无序无人机影像的并行化SfM三维重建方法  

Parallel SfM-based 3D reconstruction for unordered UAV images

作　　者：姜三 马一尘 李清泉 江万寿[4] 郭丙轩[4] 王力哲 JIANG San;MA Yichen;LI Qingquan;JIANG Wanshou;GUO Bingxuan;WANG Lizhe(School of Com puter Science,China University of Geosciences,Wuhan 430074,China;Guangdong Laboratory of Artificial Intelligence and Digital Economy(Shenzhen),Shenzhen 518060,China;Hubei Luojia Laboratory,Wuhan 430072,China;State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China)

机构地区：[1]中国地质大学(武汉)计算机学院,湖北武汉430074 [2]人工智能与数字经济广东省实验室(深圳),广东深圳518060 [3]湖北珞珈实验室,湖北武汉430072 [4]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079

出　　处：《测绘学报》2024年第5期946-958,共13页Acta Geodaetica et Cartographica Sinica

基　　金：国家自然科学基金(42371442);湖北省自然科学基金(2023AFB568);人工智能与数字经济广东省实验室(深圳)开放课题(GML-KF-22-08);湖北珞珈实验室开放基金(230100013)。

摘　　要：增量式运动恢复结构(ISfM)已成为无人机影像三维重建的关键技术。然而,大数据量、大重叠度和高分辨率的无序无人机影像导致的匹配对检索代价大、迭代优化误差累积和效率低的问题,使其难以满足大场景ISfM处理需求。本文提出联合全局描述子和图索引的无人机影像并行化SfM方法。针对影像特征数量大、影像检索编码本尺寸增加导致的匹配对检索效率低的问题,设计了联合全局描述子和图索引的高效影像检索方法,从而加速影像匹配。针对分块并行化SfM子场景合并存在同名点搜索效率低、内存消耗大、合并解算精度低的问题,设计了基于按需匹配图和双向重投影误差的子场景合并方法,实现无人机影像的并行化SfM重建。利用不同场景、不同采集方式获取的真实无人机影像进行试验,结果表明本文方法能够实现36~108倍加速比的匹配对检索,ISfM重建效率达到30倍加速,且相对定向和绝对定向精度与传统方法相当。Efficient incremental structure from motion(ISfM)has become the core technique for(unmanned aerial vehicle,UAV)image orientation.However,the characteristics of large volume,high overlap,and high resolution cause the deficiency in match pair retrieval and the accumulated error and low efficiency in bundle adjustment(BA)optimization,which degenerate its performance for large-scale scenes.This study proposes a parallel SfM for UAV images via global descriptors and graph-based indexing.On the one hand,to cope with the deficiency caused by a large number of local descriptors and the large size of a codebook,an efficient match pair retrieval is designed via the global descriptor and graph-based indexing,which could dramatically accelerate feature matching;on the other hand,to address the deficiency of correspondence searching and low accuracy of transformation estimation in parallel SfM,this study designs an efficient cluster merging algorithm based on the on-demand correspondence graph and bi-directional reprojection error,which achieves efficient and accurate parallel SfM.The proposed algorithm is verified by using three UAV datasets,and the experimental results demonstrate that the proposed method can increase match pair retrieval with speedup ratios ranging from 36 to 108,and dramatically improves the SfM efficiency with the speedup ratio better than 30 and with the comparative accuracy.The accuracy of relative and absolute orientation is comparative to that of traditional methods.

关 键 词：数字摄影测量 无人机遥感 运动恢复结构 影像检索 

分 类 号：P231[天文地球—摄影测量与遥感]