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.

This paper presents ORB-SLAM, a feature-based monocular simultaneous localization and mapping (SLAM) system that operates in real time, in small and large indoor and outdoor environments. The system is robust to severe motion clutter, allows wide baseline loop closing and relocalization, and includes full automatic initialization. Building on excellent algorithms of recent years, we designed from scratch a novel system that uses the same features for all SLAM tasks: tracking, mapping, relocalization, and loop closing. A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation. We present an exhaustive evaluation in 27 sequences from the most popular datasets. ORB-SLAM achieves unprecedented performance with respect to other state-of-the-art monocular SLAM approaches. For the benefit of the community, we make the source code public.

In this paper we present for the first time a relocalisation method for keyframe-based SLAM that can deal with severe viewpoint change, at frame-rate, in maps containing thousands of keyframes. As this method relies on local features, it permits the interoperability between cameras, allowing a camera to relocalise in a map built by a different camera. We also perform loop closing (detection + correction), at keyframerate, in loops containing hundreds of keyframes. For both relocalisation and loop closing, we propose a bag of words place recognizer with ORB features, which is able to recognize places spending less than 39 ms, including feature extraction, in databases containing 10K images (without geometrical verification). We evaluate the performance of this recognizer in four different datasets, achieving high recall and no false matches, and getting better results than the state-of-art in place recognition, being one order of magnitude faster.