论文部分内容阅读
单波段阈值法和水体指数法具有方法简单、耗时少的优点,成为水体信息提取常用的方法,但对于面积较大、类型多样、影响因素复杂的区域,在全局使用任何一种方法均无法满足精度要求。为精确提取地表覆盖类型复杂、水体类型多样的山区水体信息,本文分别对归一化水体指数(MNDWI)、自动水体提取指数(AWEI)和归一化三波段指数(NDTBI)3种指数的阈值进行分析,以最优阈值分区方案进行分区并构建3个单指数决策树,寻找不同水体类型的最优指数,按照最优原则重构联合指数决策树来提取水体信息,其中,3种单指数提取法的Kappa系数分别为:0.863,0.854,0.862,最优指数联合决策树法的Kappa系数为0.881。结果表明,基于3个指数构成的最优指数联合决策树的提取方法可以达到最高精度,由此说明,采用该法用于水体信息提取可得到最佳效果。
The single-band threshold method and water body index method have the advantages of simple method and less time-consuming, and become a commonly used method for water body information extraction. However, for any area with large area, various types and complicated factors, no method can be used globally Meet the accuracy requirements. In order to accurately extract the information of mountain water bodies with complex surface cover types and various types of water bodies, the thresholds of MNDWI, AWEI and NDTBI The optimal thresholds were partitioned and three single-exponential decision trees were constructed to find the best index of different water body types. According to the optimal principle, the decision tree of joint index was reconstructed to extract water body information. Among them, three kinds of single-index The Kappa coefficients of the extraction method were 0.863, 0.854 and 0.862, respectively. The Kappa coefficient of the optimal index joint decision tree method was 0.881. The results show that the optimal index based on three indices can be combined to extract the best decision tree, which shows that this method can be used to extract the best water information.