基于FCM与SVM相结合的高分辨率遥感影像道路提取

Road Extraction of High Resolution Remote Sensing Images Based on Combining FCM and SVM

在现有的高分辨率遥感卫星影像中道路信息提取方法的充分研究与分析的基础上,本文提出了一种基于模糊C均值聚类与支持向量机相结合的高分辨率遥感影像道路提取算法。实验选取数据是IKONOS遥感卫星采集获得的山东济南城区部分道路影像,将本文算法与支持向量机、模糊C均值聚类常用的道路提取算法方法做对比,实验结果显示文中提出的算法在精度上有很大的提高,验证了算法的有效性与可靠性。

Based on the full study and analysis of the existing roads information extraction algorithms for the high resolution remote sensing satellite images, a road extraction algorithm combining Fuzzy c-means algorithm and Support Vector Machine for the high resolution remote sensing satellite images. The experimental data are part of roads images collected from IKONOS remote sensing satellite in Shandong, Ji′nan, the proposed algorithm was compared with Fuzzy c-means algorithm and Support Vector Machine, the results show that the proposed algorithm is greatly improved in accuracy, and verifying the reliability and validity of the roads extraction algorithm.