IEEE Transactions on Robotics
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
✓ Free legal copy found
Preprint, hosted by Cornell University (arxiv.org)
This is the authors’ own version from before peer review, so it may differ from the published paper.
Read the free PDF →Other free copies
Abstract
We present ORB-SLAM2, a complete simultaneous localization and mapping (SLAM) system for monocular, stereo and RGB-D cameras, including map reuse, loop closing, and relocalization capabilities. The system works in real time on standard central processing units in a wide variety of environments from small hand-held indoors sequences, to drones flying in industrial environments and cars driving around a city. Our back-end, based on bundle adjustment with monocular and stereo observations, allows for accurate trajectory estimation with metric scale. Our system includes a lightweight localization mode that leverages visual odometry tracks for unmapped regions and matches with map points that allow for zero-drift localization. The evaluation on 29 popular public sequences shows that our method achieves state-of-the-art accuracy, being in most cases the most accurate SLAM solution. We publish the source code, not only for the benefit of the SLAM community, but with the aim of being an out-of-the-box SLAM solution for researchers in other fields.
DOI: 10.1109/tro.2017.2705103 · Publisher: Institute of Electrical and Electronics Engineers (IEEE)