《计算机应用研究》|Application Research of Computers

基于单目视觉的同时定位与建图算法研究综述

Survey on monocular visual SLAM algorithms

免费全文下载 (已被下载 次)  
获取PDF全文
作者 朱凯,刘华峰,夏青元
机构 南京理工大学 计算机科学与工程学院,南京 210094
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)01-0001-06
DOI 10.3969/j.issn.1001-3695.2018.01.001
摘要 与传统基于激光传感器的同时定位与建图(SLAM)方法相比,基于图像视觉传感器SLAM方法能廉价地获得更多环境信息,帮助移动机器人提高智能性。不同于用带深度信息的3D传感器研究SLAM问题,单目视觉SLAM算法用二维图像序列在线构建三维环境地图并实现实时定位。针对多种单目视觉SLAM算法进行对比研究,分析了近10年来流行的单目视觉定位算法的主要思路及其分类,指出基于优化方法正取代滤波器方法成为主流方法。从初始化、位姿估计、地图创建、闭环检测等功能组件的角度分别总结了目前流行的各种单目视觉 SLAM 或Odometry系统的工作原理和关键技术,阐述它们的工作过程和性能特点;总结了近年最新单目视觉定位算法的设计思路,最后概括指出本领域的研究热点与发展趋势。
关键词 单目相机;视觉定位;视觉里程计;视觉同时定位与建图
基金项目 国家自然科学基金资助项目(61403202)
中国博士后科学基金面上资助项目(2014M561654)
本文URL http://www.arocmag.com/article/01-2018-01-001.html
英文标题 Survey on monocular visual SLAM algorithms
作者英文名 Zhu Kai, Liu Huafeng, Xia Qingyuan
机构英文名 SchoolofComputerScience&Engineering,NanjingUniversityofScience&Technology,Nanjing210094,China
英文摘要 Compared with traditional laser scanner based SLAM method, camera based SLAM algorithms outperformed in cost as well as information, and could make mobile robot smarter. Instead of using 3D sensors, monocular visual SLAM utilized 2D image sequence to reconstruct 3D map and performed real-time localization. This paper aimed at providing a survey on mono-cular visual SLAM algorithms. It studied the most popular visual SLAM algorithms in the last decade and discussed the main principle and their classification. Then it pointed out that the optimization method would be the mainstream. It summarized the principle and practice of the state of the art visual SLAM or visual Odometry systems from the angle of initialization, pose estimation, map generation and loop closure. According to above, this paper also elaborated the design scheme and performance of the state of art monocular SLAM algorithms. At last, it concluded with the viewpoint for the research trend.
英文关键词 monocular camera; visual localization; visual odometry; visual SLAM(simultaneous localization and mapping)
参考文献 查看稿件参考文献
  [1] Nistér D, Naroditsky O, Bergen J. Visual odometry[C] //Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004:652-659.
[2] Engel J, Schops T, Cremers D, et al. LSD-SLAM:large-scale direct monocular SLAM[C] //Proc of European Conference on Computer Vision. 2014:834-849.
[3] Engel J, Stückler J, Cremers D. Large-scale direct SLAM with stereo cameras[C] //Proc of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2015.
[4] Caruso D, Engel J, Cremers D. Large-scale direct SLAM for omnidirectional cameras[C] //Proc of IEEE/RSJ International Conference on Intelligent Robots and Systems. 2015:141-148.
[5] Strasdat H, Montiel J M M, Davison A J. Visual SLAM:why filter?[J] . Image and Vision Computing, 2012, 30(2):65-77.
[6] Yousif K, Bab-Hadiashar A, Hoseinnezhad R. An overview to visual Odometry and visual SLAM:applications to mobile robotics[J] . Intelligent Industrial Systems, 2015, 1(4):289-311.
[7] Dellaert F. Square root SAM[C] //Robotics:Science and Systems. Cambridge:Massachusetts Institute of Technology, 2005:177-184.
[8] Julier S J, Uhlmann J K. A counter example to the theory of simultaneous localization and map building[C] //Proc of IEEE International Conference on Robotics & Automation. 2001:4238-4243.
[9] Clemente L A, Davison A J, Reid I D, et al. Mapping large loops with a single hand-held camera[C] //Robotics:Science and Systems III. Georgia:Georgia Institute of Technology, 2007:297-304.
[10] Piniés P, Tardós J D. Large-scale SLAM building conditionally independent local maps:application to monocular vision[J] . IEEE Trans on Robotics, 2008, 24(5):1094-1106.
[11] Lim J, Frahm J M, Pollefeys M. Online environment mapping[C] //Proc of IEEE Conference on Computer Vision & Pattern Recognition. 2011:3489-3496.
[12] Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C] //Proc of International Joint Conference on Artificial Intelligence. San Francisco:Morgan Kaufmann Publishers Inc, 1981:285-289.
[13] Baker S, Matthews I. Lucas-kanade 20 years on:a unifying framework[J] . International Journal of Computer Vision, 2004, 56(3):221-255.
