广东工业大学学报 ›› 2021, Vol. 38 ›› Issue (03): 48-54.doi: 10.12052/gdutxb.200111

• • 上一篇    下一篇

基于稀疏直接法闭环检测定位的视觉里程计

汝少楠, 何元烈, 叶星余   

  1. 广东工业大学 计算机学院，广东 广州 510006
  • 收稿日期:2020-09-04 出版日期:2021-05-10 发布日期:2021-03-12
  • 通信作者: 何元烈(1976-)，男，副教授，主要研究方向为计算机视觉、深度学习和智能机器人，E-mail：heyuanlie@163.com E-mail:heyuanlie@163.com
  • 作者简介:汝少楠(1997-)，男，硕士研究生，主要研究方向为计算机视觉、多传感器
  • 基金资助:
    国家自然科学基金资助项目(61876043)

Visual Odometry Based on Sparse Direct Method Loop-Closure Detection

Ru Shao-nan, He Yuan-lie, Ye Xing-yu   

  1. School of Computers, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2020-09-04 Online:2021-05-10 Published:2021-03-12

HTML

PDF (PC)

2692

摘要： 视觉里程计在移动机器人的定位导航中发挥着关键性作用, 但当前的算法在运行速度、轨迹精度和鲁棒性等方面依然存在改善空间。为提高相机轨迹精度, 提出基于稀疏直接法的闭环检测算法。该算法直接提取两种特征组成混合型特征点提升系统鲁棒性, 混合型特征点用于跟踪和匹配关键帧, 使视觉里程计能够检测闭环, 再用位姿图优化提升定位精度。实验结果表明在复杂环境中具有较强的鲁棒性, 并且在速度和精度之间取得平衡。

关键词: 视觉里程计, 闭环检测, 稀疏直接法, 视觉特征, 相机轨迹

Abstract: The visual odometry plays a key role in the positioning and navigation of mobile robots, but the current algorithm still has room for improvement in terms of running speed, trajectory accuracy, and robustness. In order to improve the accuracy of camera trajectory, a loop-closure detection algorithm is proposed based on the sparse direct method. The algorithm directly extracts two features to form a hybrid feature point to improve the robustness of the system. The hybrid feature point is used to track and match key frames, so that the visual odometry can detect closed loops, and then the pose map is used to optimize the positioning accuracy. Experimental results show strong robustness in a complex environment and a balance between speed and accuracy.

Key words: visual odometry, loop-closure detection, sparse direct method, visual feature, camera trajectory

中图分类号: 

  • TP249
[1] TAKETOMI T, UCHIYAMA H, IKEDA S. Visual SLAM algorithms: a survey from 2010 to 2016 [J]. IPSJ Transactions on Computer Vision and Applications, 2017, 9(1): 16-26.
[2] KLEIN G, MURRAY D. Parallel tracking and mapping for small AR workspaces[C]//2007 6th IEEE and ACM international symposium on mixed and augmented reality. Nara: IEEE, 2007: 225-234.
[3] GOMEZ-OJEDA R, MORENO F A, ZUÑIGA-NOËL D, et al. PL-SLAM: a stereo SLAM system through the combination of points and line segments [J]. IEEE Transactions on Robotics, 2019, 35(3): 734-746.
[4] MUÑOZ-SALINAS R, MEDINA-CARNICER R. UcoSLAM: simultaneous localization and mapping by fusion of key points And squared planar markers [J]. Pattern Recognition, 2020, 101: 107-193.
[5] 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.
[6] FORSTER C, PIZZOLI M, SCARAMUZZA D. SVO: Fast semidirect monocular visual odometry[C]//2014 IEEE international conference on robotics and automation (ICRA). Hong Kong: IEEE, 2014: 15-22.
[7] 岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(4): 35-41.
CEN S J, HE Y L, CHEN X C. A monocular depth estimation combined with attention and unsupervised deep learning [J]. Journal of Guangdong University of Technology, 2020, 37(4): 35-41.
[8] ANGELI A, FILLIAT D, DONCIEUX S, et al. Fast and Incremental method for loop-closure detection using bags of visual words [J]. IEEE Transactions on Robotics, 2008, 24(5): 1027-1037.
[9] 何元烈, 陈佳腾, 曾碧. 基于精简卷积神经网络的快速闭环检测方法[J]. 计算机工程, 2018, 44(6): 182-187.
HE Y L, CHEN J T, ZENG B. Fast closed loop detection method based on simplification convolutional neural network [J]. Computer Engineering, 2018, 44(6): 182-187.
[10] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: an efficient alternative to SIFT or SURF[C]//2011 International ConfeRence on Computer Vision. Barcelona: IEEE, 2011: 2564-2571.
[11] GÁLVEZ-LÓPEZ 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.
[12] GAO X, WANG R, DEMMEL N, et al. LDSO: direct sparse odometry with loop closure[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid: IEEE, 2018: 2198-2204.
[13] KÜMMERLE R, GRISETTI G, STRASDAT H, et al. g2o: A general framework for graph optimization[C]//2011 IEEE International Conference on Robotics and Automation. Shanghai: IEEE, 2011: 3607-3613.
[14] MUR-ARTAL R, TARDÓS J D. Orb-slam2: an open-source slam system for monocular, stereo, and RGB-D cameras [J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
[15] 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.
[16] ENGEL J, KOLTUN V, CREMERS D. Direct sparse odometry [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(3): 611-625.
[17] ELVIRA R, TARDÓS J D, MONTIEL J M M. ORBSLAM-Atlas: a robust and accurate multi-map system[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau: IEEE, 2019: 6253-6259.
[1] 徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(01): 56-60,76.
[2] 叶培楚, 李东, 章云. 基于双目强约束的直接稀疏视觉里程计[J]. 广东工业大学学报, 2021, 38(04): 65-70.
[3] 杨孟军, 苏成悦, 陈静, 张洁鑫. 基于卷积神经网络的视觉闭环检测研究[J]. 广东工业大学学报, 2018, 35(05): 31-37.
[4] 马晓东, 曾碧, 叶林锋. 基于BA的改进视觉/惯性融合定位算法[J]. 广东工业大学学报, 2017, 34(06): 32-36.
[5] 池鹏可, 苏成悦. 移动机器人中单目视觉里程计的研究[J]. 广东工业大学学报, 2017, 34(05): 40-44.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发