ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Most SLAM methods represent the scene as a set of sparse 3D landmarks corresponding to discriminative features in the environment (e.g., lines, corners) [179]”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [179]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 3×
“This reduced in more than one order of magnitude the time needed for feature extraction, compared with SURF [18] and SIFT [19] features that were used in bags of words approaches so far.”
MethodMultiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
ORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037 · cited 3×
“We chose ORB [9], which are oriented multiscale FAST corners with a 256-bit descriptor associated.”
BackgroundMethodVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 3×
“The odometry benchmark from the KITTI dataset [40] contains 11 sequences from a car driven around a residential area with accurate ground truth from GPS and a Velodyne laser scanner.”
MethodMachine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555 · cited 1×
“DBoW2 [5] used for the first time bags of binary words obtained from BRIEF descriptors [16] along with the very efficient FAST feature detector [17].”
MethodParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346 · cited 7×
“The most representative keyframe-based SLAM system is probably PTAM by Klein and Murray [4].”
MethodInfluentialClosed-form solution of absolute orientation using unit quaternions
Horn, B. K. P. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.000629 · Cited by 4,116
Bundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988 · cited 3×
“BUNDLE adjustment (BA) is known to provide accurate estimates of camera localizations as well as a sparse geometrical reconstruction [1], [2], given that a strong network of matches and good initial guesses are provided.”
BackgroundInfluentialA benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385773 · Cited by 3,976 · cited 6×
“Reconstruction and graphs in the sequence fr3 long off ice household from the TUM RGB-D Benchmark [38].”
BackgroundMethodInfluentialMonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959 · cited 2×
“Monocular SLAM was initially solved by filtering [20], [21], [29], [30].”
BackgroundMethodLSD-SLAM: Large-scale direct monocular SLAM
Engel, J., Schöps, T., & Cremers, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_54 · Cited by 3,851 · cited 15×
“Notably, we achieve better camera localization accuracy than the state of the art in direct methods [10], which optimize directly over pixel intensities instead”
MethodInfluentialBRIEF: Binary Robust Independent Elementary Features
Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_56 · Cited by 3,597 · cited 5×
“DBoW2 [5] used for the first time bags of binary words obtained from BRIEF descriptors [16] along with the very efficient FAST feature detector [17].”
MethodInfluentialScalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579 · cited 1×
“Within appearance-based methods, bags of words techniques [14], such as the probabilistic approach FAB-MAP [15], are to the fore because of their high efficiency.”
MethodEPnP: An Accurate O(n) Solution to the PnP Problem
Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0152-6 · Cited by 3,298
SVO: Fast semi-direct monocular visual odometry
Forster, C., Pizzoli, M., & Scaramuzza, D. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906584 · Cited by 2,205 · cited 1×
“Initialization methods from two views either assume locally scene planarity [4], [22] and recover the relative camera pose from a homography using the method of Faugeras and Lustman”
MethodDTAM: Dense tracking and mapping in real-time
Newcombe, R. A., Lovegrove, S. J., & Davison, A. J. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126513 · Cited by 2,078 · cited 3×
“Finally, because direct methods are, in general, very computationally demanding, the map is just incrementally expanded as in DTAM, or map optimization is reduced to a pose graph, discarding all sensor measurements as in LSD-SLAM.”
MethodAn efficient solution to the five-point relative pose problem
Nister, D. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.17 · Cited by 2,009 · cited 4×
“Initialization methods from two views either assume locally scene planarity [4], [22] and recover the relative camera pose from a homography using the method of Faugeras and Lustman [23], or compute an essential matrix [24], [25] that models planar and general scenes, using the five-point algorithm of Nistér [26], wh…”
MethodInfluentialG2o: A general framework for graph optimization
Kummerle, R., Grisetti, G., Strasdat, H., Konolige, K., & Burgard, W. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5979949 · Cited by 1,982 · cited 2×
“We use the Levenberg–Marquardt algorithm implemented in g2o [37] to carry out all optimizations.”
BackgroundMethodBags of Binary Words for Fast Place Recognition in Image Sequences
Galvez-López, D., & Tardos, J. D. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2197158 · Cited by 1,913 · cited 14×
“In this study, we build on the main ideas of PTAM, the place recognition work of Gálvez-López and Tardós [5], the scaleaware loop closing of Strasdat et al.”
BackgroundMethodInfluentialFast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces
Alcantarilla, P., Nuevo, J., & Bartoli, A. (2013) · Procedings of the British Machine Vision Conference 2013 · doi:10.5244/c.27.13 · Cited by 1,173 · cited 1×
“We require features that need for extraction much less than 33 ms per image, which excludes the popular SIFT (∼ 300 ms) [19], SURF (∼ 300 ms) [18], or the recent A-KAZE (∼ 100 ms) [35].”
