Improved Point-Line Visual-Inertial Odometry System Using Helmert Variance Component Estimation

被引:11
|
作者
Xu, Bo [1 ]
Chen, Yu [1 ]
Zhang, Shoujian [1 ]
Wang, Jingrong [2 ]
机构
[1] Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Peoples R China
[2] Wuhan Univ, GNSS Res Ctr, Wuhan 430079, Peoples R China
基金
国家重点研发计划;
关键词
visual-inertial odometry; Helmert variance component estimation; line feature matching method; correlation coefficient; point and line features; ROBUST;
D O I
10.3390/rs12182901
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Mobile platform visual image sequence inevitably has large areas with various types of weak textures, which affect the acquisition of accurate pose in the subsequent platform moving process. The visual-inertial odometry (VIO) with point features and line features as visual information shows a good performance in weak texture environments, which can solve these problems to a certain extent. However, the extraction and matching of line features are time consuming, and reasonable weights between the point and line features are hard to estimate, which makes it difficult to accurately track the pose of the platform in real time. In order to overcome the deficiency, an improved effective point-line visual-inertial odometry system is proposed in this paper, which makes use of geometric information of line features and combines with pixel correlation coefficient to match the line features. Furthermore, this system uses the Helmert variance component estimation method to adjust weights between point features and line features. Comprehensive experimental results on the two datasets of EuRoc MAV and PennCOSYVIO demonstrate that the point-line visual-inertial odometry system developed in this paper achieved significant improvements in both localization accuracy and efficiency compared with several state-of-the-art VIO systems.
引用
收藏
页数:20
相关论文
共 50 条
  • [31] HTSR-VIO: Real-Time Line-Based Visual-Inertial Odometry With Point-Line Hybrid Tracking and Structural Regularity
    Zhang, Bing
    Wang, Yankun
    Yao, Weiran
    Sun, Guanghui
    IEEE SENSORS JOURNAL, 2024, 24 (07) : 11024 - 11035
  • [32] A Tightly Coupled Visual-Inertial GNSS State Estimator Based on Point-Line Feature
    Dong, Bo
    Zhang, Kai
    SENSORS, 2022, 22 (09)
  • [33] IMU Preintegration for Visual-Inertial Odometry Pose Estimation
    Liu, Fuchun
    Su, Xuan
    He, Yun
    Luo, Fei
    Gao, Huanli
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 5305 - 5310
  • [34] Visual-Inertial Odometry Based on Points and Line Segments
    Qiu, Dezhuo
    Fan, Guishuang
    2020 INTERNATIONAL CONFERENCE ON IMAGE, VIDEO PROCESSING AND ARTIFICIAL INTELLIGENCE, 2020, 11584
  • [35] Stereo visual-inertial localization algorithm for orchard robots based on point-line features
    Xu, Xing
    Liang, Jinming
    Li, Jianying
    Wu, Guang
    Duan, Jieli
    Jin, Mohui
    Fu, Han
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 224
  • [36] DPLVO: Direct Point-Line Monocular Visual Odometry
    Zhou, Lipu
    Wang, Shengze
    Kaess, Michael
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) : 7113 - 7120
  • [37] LRPL-VIO: A Lightweight and Robust Visual-Inertial Odometry with Point and Line Features
    Zheng, Feixiang
    Zhou, Lu
    Lin, Wanbiao
    Liu, Jingyang
    Sun, Lei
    SENSORS, 2024, 24 (04)
  • [38] A Real-Time Visual-Inertial Monocular Odometry by Fusing Point and Line Features
    Li, Chengwei
    Yan, Liping
    Xia, Yuanqing
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 4085 - 4090
  • [39] EDPLVO: Efficient Direct Point-Line Visual Odometry
    Zhou, Lipu
    Huang, Guoquan
    Mao, Yinian
    Wang, Shengze
    Kaess, Michael
    2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 7559 - 7565
  • [40] Point-Line Feature Fusion in Monocular Visual Odometry
    Yuan Meng
    Li Aihua
    Zheng Yong
    Cui Zhigao
    Bao Zhengqiang
    LASER & OPTOELECTRONICS PROGRESS, 2018, 55 (02)