[1]董蕊芳,柳长安,杨国田,等.基于图优化的单目线特征SLAM算法[J].东南大学学报(自然科学版),2017,47(6):1094-1100.[doi:10.3969/j.issn.1001-0505.2017.06.003]
 Dong Ruifang,Liu Changan,Yang Guotian,et al.Line-based monocular graph SLAM algorithm[J].Journal of Southeast University (Natural Science Edition),2017,47(6):1094-1100.[doi:10.3969/j.issn.1001-0505.2017.06.003]
点击复制

基于图优化的单目线特征SLAM算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
47
期数:
2017年第6期
页码:
1094-1100
栏目:
自动化
出版日期:
2017-11-20

文章信息/Info

Title:
Line-based monocular graph SLAM algorithm
作者:
董蕊芳柳长安杨国田程瑞营
华北电力大学控制与计算机工程学院, 北京 102206
Author(s):
Dong Ruifang Liu Changan Yang Guotian Cheng Ruiying
School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
关键词:
单目SLAM 线特征 图优化 Plücker坐标 Cayley直线
Keywords:
monocular slam line feature graph optimization Plücker coordinates Cayley representation
分类号:
TP242
DOI:
10.3969/j.issn.1001-0505.2017.06.003
摘要:
提出了基于图优化的单目线特征同时定位和地图构建(SLAM)的方法.首先,针对主流视觉SLAM算法因采用点作为特征而导致构建的点云地图稀疏、难以准确表达环境结构信息等缺点,采用直线作为特征来构建地图.然后,根据现有线特征的SLAM算法都是基于滤波器的SLAM框架、存在线性化及更新效率的问题,采用基于图优化的SLAM解决方案以提高定位精度及地图构建的一致性和准确性.将线特征的Plücker坐标和Cayley参数化方式相结合,一方面采用Plücker坐标便于线性投影计算,另一方面采用Cayley参数化方式有利于线特征参数的非线性优化.仿真实验结果显示:所提出算法的位姿估计误差平方和与均方根误差分别是里程计位姿估计的2.5%和10.5%,是基于EKF线特征SLAM算法估计位姿误差的22.4%和33%,重投影误差仅为45.5像素;实际图像实验中的位姿估计误差平方和为958 cm2,均方根误差为3.9 413 cm,从而证明了所提出算法的有效性和准确性.
Abstract:
A new line based 6-DOF monocular algorithm for using graph simultaneous localization and mapping(SLAM)algoritm was proposed. First, the straight line were applied as a feature instead of points, due to a map consisting of a sparse set of 3D points is unable to describe the structure of the surrounding world. Secondly,most of previous line-based SLAM algorithms were focused on filtering-based solutions suffering from the inconsistent when applied to the inherently non-linear SLAM problem, in contrast, the graph-based solution was used to improve the accuracy of the localization and the consistency of mapping. Thirdly, a special line representation was exploited for combining the Plücker coordinates with the Cayley representation. The Plücker coordinates were used for the 3D line projection function, and the Cayley representation helps to update the line parameters during the non-linear optimization process. Finally, the simulation experiment shows that the proposed algorithm outperforms odometry and EKF-based SLAM in terms of the pose estimation, while the sum of the squared errors(SSE)and root-mean-square error(RMSE)of proposed method are 2.5% and 10.5% of odometry, and 22.4% and 33% of EKF-based SLAM. The reprojection error is only 45.5 pixels. The real image experiment shows that the proposed algorithm obtains only 958 cm2 and 3.941 3 cm the SSE and RMSE of pose estimation. Therefore, it can be concluded that the proposed algorithm is effective and accuracy.

参考文献/References:

