3D Reconstruction of UAV Sequence Image Based on Motion Structure Graph

doi:10.16182/j.issn1004731x.joss.18-0779

Abstract

Abstract: UAV sequence image has the characteristics of high overlap and strong topological connection. Aiming at the inefficient and unstable in processing the large-scale UAV images of the existing incremental 3D reconstruction algorithm, a 3D reconstruction method based on motion structure graph is proposed. The image matching index is established by using the geolocation information and IMU data to improve the image matching efficiency, and the random motion consistency algorithm is used to calculate the relative motion; motion structure graph is used to represent the "association" between images, and closed-loop detection algorithm is used to eliminate the false edges. Under the mapping relationship between Lie algebra and Lie group, the global motion of the image is solved at one time by 1 L paradigm and M estimation, and the beam adjustment is used only once. Experiments show that the proposed algorithm improves the efficiency and reconstruction result.

Key words: three-dimensional reconstruction, geographic location information, IMU data, motion structure graph, Lie algebra average

CLC Number:

TP391.9

Wu Yuhao, Cao Xuefeng, Peng Jinchao, Xu Lianrui. 3D Reconstruction of UAV Sequence Image Based on Motion Structure Graph[J]. Journal of System Simulation, 2020, 32(6): 1094-1102.

References

[1] Sujit P B, Sousa J, Pereira F L. UAV and AUVs coordination for ocean exploration[C]//Oceans 2009-Europe. IEEE, 2009: 1-7.
[2] Xu Z, Yang J, Peng C, et al. Development of an UAS for post-earthquake disaster surveying and its application in Ms7.0 Lushan Earthquake, Sichuan, China[J]. Computers & Geosciences (S0098-3004), 2014, 68: 22-30.
[3] Watts A C, Ambrosia V G, Hinkley E A. Unmanned aircraft systems in remote sensing and scientific research: Classification and considerations of use[J]. Remote Sensing (S2072-4292), 2012, 4(6): 1671-1692.
[4] Moulon P, Monasse P, Perrot R, et al. OpenMVG: Open multiple view geometry[C]. International Workshop on Reproducible Research in Pattern Recognition. Springer: Cham, 2016: 60-74.
[5] Mur-Artal R, Tardós J D. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE Transactions on Robotics (S1552-3098), 2017, 33(5): 1255-1262.
[6] Zhu Y, Mottaghi R, Kolve E, et al. Target-driven visual navigation in indoor scenes using deep reinforcement learning[C]//2017 IEEE international conference on robotics and automation (ICRA). IEEE, 2017: 3357-3364.
[7] Snavely N, Seitz S M, Szeliski R. Photo tourism: exploring photo collections in 3D[M]//ACM Siggraph 2006 Papers. 2006: 835-846.
[8] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision (S0920-5691), 2004, 60(2): 91-110.
[9] Cui H, Gao X, Shen S, et al. HSfM: Hybrid structure-from-motion[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 1212-1221.
[10] Havlena M, Torii A, Pajdla T. Efficient structure from motion by graph optimization[C]//European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2010: 100-113.
[11] Hinzmann T, Schönberger J L, Pollefeys M, et al. Mapping on the fly: real-time 3D dense reconstruction, digital surface map and incremental orthomosaic generation for unmanned aerial vehicles[C]//Field and Service Robotics. Springer, Cham, 2018: 383-396.
[12] 许志华, 吴立新, 刘军, 等. 顾及影像拓扑的SfM 算法改进及其在灾场三维重建中的应用[J]. 武汉大学学报(信息科学版), 2015, 40(5): 599-606.
Xu Zhihua, Wu Lixin, Liu Jun, et al. Improvement of SfM algorithm considering image topology and its application in 3D reconstruction of disaster field[J]. Journal of Wuhan University (Information Science Edition), 2015, 40(5): 599-606.
[13] 沈永林, 刘军, 吴立新, 等. 基于无人机影像和飞控数据的灾场重建方法研究[J]. 地理与地理信息科学, 2011, 27(6): 13-17.
Shen Yonglin, Liu Jun, Wu Lixin, et al. Research on disaster site reconstruction method based on UAV image and flight control data [J]. Geographic and Geographic Information Science, 2011, 27(6): 13-17.
[14] Furukawa Y, Ponce J. Dense 3D Motion Capture from Synchronized Video Streams[M]. Springer Berlin Heidelberg: Image and Geometry Processing for 3-D Cinematography, 2010: 1-8.
[15] 刘军, 张永生, 王冬红, 等. PO SAV510-DG 系统外方位元素的计算方法[J]. 测绘技术装备, 2004, 6(4): 6-9.
Liu Jun, Zhang Yongsheng, Wang Donghong, et al. Calculation Method of Outer Orientation Elements in PO SAV510-DG System[J]. Surveying and Mapping Technique, 2004, 6(4): 6-9.
[16] 鲁珊, 雷英杰, 孔韦韦, 等. 基于概率抽样一致性的基础矩阵估计算法[J]. 控制与决策, 2012, 27(3): 425-430.
Lu Shan, Lei Yingjie, Kong Weiwei, et al. Basic matrix estimation algorithm based on probability sampling consistency[J]. Control and Decision, 2012, 27(3): 425-430.
[17] Hall B. Lie groups, Lie algebras, and representations: an elementary introduction[M]. Springer, 2015.
[18] Fletcher P T, Lu C, Joshi S. Statistics of shape via principal geodesic analysis on Lie groups[C]//2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. IEEE, 2003, 1: I-I.
[19] Hartley R, Aftab K, Trumpf J. L1 rotation averaging using the Weiszfeld algorithm[C]//CVPR 2011. IEEE, 2011: 3041-3048.
[20] Hampel F R, Ronchetti E M, Rousseeuw P J, et al. Robust statistics: the approach based on influence functions[M]. John Wiley & Sons, 2011.