[14] Hartmann J, Klüssendorff J H, Maehle E. A comparison of feature descriptors for visual SLAM[C] //Proc of European Conference on Mobile Robots. 2013:56-61.
[15] Forster C, Pizzoli M, Scaramuzza D. SVO:fast semi-direct monocular visual odometry[C] //Proc of IEEE International Conference on Robotics and Automation. 2014:15-22.
[16] Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C] //Proc of IEEE and ACM International Symposium on Mixed and Augmented Reality. Washington DC:IEEE Computer Socie-ty, 2007:1-10.
[17] Davison A J, Reid I D, Molton N D, et al. MonoSLAM:real-time single camera SLAM[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(6):1052-1067.
[18] Faugeras O D, Lustman F. Motion and structure from motion in a piecewise planar environment[J] . International Journal of Pattern Recognition and Artificial Intelligence, 1988, 2(3):485-508.
[19] Rosten E, Drummond T. Machine learning for high-speed corner detection[C] //Proc of European Conference on Computer Vision. [S. l. ] :Springer-Verlag, 2006:430-443.
[20] Torr P H S, Zisserman A. MLESAC:a new robust estimator with application to estimating image geometry[J] . Computer Vision and Image Understanding, 2000, 78(1):138-156.
[21] Tomasi C, Kanade T. Detection and tracking of point features[D] . Pittsburgh:School of Computer Science, Carnegie Mellon University, 1991.
[22] Maronna R A, Martin D R, Yohai V J. Robust statistics:theory and methods[M] . Hoboken:Wiley, 2006.
[23] Engel J, Sturm J, Cremers D. Semi-dense visual odometry for a monocular camera[C] //Proc of IEEE International Conference on Computer Vision. Washington DC:IEEE Computer Society, 2013:1449-1456.
[24] Konolige K. Sparse sparse bundle adjustment[C] //Proc of British Machine Vision Conference. 2010:1-11.
[25] Vogiatzis G, Hernández C. Video-based, real-time multi-view stereo[J] . Image and Vision Computing, 2011, 29(7):434-441.
[26] Strasdat H, Davison A J, Montiel J M M, et al. Double window optimisation for constant time visual SLAM[C] //Proc of International Conference on Computer Vision. Washington DC:IEEE Computer Society, 2011:2352-2359.
[27] Kümmerle R, Grisetti G, Strasdat H, et al. g2o:a general framework for graph optimization[C] //Proc of IEEE International Conference on Robotics and Automation. 2010.
[28] Glover A, Maddern W, Warren M, et al. OpenFABMAP:an open source toolbox for appearance-based loop closure detection[C] //Proc of IEEE International Conference on Robotics and Automation. 2012:4730-4735.
[29] Galvez-López D, Tardos J D. Bags of binary words for fast place re-cognition in image sequences[J] . IEEE Trans on Robotics, 2012, 28(5):1188-1197.
[30] Tan Wei, Liu Haomin, Dong Zilong, et al. Robust monocular SLAM in dynamic environments[C] //Proc of IEEE International Symposium on Mixed and Augmented Reality. 2013:209-218.
[31] Mei C, Sibley G, Cummins M, et al. RSLAM:a system for large-scale mapping in constant-time using stereo[J] . International Journal of Computer Vision, 2011, 94(2):198-214.
[32] McManus C, Churchill W, Maddern W, et al. Shady dealings:robust, long-term visual localisation using illumination invariance[C] //Proc of IEEE International Conference on Robotics and Automation. 2014:901-906.
[33] Pascoe G, Maddern W, Newman P. Direct visual localisation and calibration for road vehicles in changing city environments[C] //Proc of IEEE International Conference on Computer Vision. Washington DC:IEEE Computer Society, 2015:98-105.
[34] Urtasun R, Lenz P, Geiger A. Are we ready for autonomous driving? The KITTI vision benchmark suite[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society, 2012:3354-3361.
[35] Konolige K, Agrawal M. FrameSLAM:from bundle adjustment to real-time visual mapping[J] . IEEE Trans on Robotics, 2008, 24(5):1066-1077.
[36] Nist D. An efficient solution to the five-point relative pose problem[J] . IEEE Trans on Pattern Analysis & Machine Intelligence, 2003, 26(6):756-777.
[37] Benhimane S, Malis E. Homography-based 2D visual tracking and servoing[J] . International Journal of Robotics Research, 2007, 26(7):661-676.
收稿日期 2016/12/27
修回日期 2017/2/23
页码 1-6
中图分类号 TP391.41
文献标志码 A