面向视觉惯导的导航系统初始化技术综述

doi:10.3778/j.issn.1002-8331.2406-0038

摘要/Abstract

摘要： 视觉惯导系统是导航中应用最广泛的基础传感器系统之一，其单独使用或与其他系统联合使用是目前传感器配置的主要方案。初始化技术作为决定导航性能的前置环节，决定了导航的成败，也因此被大量研究。目前与初始化相关的方法种类丰富、工程性强，但是缺少较为全面和系统的综述；同时，尽管目前已经有很成熟的初始化范式，但是在实际使用时，初始化环节仍然有较高的失败率，且一些展示良好导航效果的初始化方法并未公开。随着任务的升级与技术的革新，新型视惯系统与人工智能也为初始化环节带来了新的提升与挑战。对视惯导航系统与初始化技术进行概述，然后针对初始化环节中的关键技术进行详细的调研与讨论，在给出经典初始化框架后，进行了总结与展望。

关键词: 视觉惯导, 导航系统, 初始化技术, 标定, 人工智能

Abstract: The visual-inertial systems are one of the most widely used basic sensor systems in navigation, and its separate use or combined use with other systems is the main scheme of sensor configuration at present. Initialization technology, as the front end of the navigation processes, determines the success or failure of navigation, so it has been studied extensively. At present, the methods related to initialization are rich in variety and engineering, but there is a lack of more comprehensive and systematic reviews. Meanwhile, although there are mature initialization paradigms, the initialization process still has a high failure rate in practice, and some initialization methods that demonstrate good navigation effects are not publicly available. With the escalation of missions and the innovation in technology, new visual-inertial systems and artificial intelligence have also brought new enhancements and challenges to the initialization. This paper summarizes the visual inertial navigation system and initialization technology, and then researches and discusses the key technologies in the initialization process in detail. After presenting classical initialization frameworks, the paper concludes with a summary and prospects.

Key words: visual-inertial, navigation systems, initialization technology, calibration, artificial intelligence

刘悦, 李化义, 张世杰, 张超, 赵祥天. 面向视觉惯导的导航系统初始化技术综述[J]. 计算机工程与应用, 2025, 61(2): 1-18.

LIU Yue, LI Huayi, ZHANG Shijie, ZHANG Chao, ZHAO Xiangtian. Review of Initialization Technology for Visual-Inertial Navigation Systems[J]. Computer Engineering and Applications, 2025, 61(2): 1-18.

