期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 37, 期 6, 页码 1874-1890出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2021.3075644
关键词
Simultaneous localization and mapping; Visualization; Cameras; Feature extraction; Sensor systems; Robustness; Optimization; Computer vision; inertial navigation; simult- aneous localization and mapping
类别
资金
- Spanish government [PGC2018-096367-B-I00, DPI2017-91104-EXP]
- Aragn government [DGA-T45-17R]
ORB-SLAM3 is the first system capable of performing various SLAM tasks, including visual, visual-inertial, and multi-map SLAM, with improved accuracy and robustness, while also being able to survive in situations with poor visual information and achieve high accuracy.
This article presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multimap SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models. The first main novelty is a tightly integrated visual-inertial SLAM system that fully relies on maximum a posteriori (MAP) estimation, even during IMU initialization, resulting in real-time robust operation in small and large, indoor and outdoor environments, being two to ten times more accurate than previous approaches. The second main novelty is a multiple map system relying on a new place recognition method with improved recall that lets ORB-SLAM3 survive to long periods of poor visual information: when it gets lost, it starts a new map that will be seamlessly merged with previous maps when revisiting them. Compared with visual odometry systems that only use information from the last few seconds, ORB-SLAM3 is the first system able to reuse in all the algorithm stages all previous information from high parallax co-visible keyframes, even if they are widely separated in time or come from previous mapping sessions, boosting accuracy. Our experiments show that, in all sensor configurations, ORB-SLAM3 is as robust as the best systems available in the literature and significantly more accurate. Notably, our stereo-inertial SLAM achieves an average accuracy of 3.5 cm in the EuRoC drone and 9 mm under quick hand-held motions in the room of TUM-VI dataset, representative of AR/VR scenarios. For the benefit of the community we make public the source code.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据