【作者】 薛笑荣； 赵荣椿； 张艳宁； 段锋； 苏爱民；

【Author】 XueXiaoRong ZhaoRongChun Zhang YanNing DuanFeng SuAiMin (Dept. of Computer Science & Engineering, Northwestern Polytechnical University,Xi’an 710072)

【机构】 西北工业大学计算机科学与工程系；

【摘要】 SAR(合成孔径雷达)图像包含有相干斑噪声,传统方法不能很好对SAR图像进行分割,本文结合SAR图像和小波变换多分辨分析的特点,提出了一种新的SAR图像分割方法。该方法利用树型小波变换提取SAR图像的纹理特征信息,根据SAR图像噪声在小波域中的分布特点对SAR图像进行滤波,最后以SAR图像的树型小波能量特征和滤波后的灰度为特征向量对SAR图像进行分割。实验结果分析表明,该方法是一种有效的SAR图像分割方法。更多还原

【Abstract】 There is speckle in SAR image. In the paper, a new method of SAR Image segmentation is proposed with the combination of the features of SAR image and multifrequency analysis of wavelet. First, texture features are distilled with tree wavelet; Second,SAR image is filtered according to the features of its distribution in the wavelet field. At last, SAR image is segmented according to the vector composed of wavelet texture features and tone of filtered SAR image. With the experiment result, the method is proved that it is an efficient one of SAR image segmentation.更多还原