基于直接法与惯性测量单元融合的视觉里程计

doi:10.13973/j.cnki.robot.180601

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (460 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
刘艳娇, 张云洲, 荣磊, 姜浩, 邓毅. 基于直接法与惯性测量单元融合的视觉里程计[J]. 机器人, 2019, 41(5): 683-689.DOI: 10.13973/j.cnki.robot.180601. LIU Yanjiao, ZHANG Yunzhou, RONG Lei, JIANG Hao, DENG Yi. Visual Odometry Based on the Direct Method and the Inertial Measurement Unit. ROBOT, 2019, 41(5): 683-689. DOI: 10.13973/j.cnki.robot.180601.

摘要针对直接法完全依靠梯度搜索来计算相机位姿、容易陷入局部最优的缺点，本文将惯性测量单元（IMU）数据紧密关联到图像跟踪过程，提供精确的短期运动约束和较好的初始梯度方向信息，并对视觉位姿跟踪结果进行校正，提高单目视觉里程计的跟踪精度．在此基础上，基于相机和IMU测量结果建立传感器数据融合模型，采用滑动窗口的方式优化求解，同时在边缘化过程中根据当前帧与上一关键帧之间的相机帧间运动大小，选择应边缘化的状态量和应加入滑动窗口的状态量，确保在优化过程中有足够准确的先验信息，确保优化融合的效果．实验结果表明，与现有的视觉里程计算法相比，本文算法在数据集上的定位角度累积误差在3°左右，位移累积误差小于0.4 m．

	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
	刘艳娇
	张云洲
	荣磊
	姜浩
	邓毅

关键词 ：视觉里程计, 单目视觉, IMU融合, 直接法, 优化模型

Abstract：Traditionally, the direct method is prone to fall into local optimum because it estimates the camera pose depending on gradient search entirely. For this problem, the IMU (inertial measurement unit) data is tightly associated with camera tracking to provide accurate short-term motion constraints and initial value of gradient direction, and the visual pose tracking result is corrected to improve the tracking accuracy of the monocular visual odometry. Then, the sensor data fusion model is established based on camera and IMU measurements, and the sliding window is used to optimize the solution. During the marginalization process, the state variables which should be marginalized or added to the sliding window are selected according to the camera motion between the current frame and the previous keyframes. In this way, accurate enough prior states for optimization can be ensured to achieve better optimization and fusion performance. Experimental results show that the total orientation error of the proposed algorithm is about 3° and the total translation error is less than 0.4 m compared with the existing visual odometry algorithms.

Key words： visual odometry monocular vision IMU (inertial measurement unit) fusion direct method optimization model

收稿日期: 2018-10-08 录用日期: 2018-12-27

TP242

基金资助:国家重点研发计划（2017YFC0805005，2017YFB1301103）；十三五装备预研共用技术和领域基金（41412050202）；中央高校基本科研业务专项资金（N172608005）；辽宁省自然科学基金（20180520040）

通讯作者: 张云洲,zhangyunzhou@mail.neu.edu.cn E-mail: zhangyunzhou@mail.neu.edu.cn

作者简介: 刘艳娇(1993-),女,硕士.研究领域:计算机视觉.
张云洲(1974-),男,博士,教授.研究领域:智能机器人,计算机视觉.
荣磊(1995-),男,博士.研究领域:计算机视觉,智能机器人.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.180601 或 https://robot.sia.cn/CN/Y2019/V41/I5/683

