尹双双,邓非

• 1:武汉大学

摘要(Abstract)：

针对传统方法难以直接用大规模测量范围的移动球形全景影像较好地实现三维重建的问题,该文提出基于GPS改进的三维重建方法。采用增量式运动恢复结构算法,基于GPS改进了影像匹配,场景初始化和光束法调整等主要步骤,较好地加快了影像匹配速度,实现大规模影像数据集的EG图的有效构建;减少了两两匹配的误差对初始位姿估计的影响,实现更快更好的模型重建;采用基于GPS位置信息加权的光束法调整优化影像位姿和场景模型,实现三维重建尺度的准确恢复。实验结果表明,本文方法不仅有效地解决了传统增量式运动恢复结构算法在大规模重建过程中丢失影像的问题,还显著地提高了位姿估计效率,并且合理地优化了场景重建效果。

关键词(KeyWords)： 移动测量;全景影像;球形相机;GPS;SFM

Abstract:

Keywords:

基金项目(Foundation): 国土资源部城市土地资源监测与仿真重点实验室开放基金项目(KF-2018-03-025)

作者(Author): 尹双双,邓非

DOI: 10.16251/j.cnki.1009-2307.2020.05.003

参考文献(References)：

• [1] ANGUELOV D,DULONG C,FILIP D,et al.Google street view:capturing the world at street level[J].Computer,2010,43(6):32-38.
• [2] 罗莹,宋利,解蓉,等.全景媒体的系统架构研究综述[J].电信科学,2018(2):88-98.(LUO Ying,SONG Li,XIE Rong,et al.Review of system architecture of omnidirectional media[J].Telecommunications Science,2018(2):88-98.)
• [3] JIANG P,WEI Q,CHEN Y.Real-time panoramic system for underwater cleaning robot[C]//IEEE 9th International Conference on Mechanical and Intelligent Manufacturing Technologies (ICMIMT).Cape town:IEEE,2018:155-159.
• [4] 谢东海,钟若飞,吴俣,等.球面全景影像相对定向与精度验证[J].测绘学报,2017,46(11):1822-1829.(XIE Donghai,ZHONG Ruofei,WU Yu,et al.Relative pose estimation and accuracy verification of spherical panoramic image[J].Acta Geodaetica et Cartographica Sinica,2017,46(11):1822-1829.)
• [5] 薛武,张永生,赵玲,等.增量式SFM 与 POS辅助光束法平差精度比较[J].测绘学报,2017,46(2):198-207.(XUE Wu,ZHANG Yongsheng,ZHAO Ling,et al.Compare the accuracy of incremental SFM with POS-aided bundle adjustment[J].Acta Geodaetica et Cartographica Sinica,2017,46(2):198-207.)
• [6] 陈驰,杨必胜,田茂,等.车载MMS激光点云与序列全景影像自动配准方法[J].测绘学报,2018,47(2):215-224.(CHENG Chi,YANG Bisheng,TIAN Mao,et al.Automatic registration of vehicle-borne mobile mapping laser point cloud and sequent panoramas[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):215-224.)
• [7] SNAVELY N,SEITZ S M,SZELISKI R.Photo tourism:exploring photo collections in 3d[J].ACM Trans.on Graph,2006,25(3):835-846.
• [8] MOULON P,MONASSE P,MARLET R.Adaptive structure from motion with a contrario model estimation[C]//Computer Vision-ACCV 2012.Berlin:Springer,2013:257-270.
• [9] GOVINDU V M.Lie-algebraic averaging for globally consistent motion estimation[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition.Washington:IEEE,2004.
• [10] MOULON P,MONASSE P,MARLET R.Global Fusion of Relative Motions for Robust,Accurate and Scalable Structure from Motion[C]//IEEE International Conference on Computer Vision(ICCV).Sydney:IEEE,2013.
• [11] CORNELIS K,VERBIEST F,VAN G L.Drift detection and removal for sequential structure from motion algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(10):1249-1259.
• [12] 何鼎乾.全景图像获取和显示技术研究[D].郑州:信息工程大学,2013.(HE Dingqian.Research on technology of Panorama acquisition and display[D].Zhengzhou:Information Engineering University,2013.)
• [13] 吴幼丝.球形全景影像位姿估计[D].武汉:武汉大学,2017:12-13.(WU Yousi.Position and orientation estimation of spherical panorama image[D].Wuhan:Wuhan University,2017:12-13.)
• [14] NISTER D.An efficient solution to the five-point relative pose problem[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(6):756-770.
• [15] PAGANI A,STRICKER D.Structure from Motion using full spherical panoramic cameras[C]//IEEE International Conference on Computer Vision Workshops.Barcelona:IEEE,2011:375-382.
• [16] SCH?NBERGER J L,FRAHM J M.Structure-from-motion revisited[C]//IEEE Conference on Computer Vision & Pattern Recognition.Las Vegas:IEEE,2016:4104-4113.
• [17] CHATTERJEE A,GOVINDU V M.Efficient and robust large-scale rotation averaging[C]//IEEE International Conference on Computer Vision.Sydney:IEEE,2013:521-528.
• [18] CUI Z,TAN P.Global structure-from-motion by similarity averaging[C]//IEEE International Conference on Computer Vision.Santiago:IEEE,2015:864-872.
• [19] OZYESILAND O A.Robust camera location estimation by convex programming[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston:IEEE,2015:2674-2683.
• [20] HARALICK R M,JOO H,LEE C N,et al.Pose estimation from corresponding point data[J].IEEE Transactions on Systems,Man,and Cybernetics,1989,19(6):1426-1446.
• [21] ANSAR A,DANIILIDIS K.Linear pose estimation from points or lines[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):578-589.
• [22] HESCH J A,ROUMELIOTIS S I.A direct least-squares (DLS) method for PnP[C]//International Conference on Computer Vision(ICCV).Barcelona:IEEE,2011:383-390.
• [23] KE T,ROUMELIOTIS S I.An efficient algebraic solution to the perspective-three-point problem[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu:IEEE,2017:4618-4626.
• [24] MOISAN L,MOULON P,MONASSE P.Automatic homographic registration of a pair of images,with a contrario elimination of outliers[J].Image Processing on Line,2012,2:329-352.
• [25] TRIGGS B.Bundle adjustment-a modern synthesis[M]//Vision Algorithms:Theory and Practice.Berlin Heidelberg:Springer,1999:298-372.