摘要
运用SIFT算法对单目所采集的室外视频图像的相邻两帧进行了特征点的检测与匹配。采用改进的RANSAC算法对所匹配点进行了误匹配点剔除。根据相邻两帧图像特征点的跟踪以及里程计读数作为辅助信息,求解特征点的三维坐标;进而根据视觉里程计模型,达到机器人的定位。实验结果表明,该方法相比传统的里程计定位精度高,比之双目激光等定位方法,又有成本廉价的优点。
Detecting and matching two adjacent frames collected from outdoor environment by using the SIFT al-gorithm, and then eliminating the false matching points with the method of a modified RANSAC algorithm. Thethree-dimensional coordinates of these points according to tracking the two adjacent frame image feature point andthe odometer reading are solve. And the robot positioning according to the visual model of the odometer is achieved.The experimental results show that the positioning precision using this method is higher than the traditional odome-ter, and it is cheaper than binocular and laser.
出处
《科学技术与工程》
北大核心
2014年第26期98-102,共5页
Science Technology and Engineering
基金
2012江苏省"青蓝工程"项目
江苏省智能传感器网络工程技术研究开发中心开放基金(ZK13-02-03)资助
