基于视觉惯性融合的半直接单目视觉里程计

doi:10.13973/j.cnki.robot.190628

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (781 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
龚赵慧, 张霄力, 彭侠夫, 李鑫. 基于视觉惯性融合的半直接单目视觉里程计[J]. 机器人, 2020, 42(5): 595-605.DOI: 10.13973/j.cnki.robot.190628. GONG Zhaohui, ZHANG Xiaoli, PENG Xiafu, LI Xin. Semi-Direct Monocular Visual Odometry Based on Visual-Inertial Fusion. ROBOT, 2020, 42(5): 595-605. DOI: 10.13973/j.cnki.robot.190628.

摘要针对半直接单目视觉里程计缺乏尺度信息并且在快速运动中鲁棒性较差的缺点，设计了一种融合惯性测量信息的半直接单目视觉里程计，通过IMU（惯性测量单元）信息弥补视觉里程计的缺陷，有效提高跟踪精度与系统鲁棒性．本文联合惯性测量信息与视觉信息进行初始化，较准确地恢复了环境尺度信息．为提高运动跟踪的鲁棒性，提出一种IMU加权的运动先验模型．通过预积分获取IMU的状态估计，根据IMU先验误差调整权重系数，使用IMU先验信息的加权值为前端提供精确的初值．后端构建了紧耦合的图优化模型，融合惯性、视觉以及3维地图点信息进行联合优化，同时在滑动窗口中使用强共视关系作为约束，在消除局部累积误差的同时提高优化效率与优化精度．实验结果表明，本文的先验模型优于匀速运动模型与IMU先验模型，单帧先验误差小于1 cm．后端优化方法改进后，计算效率提高为原来的1.52倍，同时轨迹精度与优化稳定性也得到提高．在EuRoC数据集上进行测试，定位效果优于OKVIS算法，轨迹均方根误差减小为原视觉里程计的1/3．

	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
	张霄力
	彭侠夫
	李鑫
	龚赵慧

关键词 ：视觉惯性里程计, 初始化, 先验模型, 图优化, 单目视觉, 半直接法

Abstract：Considering the disadvantages of semi-direct monocular visual odometry which lacks scale factor and shows poor robustness in fast motion, a semi-direct monocular visual odometry based on inertial fusion is designed. By using IMU (inertial measurement unit) information to make up for the deficiencies of visual odometry, the tracking accuracy and the system robustness can be effectively improved. Through the joint initialization of visual information and inertial measurement, the environmental scale can be accurately recovered. In order to improve the robustness of motion tracking, an IMU-weighted prior model is proposed. IMU state estimation is obtained by preintegration, the weight coefficient is adjusted according to the IMU prior error, and then the weighted value of IMU state is used to provide accurate initial estimation for the front-end. A tightly coupled graph optimization model is constructed in the back-end, which combines inertia, vision and 3D map point for joint optimization. Using common-view relationships as constraints in sliding window, it can improve the optimization efficiency and accuracy while eliminating the local cumulative error. The experimental results show that the prior model is better than both the uniform motion model and the IMU prior model, and the single frame prior error is less than 1 cm. By improving the back-end method, the calculation efficiency is increased by 0.52 times, and both the trajectory accuracy and the optimization stability are improved at the same time. Experimental results on the public dataset EuRoC demonstrate that the proposed algorithm outperforms the open keyframe-based visual inertial SLAM (OKVIS) algorithm, and the root mean square error of trajectory is reduced to 1/3 compared with the original visual odometry.

Key words： visual-inertial odometry initialization prior model graph optimization monocular vision semi-direct method

收稿日期: 2019-11-26 录用日期: 2020-05-05

TP242

基金资助:装备预研领域基金（61405180205）；惯性技术国防重点实验室基金（61425060201162506007）；航空科学基金（201958068002）

通讯作者: 张霄力,zhxl@xmu.edu.cn E-mail: zhxl@xmu.edu.cn

作者简介: 龚赵慧(1996-),女,硕士生.研究领域:多源融合导航,视觉SLAM.
张霄力(1970-),男,博士,副教授.研究领域:组合导航技术,非线性系统和鲁棒控制.
彭侠夫(1963-),男,博士,教授.研究领域:控制与导航技术,运动体智能装置与系统.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.190628 或 https://robot.sia.cn/CN/Y2020/V42/I5/595

[1] Royer E, Lhuillier M, Dhome M, et al. Monocular vision for mobile robot localization and autonomous navigation[J]. International Journal of Computer Vision, 2007, 74(3):237-260.
[2] Moreno-Armendariz M A, Calvo H. Visual SLAM and obstacle avoidance in real time for mobile robots navigation[C]//IEEE International Conference on Mechatronics, Electronics and Automotive Engineering. Piscataway, USA:IEEE, 2014:44-49.
[3] 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.
[4] Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2007:225-234.
[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 semi-direct monocular visual odometry[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014:15-22.
[7] Forster C, Zhang Z, Gassner M, et al. SVO:Semidirect visual odometry for monocular and multicamera systems[J]. IEEE Transactions on Robotics, 2017, 33(2):249-265.
[8] 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.
[9] Engel J, Koltun V, Cremers D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3):611-625.
[10] Kelly J, Sukhatme G S. Visual-inertial simultaneous localization, mapping and sensor-to-sensor self-calibration[C]//IEEE International Symposium on Computational Intelligence in Robotics and Automation. Piscataway, USA:IEEE, 2009:360-368.
[11] Lupton T, Sukkarieh S. Visual-inertial-aided navigation for high-dynamic motion in built environments without initial conditions[J]. IEEE Transactions on Robotics, 2012, 28(1):61-76.
[12] Forster C, Carlone L, Dellaert F, et al. On-manifold preintegration for real-time visual-inertial odometry[J]. IEEE Transac-tions on Robotics, 2017, 30(1):1-21.
[13] Mur-Artal R, Tardos J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2):796-803.
[14] 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.
[15] Liu Y, Chen Z, Zheng W J, et al. Monocular visual-inertial SLAM:Continuous preintegration and reliable initialization[J]. Sensors, 2017, 17(11):2613-2637.
[16] Jones E S, Soatto S. Visual-inertial navigation, mapping and localization:A scalable real-time causal approach[J]. International Journal of Robotics Research, 2011, 30(4):407-430.
[17] Cadena C, Carlone L, Carrillo H, et al. Past, present, and future of simultaneous localization and mapping:Toward the robust-perception age[J]. IEEE Transactions on Robotics, 2016, 32(6):1309-1332.
[18] 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.
[19] 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.
[20] Burri M, Nikolic J, Gohl P, et al. The EuRoC micro aerial vehicle datasets[J]. International Journal of Robotics Research, 2016, 35(10):1157-1163.
[21] Qin T, Shen S J. Robust initialization of monocular visual-inertial estimation on aerial robots[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2017:4225-4232.
[22] Martinelli A. Closed-form solution of visual-inertial structure from motion[J]. International Journal of Computer Vision, 2014, 106(2):138-152.
[23] Kaiser J, Martinelli A, Fontana F, et al. Simultaneous state initialization and gyroscope bias calibration in visual inertial aided navigation[J]. IEEE Robotics and Automation Letters, 2017, 2(1):18-25.
[24] 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.
[25] Mur-Artal R, Tardos 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.