1.武汉大学测绘学院,湖北 武汉,430079
2.武汉大学地球空间环境与大地测量教育部重点实验室,湖北 武汉,430079
赵奕澎,硕士,研究方向为多传感器融合定位。2018302141345@whu.edu.cn
王鑫哲,博士,助理研究员。Wxz_gnss@whu.edu.cn
收稿:2025-02-11,
纸质出版:2026-05-05
移动端阅览
赵奕澎,姚宜斌,王鑫哲.利用ArUco码的单目VIO快速初始化算法[J].武汉大学学报(信息科学版),2026,51(5):979-986.
ZHAO Yipeng ,YAO Yibin ,WANG Xinzhe .A Fast Initialization Algorithm for Monocular VIO Using ArUco Markers[J].Geomatics and Information Science of Wuhan University,2026,51(5):979-986.
赵奕澎,姚宜斌,王鑫哲.利用ArUco码的单目VIO快速初始化算法[J].武汉大学学报(信息科学版),2026,51(5):979-986. DOI:10.13203/j.whugis20240174
ZHAO Yipeng ,YAO Yibin ,WANG Xinzhe .A Fast Initialization Algorithm for Monocular VIO Using ArUco Markers[J].Geomatics and Information Science of Wuhan University,2026,51(5):979-986. DOI:10.13203/j.whugis20240174
针对目前单目视觉惯性里程计(visual inertial odometry,VIO)算法初始化对设备运动状态和视觉观测条件要求较为严格,在工程应用中难以保证的问题,提出了一种利用ArUco码辅助的单目VIO快速初始化算法。该算法结合ArUco码已知的边长信息,通过边长约束恢复深度信息并获取相机与ArUco码之间的空间关系。同时结合惯性测量单元(inertial measurement unit
IMU)静止初始化流程与事先标定的相机与IMU之间的外参,实现全局坐标系与ArUco码之间空间关系的获取,完成初始化流程。实验结果表明,算法角点深度恢复误差平均值为0.75 mm,相比VINS-Fusion、OpenVINS及ORB-SLAM3的单目VIO方案的初始化算法,在效率及对后续VIO的收敛帮助上有着更好的表现,初始化后小范围2 m内VIO定位误差为0.009 m,姿态精度为0.4°,且对单目VIO整体轨迹精度带来一定程度的提升。
Objectives
2
Current monocular visual inertial odometry (VIO) algorithms impose stringent requirements on device motion states and visual observation conditions during initialization
which are often challenging to meet in real-world engineering applications. A fast and stable initialization method is thus essential.
Methods
2
The proposed method utilizes the known edge length of ArUco markers to recover depth information through edge length constraints
thereby estimating the spatial relationship between the camera and the ArUco markers. Concurrently
the inertial measurement unit (IMU) is initialized under stationary conditions. By incorporating the pre-calibrated extrinsic transformation between the camera and IMU
the spatial relationship between the global coordinate system and the ArUco markers is established.
Results
2
The accuracy of depth recovery at corner points was validated using profiles of the differences between the measured distance of two points and the recovered depth. Multiple experiments under both well-lit and low-light conditions showed that the mean error of this difference was 0.75 mm. The VIO positioning accuracy of the device within a certain spatial range after initialization was further evaluated
and several experiments demonstrated a positioning error of 0.009 m and an attitude error of 0.4°. Additional experiments were conducted to assess the stability and efficiency of the proposed method. Compared with the monocular VIO initialization methods used in VINS-Fusion
OpenVINS
and ORB-SLAM3
the proposed method achieved higher stability and efficiency
while also yielding a better overall trajectory in the subsequent VIO process.
Conclusions
2
The proposed method demonstrates high efficiency and robustness in initialization
with notable improvements in positioning accuracy during subsequent VIO tracking.
ZHAO J W , WU Y B , BAO W , et al . Indoor Robot Mapping and Navigation System Based on Cyber-Physical Systems: Integration of SLAM Algorithm and Visual Information [J]. IEEE Transactions on Intelligent Transportation Systems , 2025 , 1 - 11 .
崔晓珍 , 周琪 , 武东杰 , 等 . GNSS/IMU与里程计紧-松耦合的因子图融合定位方法 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 10 ): 1911 - 1921 .
CUI Xiaozhen , ZHOU Qi , WU Dongjie , et al . Factor Graph Fusion Localization Method with Tight and Loose Coupling of GNSS/IMU and Odometry [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 10 ): 1911 - 1921 .
辜声峰 , 戴春齐 , 何成鹏 , 等 . 面向城市车载导航的多系统PPP-RTK/VIO半紧组合算法性能分析 [J]. 武汉大学学报(信息科学版) , 2021 , 46 ( 12 ): 1852 - 1861 .
GU Shengfeng , DAI Chunqi , HE Chengpeng , et al . Analysis of Semi-Tightly Coupled Multi-GNSS PPP-RTK/VIO for Vehicle Navigation in Urban Areas [J]. Geomatics and Information Science of Wuhan University , 2021 , 46 ( 12 ): 1852 - 1861 .
廖健驰 , 李星星 , 冯绍权 . GVIL: 基于图优化的GNSS PPP/视觉/惯性/激光雷达紧组合算法 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 7 ): 1204 - 1215 .
LIAO Jianchi , LI Xingxing , FENG Shaoquan . GVIL: Tightly-Coupled GNSS PPP/Visual/INS/LiDAR SLAM Based on Graph Optimization [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 7 ): 1204 - 1215 .
