PLP-SLAM:基于点、线、面特征融合的视觉SLAM方法

doi:10.13973/j.cnki.robot.2017.0214

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1473 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
李海丰, 胡遵河, 陈新伟. PLP-SLAM:基于点、线、面特征融合的视觉SLAM方法[J]. 机器人, 2017, 39(2): 214-220.DOI: 10.13973/j.cnki.robot.2017.0214. LI Haifeng, HU Zunhe, CHEN Xinwei. PLP-SLAM: A Visual SLAM Method Based on Point-Line-Plane Feature Fusion. ROBOT, 2017, 39(2): 214-220. DOI: 10.13973/j.cnki.robot.2017.0214.

摘要基于点特征的视觉SLAM（同时定位与地图构建）算法存在计算量大、环境存储空间负荷高、定位误差较大的问题，为此，提出了一种基于点、线段、平面特征融合的视觉SLAM算法—PLP-SLAM．在扩展卡尔曼滤波（EKF）框架下，首先利用点特征估计机器人当前位姿，然后构建了基于点、线、平面特征的观测模型，最后建立了带平面约束的线段特征数据关联方法及系统状态更新模型，并利用线段和平面特征描述环境信息．在公开数据集上进行了实验，结果表明，本文PLP-SLAM算法能够成功完成SLAM任务，平均定位误差为2.3 m，优于基于点特征的SLAM方法，并通过基于不同特征的SLAM实验表明了本文提出的点、线、面特征融合的优越性．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李海丰
	胡遵河
	陈新伟

关键词 ：同时定位与地图构建, 点线面特征融合, 扩展卡尔曼滤波, 线段特征, 平面特征

Abstract：To reduce the computation and memory cost, and improve the localization accuracy of point-based visual simultaneous localization and mapping (SLAM) methods, a novel visual SLAM algorithm, named PLP-SLAM, is proposed by fusing the point, line segment and plane features. Under the EKF (extended Kalman filter) framework, the current robot pose is estimated using the point features firstly. Then, the observation models of point, line segment and plane are set up. Finally, the data association of line segments and state-updating models with plane constraints are formulated, and the unknown environment is described by line segment and plane feature map. The experiments are carried out on a public dataset, and the results show that the proposed PLP-SLAM can accomplish the SLAM task with a mean localization error of 2.3 m, which is better than the point-based SLAM method. Furthermore, the SLAM experiment results with different feature combinations illustrate the superiority of the proposed point-line-plane feature fusion.

Key words： simultaneous localization and mapping point-line-plane feature fusion extended Kalman filter line segment feature plane feature

收稿日期: 2016-12-05 录用日期: 2017-02-18

TP242

基金资助:国家自然科学基金（61305107，U1333109）；天津市应用基础与前沿技术研究计划重点项目（14JCZDJC32500）；中央高校基本科研业务费（3122016B006）；福建省信息处理与智能控制重点实验室开放课题（MJUKF201732）；福建省科技厅引导性课题（2015H0031）

通讯作者: 陈新伟,chenxw_mju@126.com E-mail: chenxw_mju@126.com

作者简介: 李海丰(1984-),男,博士,讲师,硕士生导师.研究领域:计算机视觉,机器人导航.
胡遵河(1990-),男,硕士生.研究领域:移动机器人视觉SLAM.
陈新伟(1984-),男,博士,讲师.研究领域:智能机器人控制.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2017.0214 或 https://robot.sia.cn/CN/Y2017/V39/I2/214

