计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (7): 152-159.doi: 10.11896/jsjkx.220400166

• 计算机图形学&多媒体 • 上一篇    下一篇

基于相机朝向变化的增量式位姿图分段算法

范涵奇, 王劭靖   

  1. 北方工业大学信息学院 北京 100144
  • 收稿日期:2022-04-16 修回日期:2022-10-11 出版日期:2023-07-15 发布日期:2023-07-05
  • 通讯作者: 王劭靖(494046824@qq.com)
  • 作者简介:(fhq@ncut.edu.cn)
  • 基金资助:
    国家重点研发计划(2020YFC0811004)

Incremental Pose Graph Segmentation Algorithm Based on Camera Orientation Change

FAN Hanqi, WANG Shaojing   

  1. School of Information,North China University of Technology,Beijing 100144,China
  • Received:2022-04-16 Revised:2022-10-11 Online:2023-07-15 Published:2023-07-05
  • About author:FAN Hanqi,born in 1983,Ph.D,asso-ciate professor.His main research inte-rests include computer vision and visual simultaneous localization and mapping.WANG Shaojing,born in 1995,master.His main research interest is visual simultaneous localization and mapping.
  • Supported by:
    National Key Research and Development Program of China(2020YFC0811004).

PDF (PC)

278

摘要： 位姿图优化是估计相机轨迹过程中减少累积误差的重要方法,但随着相机的不断运动,位姿图的规模会不断增大导致优化速度下降,使得轨迹估计难以应用于AR/VR(Augmented Reality/Virtual Reality)等实时性要求较高的领域。针对此问题,文中提出了一种基于相机朝向变化的增量式位姿图分段算法。所提算法能够将位姿图在相机发生朝向变化较大的时刻进行分段,从而只对这些朝向变化较大的相机进行位姿图优化,以有效减小位姿图优化的规模,提高优化速度。针对其余未进行位姿图优化的每个相机,分别将其所在轨迹段的起始相机和终止相机作为参考相机,将根据不同参考相机估计出的不同位姿进行加权平均,从而求解出相机的最终位姿,既避免了非线性优化的大量计算,又降低了噪声的影响,达到了较高的精度。在EuRoC,TUM和KITTI数据集上进行了实验,结果表明,所提算法在减小位姿图优化规模的基础上保证了相机轨迹的精度。

关键词: 位姿图, 相机朝向, 轨迹分段, 加权平均, 增量式

Abstract: In camera trajectory estimation,pose graph is one of the most widely used tools to reduce the cumulative error.How-ever,the scale of the pose graph grows as the cameras move,which would render trajectory estimation impossible in the real-time required applications like AR/VR(augmented reality/virtual reality).To reduce the size of the pose graph optimization,this paper proposes an algorithm that segments the trajectory of cameras incrementally by the change of orientation.The orientation changes significantly where the trajectory is segmented by the proposed algorithm.Efficiency is improved by optimizing the cameras with obvious orientation changes instead of the entire trajectory.In addition,the starting camera and the ending camera of the trajectory segment are utilized as references to estimate different poses for each camera within the trajectory segment,followed by the weighted average method is used on its different poses to solve the final pose.Which not only avoids a large amount of computation of nonlinear optimization,but also reduces the influence of noise to achieve high accuracy.Experiments on EuRoC,TUM,and KITTI datasets show that the proposed scheme reduces the size of the pose graph optimization and ensures the accuracy of trajectory.

Key words: Pose graph, Camera orientation, Trajectory segmentation, Weighted average, Incremental

中图分类号: 

