基于POS与图像匹配的无人机目标定位方法研究

Research on UAV Targeting Based on POS and Image Matching

针对目前无人机利用POS(position and orientation system,POS)方法定位目标精度低、利用地图匹配方法定位目标应用范围受限的问题,根据无人机航摄影像与POS数据以及数字卫星地图特点,提出了一种基于POS与图像匹配的无人机目标定位方法.首先采用改进的SIFT(scale-invariant feature transform)算法将无人机航片或视频帧实时拼接,然后利用POS数据,根据制定的搜索策略确定整张航片或视频帧在数字卫星地图上的匹配区域,最后利用改进的SIFT算法将航片或视频帧与该范围的数字卫星地图匹配完成目标定位.实验结果证明,该方法无需地面控制点即可实现大范围的目标实时二维定位,定位精度与速度均有较大提高,是一种有效利用图像匹配对目标进行定位的方法.

To address the problem of low accuracy of the target positioning for one UAV （unmanned aerial vehicle）, a UAV target positioning method is presented based on POS and image matching according to the characteristics of UAV aerial images, POS data and satellite digital map.First, by using the improved SIFT method,the UAV aerials or video frames are real- time stitched.Then,by taking advantage of POS data,the approximate areas of the entire aerials or video frames on the satellite digital map are determined based on the formulated searching strategy.Finally, by making use of the improved SIFT algorithm, the aerial photos（video frames） and satellite digital map in this range are matched to complete the positioning.The results prove that this method can achieve a wide range of real-time two-dimensional positioning without ground control points, while the precision and speed are improved, which is an effective method for target positioning utilizing image matching.