A Fast and Accurate Visual Inertial Odometry Using Hybrid Point-Line Features
- 1 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (12) , 11345-11352
Abstract
Mainstream visual-inertial SLAM systems use point features for motion estimation and localization. However, point features do not perform well in scenes such as weak texture and motion blur. Therefore, the introduction of line features has received a lot of attention. In this letter, we propose a point-line based real-time monocular visual inertial odometry. Aiming at the problem that most of the current works do not fully utilize the line feature properties, we derive the point-line based hybrid Multi-State Constraint Kalman Filter (hybrid MSCKF) in detail. To further improve the line feature initialization accuracy, we propose a two-step line triangulation method. Since filter-based methods are susceptible to visual outliers, we also propose a redundant line feature removal strategy suitable for the filtering framework. According to the experimental results in EuRoC data set and real environment, the proposed algorithm outperforms other state-of-the-art algorithms in accuracy and real-time performance.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB3903804)
- National Natural Science Foundation of China (62422307, 62273138, 62463020)
This publication has 26 references indexed in Scilit:
- Fast visual inertial odometry with point–line features using adaptive EDLines algorithmMeasurement Science and Technology, 2022
- Lightweight hybrid visual-inertial odometry with closed-form zero velocity updateChinese Journal of Aeronautics, 2020
- Visual-Inertial Odometry with Point and Line Features2019
- Visual-Inertial Navigation: A Concise Review2019
- Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry Using Points and Lines2018
- Robust visual inertial odometry using a direct EKF-based approach2015
- Efficient and consistent vision-aided inertial navigation using line observations2013
- EDLines: A real-time line segment detector with a false detection controlPattern Recognition Letters, 2011
- Structure-from-motion using lines: Representation, triangulation, and bundle adjustmentComputer Vision and Image Understanding, 2005
- Good features to track1994