特征点提取算法比较及四旋翼平台验证

摘要

Several feature points extraction methods such as Harris, SIFT and SURF were de-scribed.SIFT and SURF methods were mainly compared in order to find a better solution for the contradictions between extraction precision and extraction consuming time in vision navi-gation.A quadrotor verification platform integrating was built to test extraction precision and extraction consuming time of SIFT and SURF methods in the natural environment.The com-parison result shows that SURF was the suitable method which can meet the requirements of extraction precision and real time simultaneously.%针对视觉导航中存在的图像特征点提取精度与用时之间的矛盾，对几种常用的特征点提取算法（ Harris， SIFT， SURF）进行了论述，并针对SIFT算法和SURF算法进行了比较，同时搭建了四旋翼验证平台，利用四旋翼实验平台，针对自然环境中的实物测试了上述两种算法的提取精度与用时，结果表明SURF算法是视觉导航中综合考虑匹配的正确率及实时性的较优选择。