低空无人机影像匹配像对的提取方法  

Extraction method of image pairs for low-altitude UAV image matching

作　　者：任超锋 彭晓东 REN Chaofeng;PENG Xiaodong(School of Geology Engineering and Geomatics,Chang'an University,Xi'an 710054,China;Key Laboratory of Western Mineral Resources and Geological Engineering Ministry of Eduction,Chang’an University,Xi'an 710054,China)

机构地区：[1]长安大学地质工程与测绘学院,陕西西安710054 [2]长安大学西部矿产资源与地质工程教育部重点实验室,陕西西安710054

出　　处：《测绘工程》2019年第6期36-41,共6页Engineering of Surveying and Mapping

基　　金：中央高校基本科研业务费专项基金资助项目(310826161011,310826173101);航空遥感技术国家测绘地理信息局重点实验室开放基金(2015B10);国家自然科学基金资助项目(41271451)

摘　　要：针对已有的无人机影像匹配算法需要相机、测区先验知识且可靠性不高的问题,提出一种基于影像初始空间位置的无人机影像匹配算法。首先依据影像的位置信息对待匹配影像进行排序;然后基于盲匹配算法自动识别排序影像的搜索深度;最后根据跟踪所得的连接点结构信息,自动识别遗漏的待匹配像对。为验证文中算法的有效性,选择3种典型的无人机影像数据:传统的下视单相机、双相机倾斜相机、五相机倾斜相机。试验结果表明,算法能够适应各种类型的无人机影像匹配,其中单相机数据可靠度提升2.4%,双相机数据提升5.3%,五相机数据提升24.3%。Aiming at the problem that existing UAV image matching algorithm needs the prior information of the camera and the measuring area,as well as low reliability,this paper proposes a UAV image matching algorithm based on the initial spatial position of image.First,the images to be matched are sorted according to the location of the image.Then based on the exhaustive matching algorithm is used to automatically identify the search depth of the sorted image.Finally,the structure of the track point is used to automatically identify the missing image pairs to be matched.In order to validate the effectiveness of the proposed algorithm,three types of UAV image data are selected:the traditional down looking single-camera,double-camera and five-camera oblique camera.The experimental result shows that the proposed algorithm can adapt to all types of UAV image matching,in which the reliability of single-camera data increases by 2.4%,the double-camera data increases by 5.3%and the five-camera data increases by 24.3%.

关 键 词：影像匹配 无人机 连接点 倾斜影像 待匹配像对 

分 类 号：P237[天文地球—摄影测量与遥感]