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].”
BackgroundMethodInfluential
Cited by
Items 701–800 of 1,007
Deep Learning in Mining and Mineral Processing Operations: A Review
Fu, Y., & Aldrich, C. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.712 · Cited by 63
“The most popular vision-based localization method is called the simultaneous localization and mapping (SLAM) algorithm (Mur-Artal et al., 2015).”
MethodDeep Two-View Structure-from-Motion Revisited
Wang, J., Zhong, Y., Dai, Y., Birchfield, S. T., Zhang, K., Smolyanskiy, N., & Li, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00884 · Cited by 85
“Classic approaches to two-view SfM follow a standard pipeline of first matching features/edges between the two images, then inferring motion and geometry from those matches [8, 22, 30, 14, 12, 11, 47, 52].”
MethodORB-TEDM: An RGB-D SLAM Approach Fusing ORB Triangulation Estimates and Depth Measurements
Yuan, J., Zhu, S., Tang, K., & Sun, Q. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3154800 · Cited by 65
Li, Y., Shen, H., Fu, Y., & Wang, K. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124918 · Cited by 62
Autonomous flight and obstacle avoidance of a quadrotor by monocular SLAM
Esrafilian, O., & Taghirad, H. D. (2016) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom.2016.7886853 · Cited by 56
“ORB-SLAM is a sparse and feature-based monocular SLAM system that operates in real time and in wide assortment of indoor and outdoor environments and is robust to rapid motions [5].”
BackgroundEdge SLAM: Edge Points Based Monocular Visual SLAM
Maity, S., Saha, A., & Bhowmick, B. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.284 · Cited by 63
“Therefore, many of the existing SLAMs use geometrical validation of camera poses for reliable initialization of cameras and structure [16, 25].”
BackgroundMethodInfluentialVisual SLAM: Why Bundle Adjust?
Bustos, A. P., Chin, T.-J., Eriksson, A. P., & Reid, I. D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793749 · Cited by 70
“For example, in ORB-SLAM, elaborate map initial-isation heuristics [8, Sec.”
BackgroundInfluentialDeep Keypoint-Based Camera Pose Estimation with Geometric Constraints
Jau, Y.-Y., Zhu, R., Su, H., & Chandraker, M. K. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341229 · Cited by 72
“[14], [15], sparse keypoints for images are detected and described in order to form a set of correspondences.”
BackgroundLin, J., Liu, X., & Zhang, F. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340790 · Cited by 58
“Though visual SLAM has been widely applied in exploration and navigation tasks [4, 5], LiDAR SLAM [6]–[8] is still of significant essence.”
MethodTraining a Convolutional Neural Network for Appearance-Invariant Place RecognitionPreprint
Gomez-Ojeda, R., López-Antequera, M., Petkov, N., & González-Jiménez, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.07428 · Cited by 70
Comparison of modern open-source Visual SLAM approaches
Sharafutdinov, D., Griguletskii, M., Kopanev, P., Kurenkov, M., Ferrer, G., Бурков, А. В., Gonnochenko, A., & Tsetserukou, D. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-01812-7 · Cited by 63
“The second version is an expansion of the first one, hence ORBSLAM1 [49] has not been used.”
BackgroundMethodInfluentialRNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes
Chen, D., Wang, N., Xu, R., Xie, W., Bao, H., & Zhang, G. (2021) · 2021 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar52148.2021.00043 · Cited by 48
“ORB-SLAM [24] is a state-of-the-art visual SLAM system, which divides the system into three modules: camera tracking, local mapping, and loop closure.”
BackgroundFast ORB-SLAM Without Keypoint Descriptors
Fu, Q., Yu, H., Wang, X., Yang, Z., He, Y., Zhang, H., & Mian, A. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3136710 · Cited by 64
“High accuracy and low-computational cost are the two core requirements of visual SLAM [2], [3].”
BackgroundInfluentialRobust image matching via local graph structure consensus
Jiang, X., Xia, Y., Zhang, X.-P. S., & Ma, J. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108588 · Cited by 60
Visual SLAM algorithms and their application for AR, mapping, localization and wayfinding
Theodorou, C., Velisavljević, V., Dyo, V., & Nonyelu, F. (2022) · Array · doi:10.1016/j.array.2022.100222 · Cited by 60
Localization for Intelligent Vehicles in Underground Car Parks Based on Semantic Information
Li, Y., Feng, F., Cai, Y., Li, Z., & Sotelo, M. Á. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3320088 · Cited by 61
“We also used the method in [17] for comparison.”
