摘要
针对经典阈值分割方法在高分辨率合成孔径雷达SAR(Synthetic Aperture Radar)河流边界提取中存在很高的噪声斑点和在高山区域SAR图像存在大面积的阴影的问题,提出一种新颖的基于高分辨率SAR强度图像的河流边界自动提取方法。该方法核心在于结合河流的局部连接特性和基于变化水平集框架中的区域活动轮廓模型(ACM),以区分河流区域和背景。实验结果证实了该方法的有效性和稳健性。
Using classic thresholding method to extract river boundaries in high resolution synthetic aperture radar （SAR） image has the problems of high speckle noise and the large area shadows occurred in SAR images of mountains region. In order to solve the problems, in this paper we presented a novel approach for automatic river boundaries extraction which is based on high resolution SAR intensity image. The key of our approach lies on the combination of local connectivity feature of the river and the regional active contours model （ACM） based on variational level set framework, it is for differentiating the river field from the background. Experimental results prove the effectiveness and robustness of the appraoch,
出处
《计算机应用与软件》
CSCD
2015年第11期213-216,共4页
Computer Applications and Software
