苏北淤泥质海岸线提取及精度检验  

Extraction of coastline and accuracy detection in muddy coast zone of Jiangsu Province

作　　者：丁志磊[1] 王志一[2] 徐素宁[1,2] 

机构地区：[1]中国地质大学,北京100083 [2]中国地质环境监测院,北京100081

出　　处：《南水北调与水利科技》2014年第6期140-144,共5页South-to-North Water Transfers and Water Science & Technology

基　　金：国家公益性行业科研专项(201011019)

摘　　要：海岸线变化是研究海岸带演化及全球气候变化的基础之一,而从遥感影像上快速、准确地自动提取不同类型的海岸线一直是个难点,尤其是淤泥质海岸的岸线。采用面向对象的方法,针对苏北淤泥质海岸地区2006年的TM影像,建立包括光谱变换信息和纹理特征信息的规则集对影像进行高精度分类,进而准确地提取海岸线。使用该方法不但具有充分挖掘影像信息、自动化程度高、提取速度快等优点,而且可以从精度和稳定性两个指标对提取结果进行检验,不依赖于参考岸线,检验结果较为客观。The coastline change is one of the research bases of coastal evolution and global climate change.Automatic extraction of different coastline types from the remote sensing images quickly and accurately is always difficult,especially for the shoreline of muddy coast.In this paper,the object-oriented method was adopted to build the rule sets including the spectrum transform information and texture feature information,to classify the images in high definition,and then to extract the coastline accurately based on the TM remote sensing images of muddy coast zone in northern Jiangsu in 2006.The results showed that the method can excavate the image information sufficiently with a high degree of automation and fast extraction,and also test the results from two indexes of accuracy and stability independently of the reference coastline.

关 键 词：淤泥质海岸线 面向对象 信息提取 精度检验 

分 类 号：X87[环境科学与工程—环境工程]