基于序列非线性滤波SAR影像水体自动提取  

Automatic Water Body Extraction from SAR Images Based on Sequence Non-linear Filter

作　　者：窦建方[1] 陈鹰[1] 翁玉坤[1] 

机构地区：[1]同济大学测量与国土信息工程系,上海200092

出　　处：《海洋测绘》2008年第4期69-72,共4页Hydrographic Surveying and Charting

摘　　要：由于合成孔径雷达(SAR)图像中固有斑点噪声的强烈影响,某些对于光学图像有很好效果的目标提取区域分割方法,但是对于SAR图像来说,效果不很好,针对水体目标的亮度及形状分布特征,不作阈值分割处理,而采用序列非线性滤波处理方法,可以快速有效地实现SAR影像水体目标的自动提取识别。According to the impact of inherent speckle of SAR images, some edge detection operators have a good effect on optical images,but have a poor effect on SAR images. In this paper, as to the shape distributed characteristics and brightness of water body, we not use threshold segmentation processing, but adopt sequence non-linear filtering approach which can automatically extract and identify water body from SAR images quickly and efficiently.

关 键 词：合成孔径雷达图像 斑点噪声 区域分割 水体提取 非线性滤波 阈值分割 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]