Method3-D Mapping With an RGB-D Camera
Endres, F., Hess, J., Sturm, J., Cremers, D., & Burgard, W. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2279412 · Cited by 820 · cited 1×
“We compare also with the trajectories generated by RGBDSLAM [43], which are provided for some of the sequences in the benchmark website.”
MethodInverse Depth Parametrization for Monocular SLAM
Civera, J., Davison, A. J., & Montiel, J. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2003276 · Cited by 779 · cited 3×
“These points, which are not seen with sufficient parallax and our system does not include in the map, are very informative of the rotation of the camera [21].”
BackgroundMethodSelf-citationAppearance-only SLAM at large scale with FAB-MAP 2.0
Cummins, M., & Newman, P. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364910385483 · Cited by 609 · cited 2×
“While our current implementation makes use of ORB, the techniques proposed are not restricted to these features.”
MethodMOTION AND STRUCTURE FROM MOTION IN A PIECEWISE PLANAR ENVIRONMENT
FAUGERAS, O. D., & LUSTMAN, F. (1988) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001488000285 · Cited by 528 · cited 4×
“Initialization methods from two views either assume locally scene planarity [4], [22] and recover the relative camera pose from a homography using the method of Faugeras and Lustman [23], or compute an essential matrix [24], [25] that models planar and general scenes, using the five-point algorithm of Nistér [26], wh…”
MethodInfluentialStrasdat, H., Montiel, J. M. M., & Davison, A. J. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.02.009 · Cited by 439
Self-citationReal Time Localization and 3D Reconstruction
Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., & Sayd, P. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) · doi:10.1109/cvpr.2006.236 · Cited by 396 · cited 4×
“On the other hand, keyframe-based approaches [3], [4] estimate the map using only selected frames (keyframes) allowing to perform more costly but accurate BA optimizations, as mapping is not tied to frame rate.”
BackgroundMethodInfluentialEade, E., & Drummond, T. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.263 · Cited by 396 · cited 1×
“Monocular SLAM was initially solved by filtering [20], [21], [29], [30].”
MethodImproving the Agility of Keyframe-Based SLAM
Klein, G., & Murray, D. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88688-4_59 · Cited by 335 · cited 1×
“The original version was later improved with edge features, a rotation estimation step during tracking, and a better relocalization method [32].”
MethodStructure from motion causally integrated over time
Chiuso, A., Favaro, P., Jin, H., & Soatto, S. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.993559 · Cited by 324 · cited 1×
“Monocular SLAM was initially solved by filtering [20], [21], [29], [30].”
MethodScale Drift-Aware Large Scale Monocular SLAM
Strasdat, H., M. M. Montiel, J., & Davison, A. (2010) · Robotics: Science and Systems VI · doi:10.15607/rss.2010.vi.010 · Cited by 323
Self-citationThe New College Vision and Laser Data Set
Smith, M., Baldwin, I., Churchill, W., Paul, R., & Newman, P. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909103911 · Cited by 311
Double window optimisation for constant time visual SLAM
Strasdat, H., Davison, A. J., Montiel, J. M. M., & Konolige, K. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126517 · Cited by 296 · cited 6×
“[6], [7], the optimization framework g2o by Kuemmerle et al.”
BackgroundMethodInfluentialSelf-citationA comparison of loop closing techniques in monocular SLAM
Williams, B., Cummins, M., Neira, J., Newman, P., Reid, I., & Tardós, J. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.06.010 · Cited by 283 · cited 1×
“[13] compared several approaches for place recognition and concluded that techniques based on appearance, that is, image-to-image matching, scale better in large environments than map-to-map or image-tomap methods.”
Fast relocalisation and loop closing in keyframe-based SLAM
Mur-Artal, R., & Tardos, J. D. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906953 · Cited by 264 · cited 5×
“correspondences with an orientation consistency test (see [11] for details) that discards outliers ensuring a coherent rotation for all correspondences.”
BackgroundMethodInfluentialSelf-citationRobust monocular SLAM in dynamic environments
Tan, W., Liu, H., Dong, Z., Zhang, G., & Bao, H. (2013) · 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2013.6671781 · Cited by 249 · cited 2×
“[24], where keyframes were discarded after a process of change detection.”
MethodFeature Based Methods for Structure and Motion Estimation
Torr, P. H. S., & Zisserman, A. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_19 · Cited by 242 · cited 4×
“[46] P. H. Torr and A. Zisserman, “Feature based methods for structure and motion estimation,” in Vision Algorithms: Theory and Practice.”
