SAR图象中道路网络提取算法研究  

A Study of Road Network Extraction Method for SAR Images

作　　者：肖志强[1] 鲍光淑[1] 

机构地区：[1]中南大学信息物理工程学院,长沙410083

出　　处：《计算机工程与应用》2004年第14期94-96,共3页Computer Engineering and Applications

摘　　要：提出了一种利用遗传算法从高分辨率SAR图象中提取道路网络的方法。高分辨率SAR图象中目标背景复杂,同时由于受相干斑噪声的影响,很难直接从原始图象数据中提取道路特征。首先利用模糊C均值对滤波后的图象进行聚类,将道路类象素从图象中分离出来;根据聚类结果及道路特征建立数学模型,利用遗传算法搜索全局最优道路。实验结果表明该方法可以很好地从SAR图象中提取道路网络。A method of using GA to extract roads from high-resolution SAR images is presented.As the background of objectives in high-resolution SAR images is complicated and also affected by speckle noise,it is almost impossible to extract roads directly from original remote sensing images.We use fuzzy C means to classify the filtered images unsuper-visedly to extract road pixels from images,and construct a model according to the classified results and the feature of roads,then search globally optimized road by means of genetic algorithm.The experimental results show that the algo-rithm can effectively extract road networks from high-resolution SAR images.

关 键 词：模糊聚类 遗传算法 道路提取 SAR图象 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]