HE Y J , XU B , OUYANG Z P , et al . A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Vancouver, Canada , 2023 .
MARTINELLI A . Closed-Form Solution of Visual-Inertial Structure from Motion [J]. International Journal of Computer Vision , 2014 , 106 ( 2 ): 138 - 152 .
DOMÍNGUEZ-CONTI J , YIN J F , ALAMI Y , et al . Visual-Inertial SLAM Initialization: A General Linear Formulation and a Gravity-Observing Non-Linear Optimization [C]// IEEE International Symposium on Mixed and Augmented Reality (ISMAR) , Munich, Germany , 2018 .
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 .
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 .
张晨阳 , 杨健 . 一种自适应点线特征和IMU耦合的视觉SLAM方法 [J]. 武汉大学学报(信息科学版) , 2025 , 50 ( 10 ): 2048 - 2063 .
ZHANG Chenyang , YANG Jian . A Visual SLAM Method Coupled with Adaptive Point-Line Features and IMU [J]. Geomatics and Information Science of Wuhan University , 2025 , 50 ( 10 ): 2048 - 2063 .
史殿习 , 高云琦 , 宋林娜 , 等 . Deep-Init: 基于深度学习的视觉惯性里程计非联合初始化方法 [J]. 计算机科学 , 2024 , 51 ( 7 ): 327 - 336 .
SHI Dianxi , GAO Yunqi , SONG Linna , et al . Deep-Init: Non Joint Initialization Method for Visual Inertial Odometry Based on Deep Learning [J]. Computer Science , 2024 , 51 ( 7 ): 327 - 336 .
ZHOU Y W , KAR A , TURNER E , et al . Learned Monocular Depth Priors InVisual-Inertial Initialization [C]// Computer Vision-ECCV , Switzerland , 2022 .
牛小骥 , 王庭蔚 , 葛雯斐 , 等 . 一种基于视觉二维码/惯性融合的室内高精度定位定姿方法 [J]. 中国惯性技术学报 , 2023 , 31 ( 11 ): 1067 - 1075 .
NIU Xiaoji , WANG Tingwei , GE Wenfei , et al . A High Precision Indoor Positioning and Attitude Determination Method Based on Visual Two-Dimensional Code/Inertial Information [J]. Journal of Chinese Inertial Technology , 2023 , 31 ( 11 ): 1067 - 1075 .
邢伯阳 , 潘峰 , 冯肖雪 . ArUco-SLAM: 基于ArUco二维码阵列的单目实时建图定位系统 [J]. 北京理工大学学报 , 2020 , 40 ( 4 ): 427 - 433 .
XING Boyang , PAN Feng , FENG Xiaoxue . ArUco-SLAM: A Monocular SLAM System Based on ArUco Landmark Array [J]. Transactions of Beijing Institute of Technology , 2020 , 40 ( 4 ): 427 - 433 .
王甫红 , 栾梦杰 , 程雨欣 , 等 城市环境下智能手机车载GNSS/MEMS IMU紧组合定位算法 [J]. 武汉大学学报 (信息科学版) , 2023 , 48 ( 7 ): 1106 - 1116 .
WANG Fuhong , LUAN Mengjie , CHENG Yuxin , et al . Smartphone GNSS/MEMS IMU Tightly-Coupled Integration Positioning Method for Vehicular Navigation in Urban Conditions [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 7 ): 1106 - 1116 .
ZHANG Q Y , XU X B , SHI F Y , et al . An Integrated Positioning Method with IMU/UWB Based on Geometric Constraints of Foot-to-Foot Distances [J]. Measurement , 2025 , 242 : 115771 .
YIN J , LI A , XI W , et al . Ground-Fusion: A Low-Cost Ground SLAM System Robust to Corner Cases [C]// IEEE International Conference on Robotics and Automation (ICRA) , Yokohama, Japan , 2024 .
GENEVA P , ECKENHOFF K , LEE W , et al . OpenVINS: A Research Platform for Visual-Inertial Estimation [C]// IEEE International Conference on Robotics and Automation (ICRA) , Paris, France , 2020 .
高翔 , 张涛 , 刘毅 , 等 . 视觉SLAM十四讲: 从理论到实践 [M]. 北京 : 电子工业出版社 , 2017 .
GAO Xiang , ZHANG Tao , LIU Yi , et al . Fourteen Lectures on Visual SLAM: From Theory to Practice [M]. Beijing : Publishing House of Electronics Industry , 2017 .
AGARWAL S , MIERLE K . Ceres Solver [EB/OL]. ( 2023-01-01 ) [ 2024-08-11 ]. http://ceres-solver.org/tutorial.html http://ceres-solver.org/tutorial.html .
FURGALE P , REHDER J , SIEGWART R . Unified Temporal and Spatial Calibration for Multi-Sensor Systems [C]// IEEE/RSJ International Conferen‑ ce on Intelligent Robots and Systems, Tokyo, Japan , 2013 .
葛雯斐 , 牛小骥 , 蒋郡祥 , 等 . 智能手机利用二维码路标进行定位定姿的方法研究 [J]. 传感技术学报 , 2019 , 32 ( 12 ): 1816 - 1823 .
GE Wenfei , NIU Xiaoji , JIANG Junxiang , et al . Research on Position and Posture Determination of SmartPhone Using 2D Code Landmark [J]. Chinese Journal of Sensors and Actuators , 2019 , 32 ( 12 ): 1816 - 1823 .
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621