改进的OTSU法在遥感水体信息提取中的应用  

The application of improved OTSU algorithm in water romote sensing information extraction

作　　者：武国瑛 邓正栋[1] 陈一村[1] 

机构地区：[1]解放军理工大学国防工程学院,江苏南京210007

出　　处：《微型机与应用》2017年第20期17-18,22,共3页Microcomputer & Its Applications

基　　金：国家863项目(2012AA062601)

摘　　要：在遥感信息解译中,利用指数法提取水体信息一直存在阈值选取困难的问题。为了进一步解决该问题,将改进的OTSU法用于阈值选取。综合考虑目标像元和背景像元类间方差、类内方差两个指标,并结合粒子群算法,对研究区水体信息进行提取。实验结果表明,提出的算法能更快地确定阈值,有效地提取水体信息。In the interpretation of remote sensing information,the decision of threshold value has always been difficult when the method of index water information extraction is used. In order to further solve the problem,the improved OTSU method for threshold selection is used. Considering the maximum variance between target and background pixels,and the variance whin categories,combined with particle swarm optimization（PSO） algorithm,water information was extracted in the studied area. The experimental results show that the proposed algorithm can quickly determine the threshold value,effectively extract water information.

关 键 词：MNDWI 大津法 粒子群算法 遥感水体信息提取 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]