考虑小波数相关性的SAR图像去斑算法  

Study on Despeckling Algorithm for SAR Images by Considering Correlation of Wavelet Coefficients

作　　者：陈国忠[1] 王廿菊[2] 崔雷[1] 陈重华[1] 孙杰[1] 朱少杰[1] CHEN Guozhong;WANG Nianju;CUI Lei;CHEN Chonghua;SUN Jie;ZHU Shaojie(Shanghai Institute of Satellite Engineering,Shanghai 201109,China;Shanghai Academy of Spaceflight Technology,Shanghai 201109,China)

机构地区：[1]上海卫星工程研究所,上海201109 [2]上海航天技术研究院,上海201109

出　　处：《上海航天》2018年第3期23-27,共5页Aerospace Shanghai

摘　　要：SAR(合成孔径雷达)发射的相干信号之间会使图像产生相干斑点噪声,严重影响SAR图像的应用,需加以抑制。通过研究分析,一副图像小波分解之后的小波系数在幅度、符号之间具有强烈的相关性,由此提出了一种小波去斑算法,该算法考虑了小波系数幅度、小波系数符号之间的相关性。利用合成斑点噪声图像和实际SAR图像验证了该算法的有效性。结果表明:该算法在抑制SAR图像斑点噪声的同时,具有更好的边缘细节保持能力,提升了SAR图像后续应用效能。Because SAR（synthetic aperture radar）images are corrupted by speckle noise,which degrades the quality and interpretation,SAR images should be despeckled.The wavelet coefficients of an image exit the high correlation not only for their amplitude but also for their sign.Therefore,in this paper,a new wavelet-based despeckling algorithm is proposed by considering the sign and amplitude correlation of the wavelet coefficients.In the end,both simulated speckle images and real SAR images are used to validate the performance of this new algorithm and the final experimental results show that the speckle is reduced and the detail of the image is preserved,which improves subsequent application efficiency of SAR images.

关 键 词：合成孔径雷达图像 相关性 斑点噪声 小波 抑制 

分 类 号：TN911[电子电信—通信与信息系统]