面向气溶胶反演的高分四号影像云检测  

GF-4 Cloud Detection Algorithm for Aerosol Retrieval

作　　者：赵少帅 杨磊库[1] 陈兴峰 王涵[1] 卢晓峰[1] ZHAO Shaoshuai;YANG Leiku;CHEN Xingfeng;WANG Han;LU Xiaofeng(School of Surveying and Land Information Engineering,Henan Polytechnic University,Jiaozuo,Henan 454003,China;State Environmental Protection Key Laboratory of Satellite Remote Sensing Applications,Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences,Beijing 100101,China)

机构地区：[1]河南理工大学测绘与国土信息工程学院,河南焦作454003 [2]中国科学院遥感与数字地球研究所国家环境保护卫星遥感重点实验室,北京100101

出　　处：《遥感信息》2019年第5期81-87,共7页Remote Sensing Information

基　　金：河南省科技攻关项目（162102310089）;河南理工大学博士基金（B2014-018、B2016-14）;国家自然科学基金（41401403、41601392）;中国科学院通用光学定标与表征技术重点实验室开放课题（2017JJ-01）

摘　　要：针对在利用卫星影像进行地表信息提取、气溶胶光学厚度反演等工作中云检测不够准确的问题,提出了利用云的空间变化特性、光谱反射率特征阈值和HOT薄云检测联合的方法。通过对大量区域进行直方图统计分析,确定了适合高分四号卫星数据的阈值,进而建立了针对气溶胶反演干扰较大的碎云、云边缘、薄云的检测方法。利用该方法对多幅影像进行云检测,结果表明,该方法能够很好地检测出云像元,特别是对于碎云、云边缘和薄云有很好的识别效果,有效提升了气溶胶产品的可信程度。There is a problem of inaccurate cloud detection when using satellite imagery for surface information extraction and aerosol optical thickness retrieval.This paper jointed the cloud spatial variability,spectral reflectivity of clouds and the HOT thin cloud detection method,focused on the identification of broken clouds,cloud edges and thin clouds which have great interference with aerosol retrieval,used the histogram statistical analysis of many areas and determined the suitable threshold for GF-4,and then realized cloud detection of GF-4.Using this method,it performed cloud detection on multiple images.The results show that this method can detect cloud pixels very well especially for cloud edges and broken clouds.The method can enhance the credibility of aerosol products effectively.

关 键 词：云检测 高空间分辨率 静止轨道卫星 空间变化特征 高分四号 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]