联合均匀离散曲波变换及非局部张量稀疏正则化的SAR图像相干斑抑制  

SAR Image Despeckling Based on Joint of Discrete Curvelet Transform and Nonlocal Tensor Sparse Regularization

作　　者：洪樱[1] 肖霞 张承德 陈高 HONG Ying;XIAO Xia;ZHANG Cheng-de;CHEN Gao(School of Computer Science and Artificial Intelligence,Wuhan Textile University,Wuhan 430200,China;School of Public Administration,Huazhong Agricultural University,Wuhan 430070,China;School of Information and Safety Engineering,Zhongnan University of Economics and Law,Wuhan 430073,China;School of Electrical Engineering and Intelligentization,Dongguan University of Technology,Dongguan 523808,China)

机构地区：[1]武汉纺织大学计算机与人工智能学院,中国武汉430200 [2]华中农业大学公共管理学院,中国武汉430070 [3][JP2]中南财经政法大学信息与安全工程学院,中国武汉430073[JP] [4]东莞理工学院电子工程与智能化学院,中国东莞523808

出　　处：《湖南师范大学自然科学学报》2022年第4期159-166,共8页Journal of Natural Science of Hunan Normal University

基　　金：国家自然科学基金资助项目(71974202);教育部人文社会科学研究青年基金项目(20YJC860040);湖北省高等学校哲学社会科学研究重大项目(21ZD018);2020年度武汉市科技局应用基础前沿项目(2020010601012183);湖北省高等学校实验室研究项目(HBSY2021-58);中南财经政法大学研究生拔尖人才培养项目(XKRH202101);中南财经政法大学中央高校基本科研业务费专项资金(202211411,202151423,202211415)。

摘　　要：正则化技术是合成孔径雷达(Synthetic Aperture Radar,SAR)图像相干斑抑制的一种有效工具。在正则化相干斑抑制中,设计有效的正则化项来反映图像的先验信息起着至关重要的作用。本文通过同时刻画SAR图像的局部稀疏性和非局部自相似性,提出了一种新的基于联合稀疏正则化的SAR图像相干斑抑制模型。该模型包含一个数据保真项和两个正则化项,其中一个正则化项采用离散曲波变换来描述SAR图像的局部平滑性,另一个正则化项采用张量稀疏模型刻画SAR图像的非局部自相似性,图像张量是由具有相似结构的图像块组合,从而在对图像张量进行稀疏表示的过程中能够刻画图像中固有的局部稀疏性和非局部自相似性。进一步,为了求解该模型,提出了一种分离Bregman迭代技术的高效求解算法。实验结果表明,该模型在图像质量的主观视觉评价和客观评价方面均明显优于传统和最新的技术。Regularization-based approaches have recently been considered as effective tools for synthetic aperture radar(SAR)image despeckling,where designing effective regularization terms to reflect the image priors plays a critical role.In this paper,by characterizing local sparsity and nonlocal self-similarity of SAR images simultaneously,a new joint sparsity regularization model for SAR image despeckling is proposed.The proposed model contains a data fidelity term and two regularization terms.One of the two regularization terms employs the discrete curvelet transform to depict the local smoothness of the SAR image,and the other employs a tensor sparse transform of the three-dimensional(3 D)tensor generated by stacking similar SAR image patches.The joint employment of these two regularization terms,which has not been utilized in existing methods of SAR image despeckling yet,aims to produce better despeckling performance and preserve more geometrical features of SAR images.Furthermore,to address the optimization problem in the proposed model,a new efficient algorithm is derived based on the split Bregman iterations framework.Experimental results show that the proposed model considerably outperforms some conventional and state-of-the-art techniques in terms of both subjective visual assessment of image quality and objective evaluation.

关 键 词：SAR图像相干斑抑制 离散曲波变换 非局部自相似性 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]