摘要
为了提升无人机飞行过程中的定位精度,以及使无人机正常飞行于全球定位系统(GPS)信号受到干扰或是失效的环境中,提出了基于机器视觉的无人机飞行过程中的定位算法。首先,基于尺度不变特征转换(SIFT)和KDTree搜索的图像匹配算法以及各坐标系之间的变换关系得到改进的坐标变换算法Trf1和Trf2,算法Trf1可求出目标匹配点的地面坐标,即建立无人机飞行环境地图,算法Trf2可计算出无人机实时位置;然后,在无人机飞行过程中利用算法Trf1和Trf2得出定位算法,并设计实验。实验表明,利用该算法计算出的无人机实时位置误差保持在12 cm的范围内,从而验证了算法的准确性。
In order to improve the localization accuracy for Unmanned Aerial Vehicle(UAV)in flighta localization algorithm is proposed based on machine vision.This algorithm can make UAV fly in the environment where Global Positioning System (GPS) signal is disturbed or is in failure.First of alltwo modified coordinate transformation algorithmsTrf1 and Trf2were obtained based on ScaleInvariant Feature Transform(SIFT)KDTree search image matching algorithm and the transformation between coordinate systems.With the help of Trf1the first coordinate transformation algorithmground coordinates of the target matched points were calculated out to build up a map of the flight environment.The second algorithmTrf2could calculate the realtime locations of UAV.Subsequentlythe localization algorithm in UAV flight was obtained based on the two modified coordinate transformation algorithmsand experiment was carried out based on the algorithms.Experiment results show that errors of calculated UAV positions are within 12 cmwhich demonstrates the accuracy of this method.
出处
《电光与控制》
北大核心
2013年第11期42-46,共5页
Electronics Optics & Control
基金
国家自然科学基金(61074064)
关键词
无人机
SIFT算法
坐标变换算法
机器视觉
飞行过程定位算法
UAV
SIFT algorithm
coordinate transformation algorithm
machine vision
localization algorithm in flight