基于VI-SLAM的四翼无人机多目标视觉定位技术

Multi-target visual positioning technology of four-wing UAV based on VI-SLAM

摘要:

针对传统多目标视觉定位技术定位误差大这一问题，基于VI-SLAM的四旋翼无人机提出了一种新的多目标视觉定位技术，阐述了定位技术原理，在进行定位时，导航定位系统、航空姿态测量系统、机载光电测量平台共同工作，通过多目标相机标定、锁定目标背景差分确定目标在摄像机坐标系的位置，将摄像机坐标系转换成载机机体坐标系，再将载机机体坐标系转换成大地坐标系，从而实现定位，引入北斗卫星导航系统和递归最小二乘算法降低定位误差。对比实验结果表明，相较于传统定位技术，基于VI-SLAM的四旋翼无人机的多目标视觉定位技术定位误差更小，应用性更广。

Abstract:

Aiming at the problem of large positioning error of traditional multi-target visual positioning technology, a new multi-target visual positioning technology based on VI-SLAM is proposed. The principle of positioning technology is expounded. The positioning system, the aeronautical attitude measurement system, and the airborne photoelectric measurement platform work together. The multi-target camera is calibrated and the target background difference is locked to determine the position of the target in the camera coordinate system, and the camera coordinate system is converted into the carrier coordinate system. The machine body coordinate system is converted into a geodetic coordinate system to achieve positioning, and the Beidou satellite navigation system and the recursive least squares algorithm are introduced to reduce the positioning error. The experimental results show that compared with the traditional positioning technology, the multi-target visual positioning technology of the quad-rotor UAV based on VI-SLAM has smaller positioning error and wider application.