性。Aiming at the low accuracy of the existing coastline extraction methods,which cannot meet the needs of processing various sensor satellite images and the extraction of linear and complex coastlines.This paper proposes a combination of Otsu,regional growth method with morphology method for coastline extraction of remote sensing images.And the experiments show that this coastline extraction method can give full play to the advantages of Otsu,regional growth method and morphology separately in the extraction of coastline,which improves the accuracy of coastline extraction greatly.Two different satellite image data are used to test to verify the good applicability of the method under different conditions.

关 键 词：海岸线提取 OTSU法 区域生长法 效果评价 遥感影像 

分 类 号：P237[天文地球—摄影测量与遥感]