[1] Fuentes-Pacheco J, Ruiz-Ascencio J, Manuel Rendon-Mancha J. Visual simultaneous localization and mapping:A survey[J]. Artificial Intelligence Review, 2012, 43(1):55-81.
[2] 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.Liang M J, Min H Q, Luo R H. Graph-based SLAM:A survey[J]. Robot, 2013, 35(4):500-512.
[3] 孙凤池,黄亚楼,康叶伟.基于视觉的移动机器人同时定位与建图研究进展[J].控制理论与应用,2010,27(4):488-494.Sun F C, Huang Y L, Kang Y W. Review on the achievements in simultaneous localization and mapping for mobile robot based on vision sensor[J]. Control Theory and Applications, 2010, 27(4):488-494.
[4] Tardif J P, Pavlidis Y, Daniilidis K. Monocular visual odometry in urban environments using an omnidirectional camera[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2008:2531-2538.
[5] Civera J, Grasa O G, Davison A J, et al. 1-point RANSAC for extended Kalman filtering:Application to real-time structure from motion and visual odometry[J]. Journal of Field Robotics, 2010, 27(5):609-631.
[6] Mullane J, Vo B N, Adams M D, et al. A random-finite-set approach to Bayesian SLAM[J]. IEEE Transactions on Robotics, 2011, 27(2):268-282.
[7] Adams M, Vo B N, Mahler R, et al. SLAM gets a PHD:New concepts in map estimation[J]. IEEE Robotics and Automation Magazine, 2014, 21(2):26-37.
[8] Klein G, Murray D. Parallel tracking and mapping for smallAR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2007:250-259.
[9] Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM:A versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163.
[10] Zhang G X, Kang D H, Suh I H. Loop closure through vanishing points in a line-based monocular SLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2012:4565-4570.
[11] Endres F, Hess J, Sturm J, et al. 3-D mapping with an RGB-D camera[J]. IEEE Transactions on Robotics, 2014, 30(1):177-187.
[12] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[13] 付梦印,吕宪伟,刘彤,等.基于RGB-D数据的实时SLAM算法[J].机器人,2015,37(6):683-692.Fu M Y, Lü X W, Liu T, et al. Real-time SLAM algorithm based on RGB-D data[J]. Robot, 2015, 37(6):683-692.
[14] Grompone von Gioi R, Jakubowicz J, Morel, J M, et al. LSD:A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4):722-732.
[15] Lemaire T, Lacroix S. Monocular-vision based SLAM using line segments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2007:2791-2796.
[16] Sola J, Vidal-Calleja T, Devy M. Undelayed initialization of line segments in monocular SLAM[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2009:1553-1558.
[17] 武涛,孙凤池,苑晶,等.一种基于线段特征的室内环境主动SLAM方法[J].机器人,2009,31(2):166-170,178.Wu T, Sun F C, Yuan J, et al. An active SLAM approach based on line segment feature in indoor environment[J]. Robot, 2009, 31(2):166-170,178.
[18] Zhang G X, Lee J H, Lim J W, et al. Building a 3-D line-based map using stereo SLAM[J]. IEEE Transactions on Robotics, 2015, 31(6):1364-1377.
[19] Gee A P, Chekhlov D, Calway A, et al. Discovering higher level structure in visual SLAM[J]. IEEE Transactions on Robotics, 2008, 24(5):980-990.
[20] Flint A, Mei C, Reid I, et al. Growing semantically meaningful models for visual SLAM[C]//IEEE Computer Society International Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2010:467-474.
[21] 王文斐,熊蓉,褚健.基于粒子滤波和点线相合的未知环境地图构建方法[J].自动化学报,2009,35(9):1185-1192. Wang W F, Xiong R, Chu J. A simultaneous localization and mapping approach by combining particle filter and dot-line congruence[ J]. Acta Automatica Sinica, 2009, 35(9):1185-1192.
[22] Tretyak E, Barinova O, Kohli P, et al. Geometric image parsing in man-made environments[J]. International Journal of Computer Vision, 2012, 97(3):305-321.
[23] Forster C, Pizzoli M, Scaramuzza D. SVO:Fast semi-direct monocular visual odometry[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014: 15-22.
[24] Engel J, Schöps T, Cremers D. LSD-SLAM:Large-scale direct monocular SLAM[C]//13th European Conference on Computer Vision. Berlin, Germany:Springer, 2014:834-849.
[25] Fan B,Wu F C, Hu Z Y. Robust line matching through line-point invariants[J]. Pattern Recognition, 2012, 45(2):794-805.
[26] Lu Y, Song D Z. Visual navigation using heterogeneous landmarks and unsupervised geometric constraints[J]. IEEE Transactions on Robotics, 2015, 31(3):736-749.