基于ETM遥感影像的海岸线提取与验证研究

The Study of Coastline Extraction and Validation Using ETM Remote Sensing Image

利用ETM遥感数据,以黄河三角洲为研究区域,运用边缘检测方法中的Soble算法和修复归一化水体指数法(MNDWI)两种方法对该地区的两种海岸线类型——人工海岸和淤泥质海岸进行海岸线提取研究,并验证评价海岸线提取效果。结果表明,Soble算法提取的海岸线准确度更高,在淤泥质海岸提取中表现更为明显,相对误差由0.025%降低为0.018%。

Using the ETM remote sensing image and two kinds of methods——Soble arithmetic which is one of the edge detection methods and MNDWI,there is going to research the coastline extraction in Yellow River delta which has artificial coastline and muddy coastline,then validate and evaluate the coastline extractions.The result indicates that the Soble arithmetic is more accurate.This is especially obvious in the muddy coastline,and we can find that the relative error has reduced to 0.018% from 0.025%.