参考文献

[1] 吴涛, 谢志军. 一种改进的视觉/IMU导航系统初始化方法[J]. 压电与声光, 2021, 43(6): 863-868.
WU T, XIE Z J. An improved initialization method of visual/IMU navigation system initialization[J]. Piezoelectrics & Acoustooptics, 2021, 43(6): 863-868.
[2] HESCH J A, KOTTAS D G, BOWMAN S L, et al. Consistency analysis and improvement of vision-aided inertial navigation[J]. IEEE Transactions on Robotics, 2014, 30(1): 158-176.
[3] ARTH C, PIRCHHEIM C, VENTURA J, et al. Instant outdoor localization and SLAM initialization from 2.5D maps[J]. IEEE Transactions on Visualization and Computer Graphics, 2015, 21(11): 1309-1318.
[4] CIVERA J, DAVISON A J, MONTIEL J M M. Interacting multiple model monocular SLAM[C]//Proceedings of the 2008 IEEE International Conference on Robotics and Automation, 2008: 3704-3709.
[5] GAUGLITZ S, SWEENEY C, VENTURA J, et al. Live tracking and mapping from both general and rotation-only camera motion[C]//Proceedings of the2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012: 13-22.
[6] DOMíNGUEZ-CONTI J, YIN J, ALAMI Y, et al. Visual-inertial SLAM initialization: a general linear formulation and a gravity-observing non-linear optimization[C]//Proceedings of the 2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2018: 37-45.
[7] 刘哲, 史殿习, 杨绍武, 等. 视觉惯性导航系统初始化方法综述[J]. 国防科技大学学报, 2023, 45(2): 15-26.
LIU Z, SHI D X, YANG S W, et al. Review of visual-inertial navigation system initialization method[J]. Journal of National University of Defense Technology, 2023, 45(2): 15-26.
[8] QIN T, SHEN S. Robust initialization of monocular visual-inertial estimation on aerial robots[C]//Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017: 4225-4232.
[9] FU B, HAN F, WANG Y, et al. High-precision multicamera-assisted camera-IMU calibration: theory and method[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-17.
[10] 杨梦佳. 基于惯导与双目视觉融合的 SLAM 技术研究 [D]. 西安: 西安科技大学, 2020.
YANG M J. Research on SLAM technology based on fusion of inertial navigation and binocular vision[D]. Xi’an: Xi’an University of Science and Technology, 2020.
[11] FAN Y, WANG R, MAO Y. Stereo visual inertial odometry with online baseline calibration[C]//Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: 1084-1090.
[12] PAUL M K, ROUMELIOTIS S I. Alternating-stereo VINS: observability analysis and performance evaluation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 4729-4737.
[13] LIU Y, WANG F, ZHANG W, et al. Online self-calibration initialization for multi-camera visual-inertial SLAM[C]//Proceedings of the 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2018: 192-199.
[14] YANG Z, LIU T, SHEN S. Self-calibrating multi-camera visual-inertial fusion for autonomous MAVs[C]//Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016: 4984-4991.
[15] ECKENHOFF K, GENEVA P, BLOECKER J, et al. Multi-camera visual-inertial navigation with online intrinsic and extrinsic calibration[C]//Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), 2019: 3158-3164.
[16] ECKENHOFF K, GENEVA P, HUANG G. MIMC-VINS: a versatile and resilient multi-IMU multi-camera visual-inertial navigation system[J]. IEEE Transactions on Robotics, 2021, 37(5): 1360-1380.
[17] LI A, ZOU D, YU W. Robust initialization of multi-camera slam with limited view overlaps and inaccurate extrinsic calibration[C]//Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021: 3361-3367.
[18] HWANGBO M, KIM J S, KANADE T. IMU self-calibration using factorization[J]. IEEE Transactions on Robotics, 2013, 29(2): 493-507.
[19] WANG Z, YANG K, SHI H, et al. LF-VIO: a visual-inertial-odometry framework for large field-of-view cameras with negative plane[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2022: 4423-4430.
[20] ZHAO X, LI Q, WANG C, et al. Robust depth-aided rgbd-inertial odometry for indoor localization[J]. Measurement, 2023, 209: 112487.
[21] CHEN P, GUAN W, LU P. ESVIO: event-based stereo visual inertial odometry[J]. IEEE Robotics and Automation Letters, 2023, 8(6): 3661-3668.
[22] LEE W, ECKENHOFF K, GENEVA P, et al. Intermittent GPS-aided VIO: online initialization and calibration[C]//Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: 5724-5731.
[23] HAN B, XIAO Z, HUANG S, et al. Multi-layer VI-GNSS global positioning framework with numerical solution aided MAP initialization[C]//Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021: 5448-5455.
[24] TKOCZ M, JANSCHEK K. Closed-form metric velocity and landmark distance determination utilizing monocular camera images and IMU data in the presence of gravity[C]//Proceedings of the 2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2014: 8-13.
[25] WANG Y, MA H. Online spatial and temporal initialization for a monocular visual-inertial-LiDAR system[J]. IEEE Sensors Journal, 2022, 22(2): 1609-1620.
