摘要
水边线附近的高浊度悬沙及浅滩表层的残余水体是影响水边线信息提取的重要因素。在分析长江口区不同浓度水体与背景地物光谱特征的基础上,采用决策树分析方法进行水边线提取,在分类器的节点用水深信息作为约束条件,消除了水边线附近热流对热红外波段水边线提取的影响。同时,利用参考DTM及潮位信息实施了水边线的提取,此方法有效消除了表层残余水体对水边线提取的影响。最后运用统计学中自身一致性校验及平均偏移指数来评价提取结果。结果表明,两种方法的总体提取效果较好,精度令人满意。
The locations of waterline in remotely sensed images are mainly affected by high concentration suspended sediments and surface remnant water. A decision tree model considering the water depth was applied in this paper to detecting waterline. Furthermore, waterline was also traced from the reference digital terrain model （DTM） and the associated tidal elevation. The two approaches were both used to delineate the waterline in the Yangtze Estuary, and the experimental results indicate that they are fairly effective in waterline extraction.
出处
《国土资源遥感》
CSCD
2007年第2期56-59,共4页
Remote Sensing for Land & Resources
基金
国家973项目"长江口及其邻近海域细颗粒泥沙沉积动力过程"(973-2002CB412403)
教育部"高等学校优秀青年教师教学科研奖励计划"联合资助
关键词
水边线
长江口
决策树模型
DTM
Waterline
The Yangtze Estuary
Decision tree model
DTM
