基于改进重叠组稀疏的遥感图像去噪算法  

Remote Sensing Image Denoising Algorithm Based on Improved Overlap Group Sparsity

作　　者：高雪[1] 李喆 

机构地区：[1]长春理工大学数学与统计学院,吉林 长春 [2]长春理工大学中山研究院遥感技术与大数据分析实验室,广东 中山

出　　处：《应用数学进展》2024年第7期3527-3540,共14页Advances in Applied Mathematics

摘　　要：脉冲噪声对遥感图像的质量有着显著的负面影响,它会破坏图像的连续性,降低图像的可视性和信息的准确性,从而影响遥感图像的应用效果。本文通过融合自适应中值滤波技术和组稀疏模型,设计了基于改进重叠组稀疏的模型,以有效地消除遥感图像的脉冲噪声,并消除梯度伪影现象。由于本文所提出的模型是非凸问题,我们利用最大–最小化(MM)方法和交替方向乘子法(ADMM)对模型进行求解。实验结果表明,本文提出的模型在峰值信噪比(PSNR)和结构相似度(SSIM)方面优于其他四种算法。Impulse noise has a significant negative effect on the quality of remote sensing image. It can destroy the continuity of image, reduce the visibility and sourcing circumstances of image, and affect the application effect of remote sensing image. By fusing adaptive median filter and group sparse model, a new model based on improved overlap group sparse model is designed to eliminate impulse noise and gradient artifacts in remote sensing images. Since the model presented in this paper is non-convex, we use the maximum-minimum (MM) method and the alternating direction multiplier (ADMM) method to solve the model. Experimental results show that the proposed model outperforms the other four algorithms in Peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

关 键 词：脉冲噪声 重叠组稀疏 交替方向乘子法 自适应中值滤波 图像去噪 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]