  • TP242
[1]MOREIRA G,MARQUES M,COSTEIRA J P.Fast pose graph optimization via Krylov-Schur and Cholesky factorization[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.IEEE,2021:1898-1906.
[2]TIAN Y,CHEN H W,WANG F S,et al.Overview of SLAM Algorithms for Mobile Robot [J].Computer Science,2021,48(9):223-234.
[3]FAN H Q,ZHANG S.Camera Localization and Map Reconstruction Algorithm Based on Temporal-Spatial Consistency[J].Robot,2019,41(1):40-49.
[4]WANG D,SHI C X,WANG Y Q.Loop Closure DetectionMethod Based on Unsupervised Deep Learning[J].Computer Science,2020,47(10):228-232.
[5]ENGEL J,KOLTUN V,CREMERS D.Direct sparse odometry[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(3):611-625.
[6]FORSTER C,PIZZOLI M,SCARAMUZZA D.SVO:Fast semi-direct monocular visual odometry[C]//2014 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2014:15-22.
[7]MUR-ARTAL R,TARDÓS J D.Orb-slam2:An open-sourceslam system for monocular,stereo,and rgb-d cameras[J].IEEE Transactions on Robotics,2017,33(5):1255-1262.
[8]SUMIKURA S,SHIBUYA M,SAKURADA K.OpenVSLAM:A versatile visual SLAM framework[C]//Proceedings of the 27th ACM International Conference on Multimedia.ACM,2019:2292-2295.
[9]LI X.Robust 6-DOF Camera Relocalization in Multi-view Structure from Motion[D].Philadelphia:Temple University.2021.
[10]LI X,YUAN L,LATECKI L J,et al.Pushing the Envelope of Rotation Averaging for Visual SLAM[J].arXiv:2011.01163,2020.
[11]SCHLEGEL D,COLOSI M,GRISETTI G.Proslam:GraphSLAM from a programmer’s Perspective[C]//2018 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2018:3833-3840.
[12]ZENG T,SI B.A brain-inspired compact cognitive mapping system[J].Cognitive Neurodynamics,2021,15(1):91-101.
[13]LIU T,CHEN Y,JIN Z,et al.Spare Pose Graph Decomposition and Optimization for SLAM[C]//MATEC Web of Confe-rences.EDP Sciences,2019,256:05003.
[14]JOHANNSSON H,KAESS M,FALLON M,et al.Temporally scalable visual SLAM using a reduced pose graph[C]//2013 IEEE International Conference on Robotics and Automation.IEEE,2013:54-61.
[15]SCHMUCK P,CHLI M.On the redundancy detection in key-frame-based slam[C]//2019 International Conference on 3D Vision(3DV).IEEE,2019:594-603.
[16]LATIF Y,NEIRA J.Go straight,turn right:Pose graph reduction through trajectory segmentation using line segments[C]//2013 European Conference on Mobile Robots.IEEE,2013:144-149.
[17]ZHAO M,GUO X,SONG L,et al.A General Framework forLifelong Localization and Mapping in Changing Environment[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).IEEE,2021:3305-3312.
[18]DING W,HOU S,GAO H,et al.Lidar inertial odometry aided robust lidar localization system in changing city scenes[C]//2020 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2020:4322-4328.
[19]WANG Y,FUNK N,RAMEZANI M,et al.Elastic and efficient lidar reconstruction for large-scale exploration tasks[C]//2021 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2021:5035-5041.
[20]WANG C,LI J,HE Y,et al.Segmented trajectory clustering-based destination prediction in IoVs[J].IEEE Access,2020,(8):98999-99009.
[21]KEOGH E,CHU S,HART D,et al.An online algorithm for segmenting time series[C]//Proceedings 2001 IEEE International Conference on Data Mining.IEEE,2001:289-296.
[22]JANG Y,SHIN H,KIM H J.Pose correction algorithm for relative frames between keyframes in SLAM[C]//Proceedings of the Asian Conference on Computer Vision.2020.
[23]GEIGER A,LENZ P,STILLER C,et al.Vision meets robotics:The kitti dataset[J].The International Journal of Robotics Research,2013,32(11):1231-1237.
[24]BURRI M,NIKOLIC J,GOHL P,et al.The EuRoC micro aerial vehicle datasets[J].The International Journal of Robotics Research,2016,35(10):1157-1163.
[25]WANG S J.KITTI06 Experiment[EB/OL].(2022-03-08)[2022-04-16].https://youtu.be/-aZTWqphSvM.
[26]WANG S J.MH05 Experiment[EB/OL].(2022-03-08)[2022-04-16].https://youtu.be/RRQFTnmzLWw.
[27]SMITH R,SELF M,CHEESEMAN P.Estimating uncertainspatial relationships in robotics[M]//Autonomous robot vehicles.New York:Springer,1990:167-193.
[28]STURM J,ENGELHARD N,ENDRES F,et al.A benchmark for the evaluation of RGB-D SLAM systems[C]//2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.IEEE,2012:573-580.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发