摘要
传统的基于矢量或基于矩阵的遥感图像去噪方法在去噪过程中可能导致空间域和光谱域失真。为了提高去噪效果的同时尽量降低失真,提出了一种多线性加权核范数最小化方法。首先,考虑到遥感图像的谱连续性和按三模展开矩阵的相互依赖性,构建了一种多线性秩来建模遥感图像的空间和谱非局部相似性。然后,为了使该方法更易于处理,采用基于变量分裂的方法来解决此优化问题。实验结果表明:该方法在客观度量和主观视觉质量两个方面都较目前最先进的方法都有较大的提高。
Classical vector-based or matrix-based denoising methods for remote sensing images(RSIs)may cause distortion both in spatial domain and spectral domain.To improve denoising performance and reduce the distortion,a denoising method based on multi-linear weighted nuclear norm is proposed.Firstly,by considering spectral continuity and inter-dependency of three unfolding matrices along three modes of RSI,a multi-linear rank is constructed to model the spatial and spectral nonlocal similarity.Then,to make the proposed method more tractable,a variable splitting-based technique is used to solve the optimization problem.Experiment results reveal that the proposed method can provide substantial improvements over the current state-of-the-art methods in terms of both objective metric and subjective visual quality.
作者
孔祥阳
徐保根
周杰
Xiang-yang KONG;Bao-gen XU;Jie ZHOU(Ministry of Basic Education,Sichuan Engineering Technical College,Deyang 618000,China;School of Automation,Northwestern Polytechnical University,Xi’An 710072,China;School of Science,East China Jiaotong University,Nanchang 330013,China)
出处
《机床与液压》
北大核心
2020年第12期184-190,208,共8页
Machine Tool & Hydraulics
基金
国家自然科学基金项目(11961026)
江西省自然科学基金项目(20171BAB201009)。
关键词
遥感图像去噪
加权核范数
交替方向最小化
峰值信噪比
结构相似性
Denoising
Weighted nuclear norm
Alternating direction method of minimization
Peak signal-to-noise ratio
Structural similarity index measurement
