基于时空一致性的相机定位与地图重建算法

doi:10.13973/j.cnki.robot.180021

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1255 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
范涵奇, 张帅. 基于时空一致性的相机定位与地图重建算法[J]. 机器人, 2019, 41(1): 40-49,57.DOI: 10.13973/j.cnki.robot.180021. FAN Hanqi, ZHANG Shuai. Camera Localization and Map Reconstruction Algorithm Based on Temporal-Spatial Consistency. ROBOT, 2019, 41(1): 40-49,57. DOI: 10.13973/j.cnki.robot.180021.

摘要为了提高SLAM（同时定位与地图构建）的精确性，提出一种基于时空一致性的单目相机SLAM算法.稳定的特征点具有以下2个特性：一是出现在连续的多帧图像中；二是能够被多个不同视角的相机观察到.本文分别使用时间一致性和空间一致性（简称时空一致性）描述上述2个特征.利用时间一致性的策略确定插入关键帧的时机，利用空间一致性的策略严格筛选3维点云.在KITTI数据集中，本文与ORB-SLAM（基于ORB特征的SLAM系统）算法相比较，本文方法需要选取的关键帧数量更少，使得局部优化线程中关键帧位姿能够得到更加充分的优化，处理速度可达35帧/秒，能够满足实时性要求.实验表明本文方法能够有效地降低误差，提高SLAM的精确性.

	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

关键词 ：时间一致性, 空间一致性, 稳定特征点, SLAM

Abstract：In order to improve the accuracy of SLAM (simultaneous localization and mapping), a monocular SLAM method is proposed based on temporal-spatial consistency. Stable feature points usually possess the following two characters, that they appear in multiple continuous frames, and can be observed by cameras from different viewpoints. In this paper, these two characters are described by temporal consistency and spatial consistency, that is temporal-spatial consistency in short. The temporal consistency decides the timing of keyframe insertion, and the spatial consistency filters the 3D points strictly. On the KITTI dataset, the proposed method is compared with the ORB-SLAM (SLAM system based on oriented FAST and rotated BRIEF features) algorithm. Fewer keyframes need to be selected, so the keyframe poses are optimized more completely in the local optimization thread, and the processing speed is up to 35frames/s to meet the real-time performance requirements. Experiments show that the proposed method can effectively reduce errors and improve the accuracy of SLAM.

Key words： temporal consistency spatial consistency stable feature SLAM (simultaneous localization and mapping)

收稿日期: 2018-01-09 录用日期: 2018-05-25

ZTFLH:

TP242

通讯作者: 张帅,tuszhangs@163.com E-mail: tuszhangs@163.com

作者简介: 范涵奇(1983-),男,博士,副教授.研究领域:计算机图形学,计算机视觉
张帅(1990-),男,硕士.研究领域:视觉SLAM.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.180021 或 https://robot.sia.cn/CN/Y2019/V41/I1/40

