一种改进光谱角匹配的水体信息提取方法

发布时间：2018-02-08 21:49

本文关键词： 水体提取归一化差分水体指数支持向量机改进光谱角匹配　出处：《测绘通报》2017年10期 　论文类型：期刊论文

【摘要】：快速、准确地从卫星遥感影像上获取水体信息已成为水资源调查及监测、湿地保护、洪涝灾害评估等领域的重要技术手段。本文以GF-4卫星的PMS传感器影像为数据源,提出了一种改进光谱角匹配(MSAM)的水体信息提取方法,以内蒙古中东部和长江中下游两个试验区为研究对象,对比分析了MSAM与单波段阈值法、NDWI阈值法、支持向量机和光谱角匹配等传统方法的水体信息提取结果,并进行了精度评价。试验结果表明,本文提出的MSAM方法不仅能准确地提取水体信息,而且能很好地区分水体与云阴影,对细小水体的提取也具有很好的效果。在内蒙古中部和长江中下游两个试验区的水体提取精度分别达到99.86%和98.37%,在5种水体提取方法中的精度最高,可以有效地提取水体信息。
[Abstract]:Obtaining water body information from satellite remote sensing image quickly and accurately has become an important technical means in the fields of water resources investigation and monitoring, wetland protection, flood disaster assessment, etc. In this paper, the PMS sensor image of GF-4 satellite is used as the data source. In this paper, an improved spectral angle matching method for extracting water information is proposed. Two experimental areas in the middle and eastern part of Inner Mongolia and the middle and lower reaches of the Yangtze River are taken as the research objects. The MSAM and the single-band threshold method are compared and analyzed. The results of traditional methods such as support vector machine (SVM) and spectral angle matching are used to extract water information, and the accuracy is evaluated. The experimental results show that the proposed MSAM method can not only extract water information accurately. And it can well distinguish between water and cloud shadows, The extraction accuracy of the two experimental areas in the middle part of Inner Mongolia and the middle and lower reaches of the Yangtze River is 99.86% and 98.37, respectively, and the precision of the five methods is the highest, which can effectively extract the water information.
【作者单位】：中国科学院遥感与数字地球研究所;中国科学院大学;
【基金】：高分辨率对地观测系统重大专项(03-Y20A04-9001-15/16;11-Y20A05-9001-15/16)
【分类号】：P237;P332

【相似文献】