MethodInfluentialLearning Monocular Visual Odometry through Geometry-Aware Curriculum Learning
Saputra, M. R. U., de Gusmão, P. P. B., Wang, S., Markham, A., & Trigoni, N. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793581 · Cited by 56
“To evaluate the performance of CL-VO, we compare our method with the state-of-the-art feature-based and learningbased VO methods, namely VISO2 [12], ORB-SLAM [28], and DeepVO [4].”
MethodMulti-camera visual SLAM for off-road navigation
Yang, Y. M., Tang, D., Wang, D., Song, W., Wang, J., & Fu, M. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103505 · Cited by 57
OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems
Won, C., Seok, H., Cui, Z., Pollefeys, M., & Lim, J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196695 · Cited by 61
“First, we use the vocabulary tree [39] trained in [9], [29] for detecting loop closures.”
MethodLidar/UWB Fusion Based SLAM With Anti-Degeneration Capability
Zhou, H., Yao, Z. Q., & Lu, M. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3045767 · Cited by 56
“THE recent decades have shown a great development of simultaneous localization and mapping (SLAM) in indoor applications where GNSS signals are denied, such as [1]–[3].”
BackgroundVision-based positioning system for auto-docking of unmanned surface vehicles (USVs)
Volden, Ø., Stahl, A., & Fossen, T. I. (2021) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-021-00193-0 · Cited by 56
“The two main approaches to estimate the camera pose are based on natural features (Engel et al. 2014; Mur-Artal et al. 2015; Zhong et al. 2015), e.”
BackgroundKarpyshev, P., Ilin, V., Kalinov, I., Petrovsky, A., & Tsetserukou, D. (2021) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/ieeeconf49454.2021.9382649 · Cited by 54
“The critical work in solving the visual SLAM problem using features is the ORB-SLAM algorithma described in the paper [31].”
MethodAccurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
Shi, Y., Yu, X., Liu, L., Campbell, D., Koniusz, P., & Li, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3189702 · Cited by 101
“It was originally approached as a ground-to-ground image matching task, which is often used for place recognition [26], [27], [28], [29], [30], [31], [32], [33], [34], and loop-closure detection [35], [36], [37].”
Wei, R., Li, B., Mo, H., Lu, B., Long, Y., Yang, B., Dou, Q., Liu, Y., & Sun, D. B. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3195027 · Cited by 72
LTA‐OM: Long‐term association LiDAR–IMU odometry and mapping
Zou, Z., Yuan, C., Xu, W. D., Li, H., Zhou, S., Xue, K., & Zhang, F. (2024) · Journal of Field Robotics · doi:10.1002/rob.22337 · Cited by 60
“A SLAM system can estimate the trajectory of a moving platform and the map of the surrounding environment (e.g., Figure 1) in real ‐ time by processing the data from Light Detection and Rangings (LiDARs) (Xu et al., 2022; Zhang & Singh, 2014) or cameras (Mur ‐ Artal et al., 2015; Qin et al., 2018).”
Gao, Z., Chen, J., Liu, Y., Jin, Y., & Tian, D. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11060-2 · Cited by 71
Vision-Based Learning for Drones: A Survey
Xiao, J., Zhang, R., Zhang, Y., & Feroskhan, M. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3564184 · Cited by 83
“Cameras can provide positioning for drone navigation in GPS-denied environments via visual inertial odometry (VIO) [43], [44], [45] and visual simultaneous localization and mapping systems (V-SLAMs) [35], [46], [47].”
Constructing Category-Specific Models for Monocular Object-SLAM
Parkhiya, P., Khawad, R., Jatavallabhula, K. M., Bhowmick, B., & Krishna, K. M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460816 · Cited by 54
Polarimetric Dense Monocular SLAM
Yang, L., Tan, F., Li, A., Cui, Z., Furukawa, Y., & Tan, P. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00406 · Cited by 61
“SLAM: Most visual SLAM algorithms [8, 20, 26] are dedicated to improve the camera pose accuracy or system robustness.”