[26] SANJUKUMAR N, KOUNDINYA P N, RAJALAKSHMI P. Novel technique for multi sensor calibration of a UAV[C]//Proceedings of the 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON), 2020: 778-782.
[27] HUANG W, LIU H, WAN W. An online initialization and self-calibration method for stereo visual-inertial odometry[J]. IEEE Transactions on Robotics, 2020, 36(4): 1153-1170.
[28] ZHU H, ZHANG G, YE Z, et al. LVIF: a lightweight tightly coupled stereo-inertial SLAM with fisheye camera[J]. Complex & Intelligent Systems, 2024, 10: 763-780.
[29] CHEN S, LI X, LI S, et al. Targetless spatiotemporal calibration for multiple heterogeneous cameras and IMUs based on continuous-time trajectory estimation[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-12.
[30] REN H, ZHAO Y, LIN T, et al. Research on multi-sensor simultaneous localization and mapping technology for complex environment of construction machinery[J]. Applied Sciences, 2023, 13(14): 8496.
[31] YAN D, LI T, SHI C. Enhanced online calibration and initialization of visual-inertial SLAM system leveraging the structure information[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15.
[32] AMARASINGHE C, RATHNAWEERA A, MAITHRIPALA S. U-VIP-SLAM: underwater visual-inertial-pressure slam for navigation of turbid and dynamic environments[J]. Arabian Journal for Science and Engineering, 2024, 49: 3193-3207.
[33] LIU J, GAO W, XIE C, et al. Implementation and observability analysis of visual-inertial-wheel odometry with robust initialization and online extrinsic calibration[J]. Robotics and Autonomous Systems, 2024, 176: 104686.
[34] WEN T, FANG Y, LU B, et al. LIVER: a tightly coupled lidar-inertial-visual state estimator with high robustness for underground environments[J]. IEEE Robotics and Automation Letters, 2024, 9(3): 2399-2406.
[35] REHDER J, SIEGWART R. Camera/IMU calibration revisited[J]. IEEE Sensors Journal, 2017, 17(11): 3257-3268.
[36] KANG M C, YOO C H, UHM K H, et al. A robust extrinsic calibration method for non-contact gaze tracking in the 3-D space[J]. IEEE Access, 2018, 6: 48840-48849.
[37] REHDER J, NIKOLIC J, SCHNEIDER T, et al. Extending kalibr: calibrating the extrinsics of multiple IMUs and of individual axes[C]//Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016: 4304-4311.
[38] FURGALE P, REHDER J, SIEGWART R. Unified temporal and spatial calibration for multi-sensor systems[C]//Proceedings of the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013: 1280-1286.
[39] MAYE J, FURGALE P, SIEGWART R. Self-supervised calibration for robotic systems[C]//Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), 2013: 473-480.
[40] TAO L, HONGWANG D. A camera-IMU system extrinsic parameter calibration method[C]//Proceedings of the 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 2017: 1063-1066.
[41] HOL J D, SCHON T B, GUSTAFSSON F. A new algorithm for calibrating a combined camera and IMU sensor unit[C]//Proceedings of the 2008 10th International Conference on Control, Automation, Robotics and Vision, 2008: 1857-1862.
[42] REBELLO J, LI C, WASLANDER S L. DC-VINS: dynamic camera visual inertial navigation system with online calibration[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021: 2559-2568.
[43] KIM D, SHIN S, KWEON I S. On-line initialization and extrinsic calibration of an inertial navigation system with a relative preintegration method on manifold[J]. IEEE Transactions on Automation Science and Engineering, 2018, 15(3): 1272-1285.
[44] YAN J, DU X, LI H. Research on MIMU online calibration method based on multi-information source[C]//Proceedings of the 2019 IEEE International Conference on Unmanned Systems (ICUS), 2019: 699-703.
[45] TANG D, SHEN L, HU T. Online camera-gimbal-odometry system extrinsic calibration for fixed-wing UAV swarms[J]. IEEE Access, 2019, 7: 146903-146913.
[46] LI M M A. Online temporal calibration for camera-IMU systems: theory and algorithms[J]. The International Journal of Robotics Research, 2014, 33(7): 947-964.
[47] PETIT B, GUILLEMARD R, GAY-BELLILE V. Time shifted IMU preintegration for temporal calibration in incremental visual-inertial initialization[C]//Proceedings of the 2020 International Conference on 3D Vision (3DV), 2020: 171-179.
[48] FERTNER A, SJOLUND A. Comparison of various time delay estimation methods by computer simulation[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1986, 34(5): 1329-1330.
[49] HARRISON A, NEWMAN P. TICSync: knowing when things happened[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Automation, 2011: 356-363.
[50] KELLY J, SUKHATME G S. A general framework for temporal calibration of multiple proprioceptive and exteroceptive sensors[C]//Proceedings of the 12th International Symposium on Experimental Robotics, 2014: 195-209.
