基于RDA-Net模型的遥感影像云与云阴影检测方法  

Remote Sensing Image Cloud and Cloud Shadow Detection Method Based on RDA-Net Model

作　　者：张晨 张秀再[1,2] 杨昌军[3] Zhang Chen;Zhang Xiuzai;Yang Changjun(School of Electronics and Information,Nanjing University of Information Science&Technology,Nanjing,Jiangsu 210044,China;Jiangsu Province Atmospheric Environment and Equipment Technology Collaborative Innovation Center,Nanjing University of Information Science&Technology,Nanjing,Jiangsu 210044,China;National Satellite Meteororologistic Center,Key Laboratory of Radiometric Calibration and Validation for Environmental Satellites,China Meteorological Administration,Beijing 100081,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,江苏南京210044 [2]南京信息工程大学江苏省大气环境与装备技术协同创新中心,江苏南京210044 [3]中国气象局中国遥感卫星辐射测量和定标重点开放实验室国家卫星气象中心,北京100081

出　　处：《激光与光电子学进展》2021年第20期490-500,共11页Laser & Optoelectronics Progress

基　　金：国家自然科学基金青年科学基金(11504176,61601230);江苏省高校自然科学研究项目(13KJA510001);江苏省自然科学基金青年基金(BK20141004)。

摘　　要：针对目前大多数云与云阴影检测方法容易产生误检、边缘细节丢失严重以及检测不够精确的问题,提出一种基于双注意力卷积神经网络模型(RDA-Net)的遥感影像云与云阴影检测方法。模型中引入双注意力模块可以有效捕获全局特征的依赖关系,使用递归残差模块可以避免深层网络出现退化,改进空洞空间金字塔池化模块在不改变特征图尺寸的前提下可以提取图像的多尺度特征。首先对遥感影像数据集进行预处理并制作对应的标签,然后利用高分一号WFV遥感影像数据集进行训练和测试。实验结果表明,所提方法有效提高云与云阴影的检测精度,在复杂条件下仍能获得较好的云与云阴影的边缘细节。Aiming at the problems that most of the current cloud and cloud shadow detection methods are prone to misdetection,serious edge detail loss and insufficient detection accuracy,a remote sensing image cloud and cloud shadow detection method based on the dual attention convolutional neural network model(RDA-Net)is proposed.In the model,the dual attention module is introduced to can effectively capture the dependence of global features,the recursive residual module is used to avoid degradation of the deep network,and the improved atrous spatial pyramid pooling module can extract multi-scale features without changing the size of the feature map.First,the remote sensing image dataset is preprocessed and made the corresponding labels,and then the Gaofen-1 WFV remote sensing image dataset is used for training and testing.Experimental results show that the proposed method can effectively improve the detection accuracy of cloud and cloud shadow,and can still obtain better edge details of cloud and cloud shadow under complex conditions.

关 键 词：遥感 双注意力 云与云阴影检测 递归残差 改进空洞空间金字塔池化 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置] P426.5[自动化与计算机技术—控制科学与工程]