[1] Cadena C, Carlone L, Carrillo H, et al. Past, present, and future of simultaneous localization and mapping:Towards the robust-perception age[J]. IEEE Transactions on Robotics, 2016, 32(6):1309-1332.
[2] Younes G, Asmar D, Shammas E, et al. Keyframe-based monocular SLAM:Design, survey, and future directions[J]. Robotics and Autonomous Systems, 2016, 98:67-88.
[3] 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.
[4] Davison A J, Reid I D, Molton N D, et al. MonoSLAM:Real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):1052-1067.
[5] Nguyen T, Mann G K I, Vardy A, et al. Developing a cubature multi-state constraint Kalman filter for visual-inertial navigation system[C]//14th Conference on Computer and Robot Vision. Piscataway, USA:IEEE, 2017:321-328.
[6] Klein G, Murray D. Parallel tracking and mapping for smallAR workspaces[C]//IEEE/ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2007:10pp.
[7] 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.
[8] Lim H, Lim J, Kim H J. Real-time 6-DOF monocular visualSLAM in a large-scale environment[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014:1532-1539.
[9] 刘浩敏,章国锋,鲍虎军.面向大尺度场景的单目同时定位与地图构建[J].中国科学:信息科学,2016,46(12):1748-1761.Liu H M, Zhang G L, Bao H J. A survey of monocular simultaneous localization and mapping[J]. Scientia Sinica:Informtionis, 2016, 46(12):1748-1761.
[10] Strasdat H, Montiel J M M, Davison A J. Visual SLAM:Why filter?[J]. Image and Vision Computing, 2012, 30(2):65-77.
[11] Engel J, Sturm J, Cremers D. Semi-dense visual odometry for a monocular camera[C]//International Conference on Computer Vision. Piscataway, USA:IEEE, 2013:1449-1456.
[12] Newcombe R A, Lovegrove S J, Davison A J. DTAM:Dense tracking and mapping in real-time[C]//International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2320-2327.
[13] 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.
[14] Engel J, Schops T, Cremers D. LSD-SLAM:Large-scale direct monocular SLAM[C]//European Conference on Computer Vision. Berlin, Germany:Springer-Verlag, 2014:834-849.
[15] Tan W, Liu H, Dong Z, et al. Robust monocular SLAM in dynamic environments[C]//IEEE International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2013:209-218.
[16] Mur-Artal R, Tardos 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.
[17] Nister D, Naroditsky O, Bergen J. Visual odometry[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2004:652-659.
[18] Cvišic I, Petrovic I. Stereo odometry based on careful feature selection and tracking[C]//European Conference on Mobile Robots. Piscataway, USA:IEEE, 2015. DOI:10.1109/ECMR. 2015.7324219.
[19] Badino H, Yamamoto A, Kanade T. Visual odometry by multi-frame feature integration[C]//IEEE International Conference on Computer Vision Workshops. Piscataway, USA:IEEE, 2013:222-229.
[20] Paul M K, Wu K, Hesch J A, et al. A comparative analysis of tightly-coupled monocular, binocular, and stereo VINS[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2017:165-172.
[21] Lepetit V, Moreno-Noguer F, Fua P. EPnP:An accurate O(n) solution to the PnP problem[J]. International Journal of Computer Vision, 2009, 81(2):155-166.
[22] NisterR D, Stewenius H. Scalable recognition with a vocabulary tree[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2006:2161-2168.
[23] Mur-Artal R, Tardos J D. Fast relocalisation and loop closing in keyframe-based SLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014:846-853.
[24] Triggs B, McLauchlan P F, Hartley R I, et al. Bundle adjustment-A modern synthesis[C]//Proceedings of International Workshop on Vision Algorithms:Theory and Practice. Berlin, Germany:Springer-Verlag, 1999:298-372.
[25] Kummerle R, Grisetti G, Strasdat H, et al. G²o:A general framework for graph optimization[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2011:3607-3613.
[26] Song S, Chandraker M, Guest C C. Parallel, real-time monocular visual odometry[C]//IEEE International Conference on Ro-botics and Automation. Piscataway, USA:IEEE, 2013:4698-4705.
[27] Geiger A, Ziegler J, Stiller C. Stereoscan:Dense 3D reconstruction in real-time[C]//IEEE Intelligent Vehicles Symposium. Piscataway, USA:IEEE, 2011:963-968.
[28] Rublee E, Rabaud V, Konolige K, et al. ORB:An efficient alternative to SIFT or SURF[C]//International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2564-2571.
[29] 张国良,姚二亮,林志林,等.融合直接法与特征法的快速双目SLAM算法[J].机器人,2017,39(6):879-888. Zhang G L, Yao E L, Lin Z L, et al. Fast binocular SLAM algorithm combining the direct method and the feature-based method[J]. Robot, 2017, 39(6):879-888.
[30] Strasdat H, Davison A J, Montiel J M M, et al. Double window optimisation for constant time visual SLAM[C]//International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2352-2359.
[31] Williams B, Cummins M, Newman P, et al. A comparison of loop closing techniques in monocular SLAM[J]. Robotics and Autonomous Systems, 2009, 57(12):1188-1197.
[32] Galvezlopez D, Tardos J D. Bags of binary words for fast place recognition in image sequences[J]. IEEE Transactions on Robotics, 2012, 28(5):1188-1197.
[33] Geiger A, Lenz P, Stiller C, et al. Vision meets robotics:The KITTI dataset[J]. International Journal of Robotics Research, 2013, 32(11):1231-1237.
[34] Sturm J, Engelhard N, Endres F, et al. A benchmark for the evaluation of RGB-D SLAM systems[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2012:573-580.