复杂环境下尺度不变特征的检测与匹配技术研究

Research on Scale Invariant Feature Extraction and Matching Technique in Complex Environment

针对农业机器人复杂的工作环境,引入了一种新的鲁棒特征点检测算法——SURF算法,其对光照变化、旋转、尺度变化等具有很好的鲁棒性,精度能达到亚像素级别;在此基础上,利用最近邻法则结合BBF(best bin first)搜索算法,对SURF特征点进行精确匹配,实验表明,所提出的方法鲁棒性或实时性较目前常用的Harris算法和SIFT算法更好,可应用在机器人视觉定位、地图构建、智能导航等方面,具有一定的理论和应用价值。

Aimed at the complex work environment of agricultural robots, a new robust feature point detection algorithm-SURF algorithm is introduced. It shows good robustness in environment where exist illumination, rota- tion, or scale change, and achieve sub-pixel precision level; on this basis, the nearest neighbor rule and BBF （best bin first） search algorithm are used to do many feature points matching experiments. The result shows that the method is more robust than Harris and has better real time than SIFT algorithm. It has some theoretical and practical value in robot vision localization, map building, intelligent navigation, etc.