结合全局上下文与融合注意力的干涉相位去噪  

Interferometric phase denoising combining global context and fused attention

作　　者：曾庆旺 董张玉[1,2,3] 杨学志 种法亭 Zeng Qingwang;Dong Zhangyu;Yang Xuezhi;Chong Fating(College of Computer and Information,Hefei University of Technology,Hefei 230031,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology,Hefei 230031,China;Anhui Province Laboratory of Intelligent Interconnection System,Hefei 230031,China;College of Software,Hefei University of Technology,Hefei 230031,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230031 [2]工业安全与应急技术安徽省重点实验室,合肥230031 [3]智能互联系统安徽省实验室,合肥230031 [4]合肥工业大学软件学院,合肥230031

出　　处：《中国图象图形学报》2023年第9期2956-2968,共13页Journal of Image and Graphics

基　　金：安徽省重点研究与开发计划项目(202004a07020030);安徽省自然科学基金项目(2108085MF233);中央高校基本科研业务费专项项目(JZ2021HGTB0111)。

摘　　要：目的干涉相位去噪是合成孔径雷达干涉测量(interferometric synthetic aperture radar,InSAR)技术中的关键环节,其效果对测量精度具有重要影响。针对现有的干涉相位去噪方法大多关注局部特征以及在特征提取方面的局限性,同时为了平衡去噪和结构保持两者之间的关系,提出了一种结合全局上下文与融合注意力的相位去噪网络GCFA-PDNet(global context and fused attention phase denoising network)。方法将干涉相位分离为实部和虚部依次输入到网络,先从噪声相位中提取浅层特征,再将其映射到由全局上下文提取模块和融合注意力模块组成的特征增强模块,最后通过全局残差学习生成去噪图像。全局上下文提取模块能提取全局上下文信息,具有非局部方法的优势;融合注意力模块既强调关键特征,又能高效提取隐藏在复杂背景中的噪声信息。结果所提出的方法与对比方法中性能最优者相比,在模拟数据结果的平均峰值信噪比(peak signal to noise ratio,PSNR)和结构相似性(structural similarity,SSIM)指标分别提高了5.72%和2.94%,在真实数据结果的平均残差点减少百分比(percentage of residual point reduction,PRR)和相位标准偏差(phase standard deviation,PSD)指标分别提高了2.01%和3.57%。结合定性与定量分析,所提出的方法优于其他5种不同类型的相位去噪方法。结论提出的去噪网络较其他方法具有更强大的特征提取能力,此外由于关注全局上下文信息和强调关键特征,网络能够在增强去噪能力的同时保持原始相位细节。Objective Interferometric phase noise is introduced by three types of inherent factors:1)system noise,such as thermal noise and synthetic aperture radar(SAR)speckle noise;2)decoherence problems,including baseline,temporal,and spatial decoherence;3)signal processing errors,such as misregistration.The existence of noise increases the difficulty of phase unwrapping and even causes the process to fail,thereby seriously interfering with the final interferometric result.Therefore,interferometric phase denoising is a key link in interferometric SAR(InSAR)technology.Its effect has an important influence on the accuracy of measurement results.The existing interferometric phase denoising algorithms still have many defects.First is the insufficient ability to capture global contextual information.Some algorithms ignore global context information or only focus on local context information derived from a few pixels.They also lack global context infor mation.This feature is manifested as unstable detail preservation ability in denoising results.Second,many researchers only pay attention to the influence of the spatial dimension or channel dimension of the image on the denoising result to improve the performance of denoising networks.However,they do not use spatial and channel dimensions in combination.Third,the high-level features extracted from the deep layers of the convolutional neural network have rich semantic informa tion and ambiguous spatial details.In comparison,the low-level features extracted from the shallow layers of the network contain considerable pixel-level noise information.However,these features are isolated from one another;thus,they can not be fully used.Method Most of the existing interferometric phase denoising methods focus on local features,and they have many limitations in feature extraction.A phase denoising network called GCFA-PDNet is proposed to solve these prob lems while balancing the relationship between denoising and structure preservation.This proposed phase denoising network combines global

关 键 词：合成孔径雷达干涉测量(InSAR) 干涉相位去噪 残差学习 全局上下文 融合注意力 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]