BackgroundVision-Based High-Speed Driving With a Deep Dynamic Observer
Drews, P., Williams, G., Goldfain, B., Theodorou, E. A., & Rehg, J. M. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2896449 · Cited by 61
Experimental Comparison of Visual-Aided Odometry Methods for Rail Vehicles
Tschopp, F., Schneider, T., Palmer, A. W., Nourani‐Vatani, N., Cadena, C., Siegwart, R., & Nieto, J. I. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2897169 · Cited by 54
“Trajectory2 is more challenging due to faster motion, more challening lighting conditions and more dynamic objects such as cars, pedestrians and other III which suggests that OKVIS also has a higher robustness compared to ORB-SLAM2 .”
BackgroundMethodInfluentialPIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design
Zhang, Z., Liu, S., Tsai, G., Hu, H., Chu, C.-C., & Zheng, F. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460672 · Cited by 62
Monocular Localization with Vector HD Map (MLVHM): A Low-Cost Method for Commercial IVs
Xiao, Z., Yang, D., Wen, T., Jiang, K., & Yan, R. (2020) · Sensors · doi:10.3390/s20071870 · Cited by 64
“The other branch in the MLVHM system diagram is designed to estimate the odometer readings of the camera using the ORB-SLAM algorithm [23].”
Keyfilter-Aware Real-Time UAV Object Tracking
Li, Y., Fu, C., Huang, Z., Zhang, Y., & Pan, J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196943 · Cited by 56
Range-Visual-Inertial Odometry: Scale Observability Without Excitation
Delaune, J., Bayard, D. S., & Brockers, R. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3058918 · Cited by 60
“The visual odometry module can be swapped between any of the modern algorithms developed in the computer vision community, such as PTAM [5], SVO [6], ORB-SLAM [7] or DSO [8].”
A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks
Huang, B., Zhao, J., Luo, S., & Liu, J. (2021) · Journal of Global Positioning Systems · doi:10.5081/jgps.17.1.94 · Cited by 75
Self-Supervised deep homography estimation with invertibility constraints
Wang, C., Wang, X., Bai, X. P., Liu, Y., & Zhou, J. W. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.09.021 · Cited by 54
Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation
Karkus, P., Cai, S., & Hsu, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00284 · Cited by 50
Unsupervised Estimation of Monocular Depth and VO in Dynamic Environments via Hybrid Masks
Sun, Q., Tang, Y. S., Zhang, C., Zhao, C., Qian, F., & Kurths, J. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3100895 · Cited by 57
Near-Field Perception for Low-Speed Vehicle Automation Using Surround-View Fisheye Cameras
Eising, C., Horgan, J., & Yogamani, S. K. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3127646 · Cited by 78
“MonoSLAM [96], Parallel Tracking and Mapping (PTAM) [97] and ORBSLAM [98] are seminal algorithms of this type.”
BackgroundCamera, LiDAR and Multi-modal SLAM Systems for Autonomous Ground Vehicles: a Survey
Chghaf, M., Rodríguez, S., & Elouardi, A. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01582-8 · Cited by 62
“The implementation uses LOAM pipeline to generate a voxel map and an ORB-SLAM2 pipeline to obtain a visual map.”
MethodInfluentialRobust identification of fiducial markers in challenging conditions
Mondéjar-Guerra, V. M., Garrido-Jurado, S., Muñoz‐Salinas, R., Marín-Jiménez, M. J., & Medina-Carnicer, R. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.10.032 · Cited by 55
6DoF Object Tracking based on 3D Scans for Augmented Reality Remote Live Support
Rambach, J. R., Pagani, A., Schneider, M., Artemenko, O., & Stricker, D. (2018) · Computers · doi:10.3390/computers7010006 · Cited by 59
“ORB-SLAM [16] followed the same principles but extended the application area coverage capabilities by effective map management and loop closure techniques.”
MethodTowards Fully Mobile 3D Face, Body, and Environment Capture Using Only Head-worn Cameras
Cha, Y.-W., Price, T., Wei, Z., Lu, X., Rewkowski, N., Chabra, R., Qin, Z., Kim, H., Su, Z., Liu, Y., et al. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2868527 · Cited by 62
“ping (SLAM) [21, 22, 42, 61, 64], multi-view vision [53, 54], and depthcamera-based algorithms [28, 40, 43, 49] and can be used to reconstruct only static scenes.”
