基于SURF特征点的自主空中加油定位研究

Object Location Technique for Autonomous Aerial Refueling Based on SURF Feature

针对硬式空中加油技术中加油插座的定位问题,提出了一种结合SURF(Speeded-up Robust Features)特征点的双目立体视觉定位方法,确定了加油插座的空间位置,实现伸缩管和加油插座的精确对准。基于SURF匹配算法,对双目视觉系统采集的左右图像进行目标检测,并获取匹配目标的SURF特征点,通过空间误匹配点对的剔除和目标点坐标的计算,确定左右图像中具有空间位置一致性的目标点(即加油插座),从而恢复目标点的三维信息。实验结果表明,结合SURF方法能够有效地对加油插座的空间位置进行定位,具有一定的实用价值。

For the location of the refueling receptacle in the boom and receptacle aerial refueling, an object loca- tion method was developed based on SURF （ Speeded - up Robust Features） feature points by binocular stereo vi- sion, which can determine the spatial of refueling receptacle and realize the precise docking of refueling boom and re- fueling receptacle. By the use of SURF matching algorithm, both left and right images collected by a binocular stereo vision system were detected for the object, thus suitable SURF feature points of matching object were found. Then by deleting wrong matching points and computing object point coordinate, the points of object, namely refueling recepta- cle, which describes the same spatial location in the left and right images, can be determined. Finally, the three - dimensional coordinates of the object points were rebuilt in the camera＇s coordinate system. The results show that the method discussed can effectively locate the spatial location of refueling receptacle, and has some practical value.