基于种子点增长的SAR图像海岸线自动提取算法  

Algorithm of detection coastline from SAR images based on seeds growing

作　　者：谢明鸿[1,2] 张亚飞[1,2] 付琨[1] 

机构地区：[1]中国科学院电子学研究所 [2]中国科学院研究生院,北京100049

出　　处：《中国科学院研究生院学报》2007年第1期93-98,共6页Journal of the Graduate School of the Chinese Academy of Sciences

基　　金：国家863计划项目(2003AA131152)资助

摘　　要：SAR图像中斑点噪声的存在使得很难利用简单的阈值分割技术对其进行海岸线提取,而很多基于复杂数学模型的提取算法又常常由于较慢的检测速度限制了它们的应用.本文基于种子点增长的思想,给出了一种快速的海岸线自动提取算法.首先该算法利用像素值统计信息自动定位一个初始种子点区域,并计算初始均值M与初始阈值T.然后基于不断更新的M和T进行海域点增长.增长结束后,对得到的连通海域进行轮廓边界跟踪从而确定出具体的海岸线位置.将其应用于真实的SAR图像,证明了该算法的有效性和实时性.It is very difficult to extract the shoreline from SAR images by using a simple threshold technique for the presence of speckles. The applications of many coastline detection algorithms based on complex mathematic models are time consuming and thus limited. A fast method is presented in this paper based on the idea of seeds growing. First, it locates the initial seeds region automatically based on statistic information of pixel values. Then, the initial mean M and threshold T are calculated. Next, seeds-growing is performed based on the M and T which are updated continuously. After the seeds-growing ends, the location of the shoreline is extracted from the connected sea region by a traditional contour tracing algorithm. Experimental results using real SAR images indicate that it is an effective and real-time algorithm.

关 键 词：SAR图像 海岸线提取 种子点增长 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]