BackgroundLi, J., Li, Z., Feng, Y., Liu, Y., & Shi, G. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2911667 · Cited by 54
“FAST and rotated BRIEF (ORB), to match and track features between frames [13] or to recursive Bayesian estimation-based filter, such as classical Kalman filter (KF) and latest particle filter (PF), so that the localization and the updating of the map can be implemented step by step [14], [15].”
BackgroundBrickwedde, F., Abraham, S., & Mester, R. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00287 · Cited by 64
“a static scene and a moving camera [11, 13, 47, 48, 57].”
BackgroundUsing Sky‐pointing fish‐eye camera and LiDAR to aid GNSS single‐point positioning in urban canyons
Bai, X., Wen, W., & Hsu, L. (2020) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2019.0587 · Cited by 53
“Similar research studies [31, 32] are conducted recently and the improved GNSS positioning was integrated with visual simultaneous localisation and mapping [33].”
MethodAggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control
Drews, P., Williams, G., Goldfain, B., Theodorou, E. A., & Rehg, J. M. (2017) · Conference on Robot Learning · Cited by 75
RaLL: End-to-End Radar Localization on Lidar Map Using Differentiable Measurement Model
Yin, H., Chen, R., Wang, Y., & Xiong, R. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3061165 · Cited by 69
Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
Li, S., Wu, X., Cao, Y., & Zha, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01298 · Cited by 60
“DSO ORB-SLAM2 Ours Ours Ours Sequence [24] [39] [41] [22] [21] [42] [43] [7] (LC) [26] (w/o RDS) (w/o PU) fr2/desk 0.”
BackgroundMethodInfluentialA systematic literature review on long‐term localization and mapping for mobile robots
Sousa, R. B., Sobreira, H., & Moreira, A. P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22170 · Cited by 68
Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Chen, Y., Chen, X., Wang, X., Zhang, Q., Guo, Y., Shan, Y., & Wang, F. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00799 · Cited by 58
“point clouds) and estimate camera poses through image registration via associating feature correspondences [11, 30] or minimizing photometric errors [3, 15], followed by BA [3, 12, 25].”
BackgroundInfluentialLipson, L., Teed, Z., & Deng, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72627-9_24 · Cited by 115
Indoor SLAM for Micro Aerial Vehicles Control Using Monocular Camera and Sensor Fusion
Garcia, S., López-Guillén, E., Barea, R., Bergasa, L. M., Gomez, A., & Molinos, E. J. (2016) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2016.46 · Cited by 52
“The study explained in this paper uses two monocular VSLAM algorithms to calculate the pose estimation (along with the measurements from the IMU) and the map of the environment: LSD-SLAM [7] and ORB-SLAM [8].”
MethodInfluentialCombining Feature-Based and Direct Methods for Semi-dense Real-Time Stereo Visual Odometry
Krombach, N., Droeschel, D., & Behnke, S. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-48036-7_62 · Cited by 60
“LSD-SLAM, ORB-SLAM and S-PTAM often suffer from fast motions in combination with rotations, and temporarily lose track.”
MethodInfluentialVisual laser-SLAM in large-scale indoor environments
Liang, X., Chen, H., Li, Y., & Liu, Y. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866271 · Cited by 56
Learning-Based Image Enhancement for Visual Odometry in Challenging HDR Environments
Gomez-Ojeda, R., Zhang, Z., González-Jiménez, J., & Scaramuzza, D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8462876 · Cited by 63
Dense Visual SLAM with Probabilistic Surfel Map
Yan, Z., Ye, M., & Ren, L. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2017.2734458 · Cited by 58
“, [20] and [27]).”
MethodNavigation without localisation: reliable teach and repeat based on the convergence theorem
Krajník, T., Majer, F., Halodová, L., & Vintr, T. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593803 · Cited by 67
Combining Hector SLAM and Artificial Potential Field for Autonomous Navigation Inside a Greenhouse
Harik, E. H. C., & Korsæth, A. (2018) · Robotics · doi:10.3390/robotics7020022 · Cited by 52
“The pose of the platform is acquired using the motion capture system and used as a feedback for the motion controller, while they used the Oriented FAST and Rotated BRIEF (ORB)-SLAM [25] to evaluate the localization task off-board for enhancing future autonomy of the system.”