InfluentialThe Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences
Torr, P. H. S., Fitzgibbon, A. W., & Zisserman, A. (1999) · International Journal of Computer Vision · doi:10.1023/a:1008140928553 · Cited by 156 · cited 1×
“In this study, we use an improved version of that place recognizer, using covisibility information and returning several hypotheses when querying the database instead of just the best match.”
MethodProbabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM
Mur-Artal, R., & Tardós, J. D. (2015) · Robotics: Science and Systems Conference · doi:10.15607/rss.2015.xi.041 · Cited by 140 · cited 1×
“A first effort in this line is presented in [47].”
BackgroundSelf-citationLDB: An ultra-fast feature for scalable Augmented Reality on mobile devices
Yang, X., & Cheng, K.-T. T. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402537 · Cited by 128 · cited 2×
“[36] X. Yang and K.-T. Cheng, “LDB: An ultra-fast feature for scalable augmented reality on mobile devices,” in Proc.”
MethodAccurate visual odometry from a rear parking camera
Lovegrove, S. J., Davison, A. J., & Ibañez‐Guzmán, J. (2011) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2011.5940546 · Cited by 89 · cited 1×
“high-frequency texture like asphalt [45].”
The reconstruction of a plane surface from two perspective projections
Longuet-Higgins, H. C. (1986) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.1986.0030 · Cited by 84 · cited 3×
“, the twofold ambiguity described in [27].”
BackgroundMethodInfluentialChristopher Mei, A., Sibley, G., & Newman, P. M. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652266 · Cited by 66 · cited 1×
“[6], and the use of covisibility information for large-scale operation [7], [8], to design from scratch ORB-SLAM, i.”
BackgroundReal-time 6-DOF monocular visual SLAM in a large-scale environment
Lim, H., Lim, J., & Kim, H. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907055 · Cited by 61 · cited 2×
“[23], or compute an essential matrix [24], [25] that models planar and general scenes, using the five-point algorithm of Nistér [26], which requires to deal with multiple solutions.”
MethodCD SLAM - Continuous localization and mapping in a dynamic world
Pirker, K., Rüther, M., & Bischof, H. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094588 · Cited by 55 · cited 1×
“We delay the initialization until the method produces a unique solution with significant parallax.”
MethodParallel, real-time monocular visual odometry
Song, S., Chandraker, M. K., & Guest, C. C. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631246 · Cited by 54 · cited 1×
“[34] uses ORB features for tracking and a temporal sliding window BA back-end.”
Method
Cited by
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Mur-Artal, R., & Tardos, J. D. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2705103 · Cited by 6,898
“Left: Monocular ORB-SLAM [1], right: ORB-SLAM2 (stereo).”
BackgroundMethodResultInfluentialSelf-citationVINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
Qin, T., Li, P., & Shen, S. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2853729 · Cited by 4,669
“ORB-SLAM [4] is able to close loops and reuse the map, which takes advantage of Bag-of-World [6].”
BackgroundMethodInfluentialORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM
Campos, C., Elvira, R., Rodriguez, J. J. G., M. Montiel, J. M., & D. Tardos, J. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3075644 · Cited by 4,274
Self-citationPast, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
“They allow to build accurate and robust SLAM systems with automatic relocation and loop closing [179].”
InfluentialSuperPoint: Self-Supervised Interest Point Detection and Description
DeTone, D., Malisiewicz, T., & Rabinovich, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00060 · Cited by 3,355
Metadata
- Authors
- Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D.
- Affiliations
- Universidad de Zaragoza (ES)
- Venue
- IEEE Transactions on Robotics
- Published
- 2015-10
- Volume
- 31
- Issue
- 5
- Pages
- 1147-1163
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W1612997784
- Cited by
- 6,778
- References
- 46
- Citations by year
- 2026: 441 · 2025: 784 · 2024: 857 · 2023: 847 · 2022: 776 · 2021: 738 · 2020: 672 · 2019: 653 · 2018: 528 · 2017: 353 · 2016: 119 · 2015: 10
- FWCI
- 487.97
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Dirección General de Investigación of Spain (DPI2012-32168)
- Ministerio de Educación Scholarship (FPU13/04175)
- Gobierno de Aragón Scholarship (B121/13)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- ORB-SLAM, monocular SLAM, SLAM, feature-based SLAM, real-time SLAM, loop closure, relocalization, survival of the fittest, keyframe selection, automatic initialization, indoor and outdoor environments
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.