ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Authors:
Top Cited Papers
- 12 June 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 33 (5) , 1255-1262
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.Keywords
All Related Versions
Funding Information
- Spanish Government (DPI2015-67275)
- Aragón Regional Government (DGA T04-FSE)
- Ministerio de Educación Scholarship (FPU13/04175)
This publication has 21 references indexed in Scilit:
- ElasticFusion: Real-time dense SLAM and light source estimationThe International Journal of Robotics Research, 2016
- Stereo parallel tracking and mapping for robot localization2015
- Large-scale direct SLAM with stereo cameras2015
- Real-time large-scale dense RGB-D SLAM with volumetric fusionThe International Journal of Robotics Research, 2014
- Fast relocalisation and loop closing in keyframe-based SLAM2014
- Dense visual SLAM for RGB-D cameras2013
- 3-D Mapping With an RGB-D CameraIEEE Transactions on Robotics, 2013
- Bags of Binary Words for Fast Place Recognition in Image SequencesIEEE Transactions on Robotics, 2012
- ORB: An efficient alternative to SIFT or SURF2011
- KinectFusion: Real-time dense surface mapping and tracking2011