基于图像匹配的无人机飞行质量评估方法  

A method of flight quality assessment based on image matching

作　　者：田金炎[1] 段福洲[1,2] 袁媛[3] 屈新原[1] 高明亮[1] 

机构地区：[1]首都师范大学资源环境与旅游学院,北京100048 [2]首都师范大学三维信息获取与应用教育部实验室,北京100048 [3]北京林业大学信息学院,北京100083

出　　处：《测绘科学》2013年第5期175-177,174,共4页Science of Surveying and Mapping

基　　金：青年科学基金(41101403);国家高技术研究发展计划(863计划)重点项目(2008AA121301)

摘　　要：我国对低空高分辨率遥感数据的客观需求促成了无人机遥感的发展,无人机飞行质量的评估是航空摄影测量的重要步骤之一。本文通过利用GPU加速SIFT算法进行无人机影像匹配,使用RANSAC剔除粗匹配点,根据匹配参数计算影像旋转角、轨迹重叠度、航向重叠度、旁向重叠度、航带弯曲度,对无人机飞行质量进行评估,并建立了一套完整的无人机飞行质量评估系统。Since the fast development of UAV remote sensing provides low-ahitude high-resolution remote sensing data which is in great need in China, the flight quality assessment becomes a most important procedure of aerial photogrammetry. This thesis introduced a flight quality assessment method with SIFT algorithm accelerated by GPU. It used RANSAC to remove coarse matching points, and calculated image rotation angle, trajectory overlap, course overlap, adjacent to the overlap according to the matching parameters, in or- der to assess the quality of the UAV flight. In the end, it established a complete quality assessment system for flight.

关 键 词：SIFT 飞行质量评估 图像匹配 无人机 

分 类 号：P231[天文地球—摄影测量与遥感]