An inertial assisted monocular front-end model based on weighted pre-integration and fast initialization

doi:10.13474/j.cnki.11-2246.2019.0242

Abstract

Abstract: Aiming at the robustness and high precision of monocular visual inertial positioning system in complex environment and camera dynamic conditions, Improved_VIO, an inertial assisted monocular front-end model based on weighted pre-integration and fast initialization is proposed. Firstly, the visual and inertial measurement data are synchronized, and a high-precision IMU weighted pre-integration model is established to provide inter-frame motion constraints for joint initialization and visual tracking models. Secondly, constructing the visual inertia fusion state vector, and establishing the joint initialization model realize the fast joint initialization of visual inertia coupling. Finally, based on the IMU weighted pre-integration and fast initialization methods, a visual inertia-assisted tracking model is established to effectively improve the robustness of the system. The experimental results show that compared with the traditional visual inertial positioning front-end model, the Improved_VIO improves the accuracy, speed and robustness of monocular visual inertial positioning. The initialization time is shortened to 10 seconds, and the positioning accuracy is improved about 30%.

Key words: monocular visual inertial, weighted pre-integration, fast initialization, high precision, front-end model

CLC Number:

P228

ZENG Pan, PAN Shuguo, HUANG Lixiao, WANG Shuai, ZHAO Tao. An inertial assisted monocular front-end model based on weighted pre-integration and fast initialization[J]. 测绘通报, 2019, 0(8): 8-13,19.

References

[1] 李群明, 熊蓉, 褚健. 室内自主移动机器人定位方法研究综述[J]. 机器人,2003, 25(6):560-567.
[2] 胡劲草.室内自主式移动机器人定位方法研究[J].传动技术,2006(4):14-18,46.
[3] 刘浩敏,章国锋,鲍虎军.基于单目视觉的同时定位与地图构建方法综述[J].计算机辅助设计与图形学学报,2016,28(6):855-868.
[4] 白云汉. 基于SLAM算法和深度神经网络的语义地图构建研究[J]. 计算机应用与软件, 2018,35(1):183-190.
[5] 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.
[6] SHEN S, MICHAEL N, KUMAR V. Tightly-coupled monocular visual-inertial fusion for autonomous flight of rotorcraft MAVs[C]//2015 IEEE International Conference on Robotics and Automation (ICRA). Seattle:IEEE, 2015:5303-5310.
[7] 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.
[8] 王安娜. 室内移动机器人自定位方法的研究[D]. 天津:河北工业大学, 2015.
[9] LEUTENEGGER S, LYNEN S, BOSSE M, et al. Keyframe-based visual-inertial odometry using nonlinear optimization[J]. The International Journal of Robotics Research, 2015, 34(3):314-334.
[10] MUR-ARTAL R, TARDóS J D. An open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE Transactions on Robotics, 2017, 33(5):1255-1262.
[11] QIN T, LI P, SHEN S. Vins-mono:a robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4):1004-1020.
[12] FORSTER C, CARLONE L, DELLAERT F, et al. On-manifold preintegration for real-time visual-inertial odometry[J]. IEEE Transactions on Robotics, 2017, 33(1):1-21.
[13] MUR-ARTAL R, TARDóS J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2):796-803.
[14] MARTINELLI A. Closed-form solution of visual-inertial structure from motion[J]. International Journal of Computer Vision, 2014, 106(2):138-152.
[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.