[1] Cadena C, Carlone L, Carrillo H, et al. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age [J]. IEEE Transactions on Robotics, 2016, 32(6):1309-1332.DOI:10.1109/TRO.2016.2624754.
[2] 段华旭,闫飞,庄严,等.无人车基于双目视觉的同时定位与地图构建[J].华中科技大学学报(自然科学版),2015,43(z1):319-323. DOI:10.13245/j.hust.15S1076.
Duan Huaxu, Yan Fei, Zhuang Yan, et al. Simultaneous localization and mapping for ugvs with binocular camera[J].Journal of Huazhong University of Science and Technology(Nature Science Edition), 2015, 43(z1): 319-323. DOI:10.13245/j.hust.15S1076. (in Chinese)
[3] 刘浩敏,章国锋,鲍虎军.基于单目视觉的同时定位与地图构建方法综述 [J].计算机辅助设计与图形学学报,2016,28(6):855-868. DOI:10.3969/j.issn.1003-9775.2016.06.001.
Liu Haomin, Zhang Guofeng, Bao Hujun. A survey of monocular simultaneous localization and mapping [J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28(6): 855-868. DOI:10.3969/j.issn.1003-9775.2016.06.001. (in Chinese)
[4] 周慧中.基于结构线条的视觉 SLAM 方法[D].上海:上海交通大学电子信息与电气工程学院,2015.
[5] Zhao L, Huang S, Yan L, et al. A new feature parametrization for monocular SLAM using line features [J]. Robotica, 2015, 33(3):513-536.DOI:10.1017/S026357471400040X.
[6] Esparza-Jiménez O, Devy M, Gordillo J L. Visual EKF-SLAM from heterogeneous landmarks [J]. Sensors, 2016, 16(4): 489.
[7] Roberts K S. A new representation for a line [C]//Computer Society Conference on proceedings of the Computer Vision and Pattern Recognition. Ann Arbor, MI, USA, 1988:635-640.
[8] Ohwovoriole M S, Roth B. An extension of screw theory [J]. Journal of Mechanical Design, 1981, 103(4):725-735. DOI:10.1115/1.3254979.
[9] Zhang L, Koch R. Structure and motion from line correspondences: Representation, projection, initialization and sparse bundle adjustment [J]. Journal of Visual Communication and Image Representation, 2014, 25(5): 904-915. DOI:10.1016/j.jvcir.2014.02.013.
[10] Smith P, Reid D, Davison A. Real-time monocular SLAM with straight lines [C]//Proceedings of the BMVC. Edinburgh, UK, 2006:17-26. DOI:10.5244/c.20.3.
[11] Gee A P, Mayol-Cuevas W. Real-time model-based SLAM using line segments [C]//Proceedings of the International Symposium on Visual Computing. Berlin, Heidelberg: Springer, 2006:354-363. DOI:10.1007/11919629_37.
[12] Montiel J M M,Tardós D, Montano L. Structure and motion from straight line segments [J]. Pattern Recognition, 2000, 33(8):1295-1307. DOI:10.1016/s0031-3203(99)00117-x.
[13] Sola J, Vidal-Calleja T, Civera J, et al. Impact of landmark parametrization on monocular EKF-SLAM with points and lines [J]. InternationalJournal of Computer Vision, 2012, 97(3):339-368.
[14] Lemaire T, Lacroix S. Monocular-vision based SLAM using line segments [C]//Proceedings of the Proceedings 2007 IEEE International Conference on Robotics and Automation. Roma,Italy, 2007:2791-2796. DOI:10.1109/robot.2007.363894.
[15] 梁明杰,闵华清,罗荣华.基于图优化的同时定位与地图创建综述[J].机器人,2013,35(4):500-512. DOI:10.3724/SP.J.1218.2013.00500.
Liang Mingjie, Min Huaqing, Luo Ronghua. Graph-based SLAM: A survey [J]. Robot, 2013, 35(4): 500-512. DOI:10.3724/SP.J.1218.2013.00500. (in Chinese)
[16] Lourakis M I A, Argyros A A. SBA: A software package for generic sparse bundle adjustment [J]. ACM Transactions on Mathematical Software(TOMS), 2009, 36(1):2-1-2-30.
[17] Sola J, Vidal-Calleja T, Devy M. Undelayed initialization of line segments in monocular SLAM [C]//Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. Louis, USA,2009: 1553-1558. DOI:10.1109/iros.2009.5354754.
[18] Civera J, Davison A J, Montiel J M. Inverse depth parametrization for monocular SLAM [J]. IEEE Transactions on Robotics, 2008, 24(5): 932-945. DOI:10.1109/tro.2008.2003276.
[19] Triggs B, Mclauchlan P F, Hartley R I, et al. Bundle adjustment—A modern synthesis [C]//Proceedings of the International Workshop on Vision Algorithms. London, UK: Springer Springer-Verlag, 2000:298-372.
[20] Ranganathan A. The levenberg-marquardt algorithm [J]. Tutoral on Lm Algorithm, 2013, 11(1):101-110.
[21] Solà J. Slam toolbox for matlab[EB/OL].(2015-12)[2017-08].http://www.iri.upc.edu/people/jsola/JoanSola/eng/toolbox.html.
[22] von Gioi R G, Jakubowicz J, Morel J-M, et al. LSD: A line segment detector [J]. Image Processing on Line, 2012, 2:35-55. DOI:10.5201/ipol.2012.gjmr-lsd.
[23] Zhang L, Koch R. An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency [J]. Journal of Visual Communication and Image Representation,2013, 24(7):794-805.DOI:10.1016/j.jvcir.2013.05.006.

备注/Memo

备注/Memo:
收稿日期: 2017-07-23.
作者简介: 董蕊芳(1989—),女,博士生;柳长安(联系人),男,博士,教授,博士生导师,liuchangan@ncepu.edu.cn.
基金项目: 国家自然科学基金资助项目(61105083)、中央高校基本科研业务费专项资金资助项目(2015XS63).
引用本文: 董蕊芳,柳长安,杨国田,等. 基于图优化的单目线特征SLAM算法[J].东南大学学报(自然科学版),2017,47(6):1094-1100. DOI:10.3969/j.issn.1001-0505.2017.06.003.
更新日期/Last Update: 2017-11-20