摘要
针对合成孔径雷达(SAR)影像相干斑噪声强烈且分布形式及参数获取困难的问题,提出一种基于独立分量分析(ICA)和序列非线性滤波(SNF)实现多极化SAR影像相干斑噪声抑制和机场目标快速提取方法。利用ICA从多极化SAR影像中自动分离出图像数据与相干斑噪声,自动选择相干斑指数最小的分量为图像分量。通过SNF从分离出的图像分量中提取出机场目标。采用ENVISAT ASAR多极化影像进行实验,结果表明该方法能快速准确地提取多极化SAR影像中的机场目标。
A new method is proposed for speckle noise suppression and airport objects extracting from SAR imagery based on Sequential Nonlinear Filtering(SNF) and Independent Component Analysis(ICA). Speckle noise and image data are separated from multi-polarimetric imagery, and the components with the least speckle index are chosen as the object component automatically by means of ICA. Airport objects are extracted from the separated object component imagery based on sequential nonlinear filtering. Using ENVISAT ASAR polarimetric imagery, experimental results show that the proposed method can extract airport objects rapidly and accurately.
出处
《计算机工程》
CAS
CSCD
北大核心
2009年第24期1-3,共3页
Computer Engineering
基金
国家"863"计划基金资助项目"特大城市中心密集区复杂地物群信息的自动提取与定量分析技术"(2007AA12Z178)
"十一五"国家科技支撑计划基金资助项目"村镇信息快速采集与处理关键技术研究"(2006BAJ09B01)
关键词
极化合成孔径雷达影像
机场目标
自动识别
独立分量分析
序列非线性滤波
polarimetric SAR imagery
airport objects
automatic recognition
Independent Component Analysis(ICA)
Sequential Nonlinear Filtering(SNF)