[51] QIN T, SHEN S. Online temporal calibration for monocular visual-inertial systems[C]//Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018: 3662-3669.
[52] MARZULLO K, OWICKI S. Maintaining the time in a distributed system[C]//Proceedings of the Second Annual ACM Symposium on Principles of Distributed Computing, 1983: 295-305.
[53] ZAMAN M, ILLINGWORTH J. Interval-based time synchronisation of sensor data in a mobile robot[C]//Proceedings of the 2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, 2004: 463-468.
[54] OLSON E. A passive solution to the sensor synchronization problem[C]//Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010: 1059-1064.
[55] VOGES R, WAGNER B. Timestamp offset calibration for an IMU-camera system under interval uncertainty[C]//Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018: 377-384.
[56] MAIR E, FLEPS M, SUPPA M, et al. Spatio-temporal initialization for IMU to camera registration[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Biomimetics, 2011: 557-564.
[57] LINDENBERGER P, SARLIN P E, POLLEFEYS M. Lightglue: local feature matching at light speed[J]. arXiv:2306.
13643, 2023.
[58] 程珉, 陈临强, 杨全鑫. 基于改进ORB特征的单目视觉SLAM算法[J]. 计算机应用与软件, 2021, 38(10): 242-248.
CHENG M, CHEN L Q, YANG Q X. Monocular visual slam algorithm based on improved ORB feature[J]. Computer Applications and Software, 2021, 38(10): 242-248.
[59] 肖扬, 周军. 图像边缘检测综述[J]. 计算机工程与应用, 2023, 59(5): 40-54.
XIAO Y, ZHOU J. Overview of image edge detection[J]. Computer Engineering and Applications, 2023, 59(5): 40-54.
[60] ZHONG F, WANG S, ZHANG Z, et al. Detect-SLAM: making object detection and slam mutually beneficial[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018: 1001-1010.
[61] 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.
[62] 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.
[63] CAMPOS C, MONTIEL J M, TARDóS J D. Inertial-only optimization for visual-inertial initialization[C]//Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: 51-57.
[64] MARTINELLI A. Closed-form solution of visual-inertial structure from motion[J]. International Journal of Computer Vision, 2014, 106: 138-152.
[65] WEI H, ZHANG T, ZHANG L. A fast analytical two-stage initial-parameters estimation method for monocular-inertial navigation[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-12.
[66] MARTINELLI A. Observability properties and deterministic algorithms in visual-inertial structure from motion[J]. Foundations and Trends in Robotics, 2014, 3(3): 139-209.
[67] MARTINELLI A. Vision and IMU data fusion: closed-form solutions for attitude, speed, absolute scale, and bias determination[J]. IEEE Transactions on Robotics, 2012, 28(1): 44-60.
[68] ZU?IGA-NO?L D, MORENO F A, GONZALEZ-JIMENEZ J. An analytical solution to the IMU initialization problem for visual-inertial systems[J]. IEEE Robotics and Automation Letters, 2021, 6(3): 6116-6122.
[69] NISTER D, NARODITSKY O, BERGEN J. Visual odometry[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004: 652-659.
[70] DONG-SI T C, MOURIKIS A I. Estimator initialization in vision-aided inertial navigation with unknown camera-IMU calibration[C]//Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012: 1064-1071.
[71] MUR-ARTAL R, TARDóS J D. Visual-inertial monocular slam with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2): 796-803.
[72] JUNG J H, CHUNG J Y, CHA J, et al. Rapid initialization using relative pose constraints in stereo visual-inertial odometry[C]//Proceedings of the 2019 IEEE 15th International Conference on Control and Automation (ICCA), 2019: 969-974.
[73] ZHENG T, ZUO G, XU Z, et al. Rotation matrix oriented visual inertial online initialization[C]//Proceedings of the 2020 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2020: 128-133.
[74] HUANG W, LIU H. Online initialization and automatic camera-IMU extrinsic calibration for monocular visual-inertial SLAM[C]//Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018: 5182-5189.
[75] 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.
[76] 王文森, 黄凤荣, 王旭, 等. 基于深度学习的视觉惯性里程计技术综述[J]. 计算机科学与探索, 2023, 17(3): 549-560.
WANG W S, HUANG F R, WANG X, et al. Overview of visual inertial odometry technology based on deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(3): 549-560.
[77] PAN Y, ZHOU W, CAO Y, et al. Adaptive VIO: deep visual-inertial odometry with online continual learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 18019-18028.
[78] KRICHEN M. Generative adversarial networks[C]//Proceedings of the 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2023: 1-7.
