单目视觉人工路标辅助INS的组合导航定位方法

提出一种单目视觉人工路标辅助惯性导航系统(Inertial Navigation System,INS)的定位方法。首先设计人工路标,并用相机拍摄各预先设置的人工路标,记录拍摄每个路标时相机位置和姿态,建立视觉路标库。在利用惯性导航系统定位过程中,对单目相机采集到的图像进行路标提取、与路标库中相应路标进行匹配,估计当前相机位置和姿态,然后利用卡尔曼滤波将视觉匹配估计的位置信息和INS有效地融合。实验结果表明:传统航位推算方法的平均误差为0.715 m,本文组合导航方法的平均误差为0.154 m,该方法有效地提高了惯性导航定位的精度。

Integrated Navigation and Location Method of INS Assisted by Monocular Vision Artificial Landmark

This paper proposes a positioning method for the monocular visual artificial road sign assisted inertial navigation system(INS).The artificial road signs are designed,and the picture of each pre-set artificial road sign is taken by a camera,and the position and posture of the camera when it takes pictures of each road sign are recorded,and the visual road sign database is established.In the process of positioning by using the inertial navigation system,the image which is collected by the monocular camera,is extracted and matched with the corresponding landmarks in the landmark database to estimate the position and posture of the current camera.Then,by using the Kalman filter,the position information estimated by visual matching can be effectively combined with INS.The experimental results show that the average error of the traditional dead reckoning method is 0.715 m,and the average error of the combined navigation method in this paper is 0.154 m,which indicates that the above method can effectively improve the accuracy of inertial navigation positioning.