一种光学与合成孔径雷达影像融合去云方法  

A Method for Cloud Removal Using Optical and Synthetic Aperture Radar Image Fusion

作　　者：龚循强[1,2,3] 方启锐 侯昭阳 张智华 夏元平 Gong Xunqiang;Fang Qirui;Hou Zhaoyang;Zhang Zhihua;Xia Yuanping(Key Laboratory of Regional Mining Environmental Monitoring and Control of Poyang Lake,Ministry of Natural Resources,East China University of Technology,Nanchang 330013,Jiangxi,China;State Key Laboratory of Information Engineering in Surveying,Mapping,and Remote Sensing,Wuhan University,Wuhan 430079,Hubei,China;Jiangxi Academy of EcoEnvironmental Sciences and Planning,Nanchang 330039,Jiangxi,China;Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,Gansu,China;The Sixth Geological Brigade,Jiangxi Bureau of Geology,Yingtan 335000,Jiangxi,China)

机构地区：[1]东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,江西南昌330013 [2]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079 [3]江西省生态环境科学研究与规划院,江西南昌330039 [4]兰州交通大学测绘与地理信息学院,甘肃兰州730070 [5]江西省地质局第六地质大队,江西鹰潭335000

出　　处：《光学学报》2024年第24期185-196,共12页Acta Optica Sinica

基　　金：国家自然科学基金(42101457,42174055);自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室开放基金项目(MEMI2023-12);武汉大学测绘遥感信息工程国家重点实验室开放研究基金(23R03)。

摘　　要：提出一种光学与合成孔径雷达(SAR)影像融合去云的方法。首先,在云检测部分利用分形网络演化方法(FNEA)对云区进行提取,将含云影像分为有云区域和无云区域,并对无云区域和有云区域分别设置相应的融合规则。然后,用非下采样剪切波变换(NSST)对影像进行分解,在低频部分加入基于窗口中心距离赋权的区域能量(DWRE),使影像的纹理细节在最终融合影像中得到保留;在高频部分,无云区域基于双通道单位连接脉冲耦合神经网络(DCULPCNN),有云区域利用滚动引导滤波(RGF),提高SAR影像与光学影像之间的线性关联性。最后,经过NSST逆变换得到融合去云影像。实验结果表明,所提方法与其余9种方法相比,在信息熵(EN)、平均梯度(AG)、空间频率(SF)、结构相似性(SSIM)、峰值信噪比(PSNR)和均方根误差(RMSE)6个评价指标中总体表现为最优,相比次优指标分别提升了0.054、0.450、0.910、0.029、0.215、0.290,可以更好地保留地物纹理及细节信息,在有效去除云污染的同时提高了影像质量。Objective Synthetic aperture radar(SAR)data can penetrate clouds and fog in all weather conditions,which makes it a valuable tool for supplementing ground information obscured by thick clouds when SAR images are used as auxiliary data.SARassisted cloud removal techniques allow for the generation of cloudfree references on days when images are contaminated by clouds.However,there are still two main challenges in using SAR data for cloud removal.First,the differences in imaging mechanisms between optical and SAR systems make it difficult for SAR data to directly substitute the ground information blocked by clouds.Second,there are concerns regarding image quality after SAR speckle noise reduction and fusion.Methods To effectively reconstruct cloudcontaminated ground information using SAR data,we propose a new method for cloud removal through optical and SAR image fusion.First,the cloud regions are detected and extracted using the fractal net evolution approach(FNEA),which separates the image into areas with clouds and without clouds.Corresponding fusion rules are then set for the cloudfree and cloudy regions.Next,the images are decomposed into lowfrequency and highfrequency parts using the nonsubsampled shearlet transform(NSST).In the lowfrequency component,the window center distance weighted regional energy(DWRE)is utilized to preserve texture details in the final fused image.For the highfrequency component,the dualchannel unitlinking pulse coupled neural network(DCULPCNN)and rolling guidance filter(RGF)are applied to the cloudfree and cloudy regions,respectively.Thus,the linear correlation is enhanced between the SAR image and the optical image,while minimizing the introduction of SAR coherent spot noise.Finally,the fusion images are obtained through inverse NSST.Results and Discussions The experimental results demonstrate that the proposed method achieves superior performance in both qualitative and quantitative evaluations compared to nine other methods.Qualitatively,as depicted in Figs.2‒7,our approach effect

关 键 词：遥感影像去云 基于窗口中心距离赋权的区域能量 滚动引导滤波 双通道单位连接脉冲耦合神经网络 

分 类 号：P237[天文地球—摄影测量与遥感]