[79] TIAN C, XU Y, LI Z, et al. Attention-guided CNN for image denoising[J]. Neural Networks, 2020, 124: 117-129.
[80] BROSSARD M, BARRAU A, BONNABEL S. AI-IMU dead-reckoning[J]. IEEE Transactions on Intelligent Vehicles, 2020, 5(4): 585-595.
[81] ZHANG M, ZHANG M, CHEN Y, et al. IMU data processing for inertial aided navigation: a recurrent neural network based approach[C]//Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021: 3992-3998.
[82] BUCHANAN R, AGRAWAL V, CAMURRI M, et al. Deep IMU bias inference for robust visual-inertial odometry with factor graphs[J]. IEEE Robotics and Automation Letters, 2023, 8(1): 41-48.
[83] LI R, FU C, YI W, et al. Calib-Net: calibrating the low-cost IMU via deep convolutional neural network[J]. Front Robot AI, 2022, 8: 772583.
[84] GAO Y, SHI D, LI R, et al. Gyro-Net: IMU gyroscopes random errors compensation method based on deep learning[J]. IEEE Robotics and Automation Letters, 2023, 8(3): 1471-1478.
[85] DUSMANU M, ROCCO I, PAJDLA T, et al. D2-Net: a trainable cnn for joint description and detection of local features[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 8084-8093.
[86] DETONE D, MALISIEWICZ T, RABINOVICH A. SuperPoint: self-supervised interest point detection and description[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018: 337-33712.
[87] WANG K, ZHANG C, SUN K, et al. VINS-FEN: monocular visual-inertial slam based on feature extraction network[C]//Proceedings of the 2023 7th International Conference on Machine Vision and Information Technology (CMVIT), 2023: 86-91.
[88] YANG M, CHEN Y, KIM H S. Efficient deep visual and inertial odometry with adaptive visual modality selection[C]//Proceedings of the 17th European Conference on Computer Visio. Cham: Springer Nature Switzerland, 2022: 233-250.
[89] HAN L, LIN Y, DU G, et al. DeepVIO: self-supervised deep learning of monocular visual inertial odometry using 3D geometric constraints[C]//Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019: 6906-6913.
[90] CLARK R, WANG S, WEN H, et al. VINet: visual-inertial odometry as a sequence-to-sequence learning problem[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2017: 3995-4001.
[91] LIU L, LI G, LI T H. ATVIO: attention guided visual-inertial odometry[C]//Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021: 4125-4129.
[92] ALMALIOGLU Y, TURAN M, SAPUTRA M R U, et al. SelfVIO: self-supervised deep monocular visual-inertial odometry and depth estimation[J]. Neural Networks, 2022, 150: 119-136.
[93] CHEN J, ZHANG S, LI Z, et al. Gravity-Shift-VIO: adaptive acceleration shift and multi-modal fusion with transformer in visual-inertial odometry[C]//Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN), 2023: 1-8.
[94] MOURIKIS A I, ROUMELIOTIS S I. A multi-state constraint kalman filter for vision-aided inertial navigation[C]//Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007: 3565-3572.
[95] SUN K, MOHTA K, PFROMMER B, et al. Robust stereo visual inertial odometry for fast autonomous flight[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 965-972.
[96] HUANG G P, MOURIKIS A I, ROUMELIOTIS S I. A first-estimates Jacobian EKF for improving SLAM consistency[C]//Proceedings of the Eleventh International Symposium on Experimental Robotics, 2009: 373-382.
[97] GENEVA P, ECKENHOFF K, LEE W, et al. OpenVINS: a research platform for visual-inertial estimation[C]//Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: 4666-4672.
[98] LI J, BAO H, ZHANG G. Rapid and robust monocular visual-inertial initialization with gravity estimation via vertical edges[C]//Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019: 6230-6236.
[99] 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.
[100] 齐锦博. 造船起重机检测爬壁机器人视觉惯性SLAM的研究[D]. 上海: 上海电机学院, 2022.
QI J B. Research on visual-inertial SLAM of ship-building crane detection wall-climbing robot[D]. Shanghai: Shanghai Dianji University, 2022.
[101] MUR-ARTAL R, MONTIEL J M M, TARDóS J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5): 1147-1163.
[102] HORN B K P. Closed-form solution of absolute orientation using unit quaternions[J]. Journal of The Optical Society of America Aoptics Image Science and Vision, 1987, 4: 629-642.
[103] 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.
[104] CAMPOS C, ELVIRA R, RODRíGUEZ J J G, et al. ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM[J]. IEEE Transactions on Robotics, 2021, 37(6): 1874-1890.
[105] ELVIRA R, TARDóS J D, MONTIEL J. ORBSLAM-Atlas: a robust and accurate multi-map system[C]//Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019: 6253-6259.
[106] URBAN S, LEITLOFF J, HINZ S. MLPnP—a real-time maximum likelihood solution to the perspective-n-point problem[J]. arXiv:1607.08112, 2016.