[1] 张国良,林志林,姚二亮,等.考虑多位姿估计约束的双目视觉里程计[J].控制与决策,2018,33(6):1008-1016.Zhang G L, Lin Z L, Yao E L, et al. Stereo visual odometry with multi-pose estimation constraints[J]. Control and Decision, 2018, 33(6):1008-1016.
[2] 林辉灿,吕强,张洋,等.稀疏和稠密的VSLAM的研究进展[J].机器人,2016,38(5):621-631.Lin H C, Lü Q, Zhang Y, et al. The sparse and dense VSLAM:A survey[J]. Robot, 2016, 38(5):621-631.
[3] Bloesch M, Omari S, Hutter M, et al. Robust visual inertial odometry using a direct EKF-based approach[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2015:298-304.
[4] Mourikis A I, Roumeliotis S I. A multi-state constraint Kalman filter for vision-aided inertial navigation[C]//IEEE InternationalConference on Robotics and Automation. Piscataway, USA:IEEE, 2007:3565-3572.
[5] Jones E S, Soatto S. Visual-inertial navigation, mapping and localization:A scalable real-time causal approach[J]. Interna-tional Journal of Robotics Research, 2011, 30(4):407-430.
[6] Usenko V, Engel J, Stuckler J, et al. Direct visual-inertial odometry with stereo cameras[C]//IEEE International Conference onRobotics and Automation. Piscataway, USA:IEEE, 2016:1885-1892.
[7] 林辉灿,吕强,王国胜,等.鲁棒的非线性优化的立体视觉-惯导SLAM[J].机器人,2018,40(6):911-920.Lin H C, Lü Q, Wang G S, et al. Robust stereo visual-inertial SLAM using nonlinear optimization[J]. Robot, 2018, 40(6):911-920.
[8] Leutenegger S, Lynen S, Bosse M, et al. Keyframe-based visual-inertial odometry using nonlinear optimization[J]. International Journal of Robotics Research, 2015, 34(3):314-334.
[9] Konolige K, Agrawal M, Solá J. Large-scale visual odometry for rough terrain[C]//13th International Symposium on Robotics Research. Berlin, Germany:Springer, 2010:201-212.
[10] Kitt B, Rehder J, Chambers A, et al. Monocular visual odometry using a planar road model to solve scale ambiguity[C]//Euro-pean Conference on Mobile Robots. 2011:43-48.
[11] Klein G, Murray D. Parallel tracking and mapping for smallAR workspaces[C]//IEEE and ACM International Symposium on Mixed and Augmented Reality. Los Alamitos, USA:IEEE Computer Society, 2007. DOI:10.1109/ISMAR.2007.4538852.
[12] Stühmer J, Gumhold S, Cremers D. Real-time dense geometry from a handheld camera[M]//Lecture Notes in Computer Science, Vol.6376. Berlin, Germany:Springer-Verlag, 2010:11-20.
[13] Graber G, Pock T, Bischof H. Online 3D reconstruction usingconvex optimization[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:708-711.
[14] Newcombe R A, Lovegrove S J, Davison A J. DTAM:Dense tracking and mapping in real-time[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2320-2327.
[15] 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.
[16] Forster C, Zhang Z, Gassner M, et al. SVO:Semidirect visualodometry for monocular and multicamera systems[J]. IEEE Transactions on Robotics, 2017, 33(2):249-265.
[17] Engel J, Schöps T, Cremers D. LSD-SLAM:Large-scale directmonocular SLAM[M]//Lecture Notes in Computer Science, Vol.8690. Berlin, Germany:Springer, 2014:834-849.
[18] Engel J, Koltun V, Cremers D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3):611-625.
[19] Concha A, Loianno G, Kumar V, et al. Visual-inertial directSLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2016:1331-1338.
[20] von Stumberg L, Usenko V, Cremers D. Direct sparse visual-inertial odometry using dynamic marginalization[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2018:2510-2517.
[21] Forster C, Carlone L, Dellaert F, et al. On-manifold preintegration for real-time visual-inertial odometry[J]. IEEE Transac-tions on Robotics, 2017, 33(1):1-21.
[22] Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM:A versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2017, 31(5):1147-1163.
[23] Mur-Artal R, Tardos J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2):796-803.
[24] Qin T, Li P L, Shen S J. VINS-Mono:A robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4):1004-1020.
[25] 祝朝政,何明,杨晟,等.单目视觉里程计研究综述[J].计算机工程与应用,2018,54(7):20-28, 55. Zhu C Z, He M, Yang S, et al. Survey of monocular visualodometry[J]. Computer Engineering and Applications, 2018, 54(7):20-28, 55.