MethodWang, Y., Zhang, S., Wan, B., He, W., & Bai, X. (2018) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-018-2575-8 · Cited by 56
Visual-Thermal Landmarks and Inertial Fusion for Navigation in Degraded Visual Environments
Khattak, S., Papachristos, C., & Alexis, K. (2019) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2019.8741787 · Cited by 61
MagicVO: An End-to-End Hybrid CNN and Bi-LSTM Method for Monocular Visual Odometry
Jiao, J., Jiao, J., Mo, Y., Liu, W., & Deng, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2926350 · Cited by 58
“Based on the ideas of the above two papers, Artal and his colleagues propose a monocular vision SLAM based on keyframes [24].”
BackgroundSemantic Mapping for View-Invariant Relocalization
Li, J., Meger, D., & Dudek, G. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793624 · Cited by 59
“While this approach has been shown to yield excellent tracking accuracy and computational efficiency [3], [4], the low-level map representation does not lend itself well to the relocalization task (global localization) when the viewing angle changes significantly, since the same surfaces are no longer visible.”
BackgroundMethodMulti-Camera Visual-Inertial Navigation with Online Intrinsic and Extrinsic Calibration
Eckenhoff, K., Geneva, P., Bloecker, J., & Huang, G. P. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793886 · Cited by 63
“[16] extended the ORB-SLAM [17] to a system of multiple cameras with varying viewing directions and an IMU for UAVs within a graph-SLAM framework but assumed known sensor calibration and simultaneous triggering of all involved cameras.”
BackgroundZeng, T., Tang, F., Ji, D., & Si, B. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.02.023 · Cited by 57
Liu, J., Li, Q., Cao, R., Tang, W., & Qiu, G. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.06.004 · Cited by 60
“We present two variants: ORB-SLAM (full), which takes the whole sequence as input allowing loop closure detection and re-localization, and ORB-SLAM (short), which only takes 5-frame snippets as input.”
MethodInfluentialMLDA-Net: Multi-Level Dual Attention-Based Network for Self-Supervised Monocular Depth Estimation
Song, X., Li, W., Zhou, D., Dai, Y., Fang, J., Li, H., & Zhang, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3074306 · Cited by 57
“image-based scene understanding [1]–[4], SLAM [5]–[7], augmented reality [8], [9] and autonomous driving [10]–[12].”
BackgroundTinchev, G., Penate-Sanchez, A., & Fallon, M. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2895264 · Cited by 51
Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection
Yang, M., Chen, Y., & Kim, H.-S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_14 · Cited by 77
Ye, W., Lan, X., Chen, S., Ming, Y., Yu, X., Bao, H., Cui, Z., & Zhang, G. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00924 · Cited by 69
“Modern SLAM systems roughly fall into two categories, geometric-based methods [7, 22, 9, 6], and learning-based methods [44, 29, 31, 34].”
BackgroundVision-based environmental perception for autonomous driving
Liu, F., Lu, Z., & Lin, X. (2023) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070231203059 · Cited by 71
“Mur-Artal et al. 192 proposed ORB-SLAM based on PTAM with the addition of a third parallel thread, the loopback detection thread, and the loopback detection algorithm can reduce the cumulative error generated by the SLAM system.”
RelPose++: Recovering 6D Poses from Sparse-view Observations
Lin, A., Zhang, J. Y., Ramanan, D., & Tulsiani, S. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00126 · Cited by 109
“This paradigm has been scaled by efficient parallelization [40, 41] and can even run in real-time for visual odometry [3,29,30].”
MethodA multi-sensor fusion approach for maritime autonomous surface ships berthing navigation perception
Lu, H., Zhang, Y., Zhang, C., Niu, Y., Wang, Z., & Zhang, H. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.119965 · Cited by 53
Fisheye-Based Method for GPS Localization Improvement in Unknown Semi-Obstructed Areas
Moreau, J., Ambellouis, S., & Ruichek, Y. (2017) · Sensors · doi:10.3390/s17010119 · Cited by 51
“SLAM is studied in [43,44] for omnidirectional vision.”
BackgroundA Cloud and Vision-based Navigation System Used for Blind People
Bai, J., Liu, D., Su, G., & Fu, Z. (2017) · International Conference on Artificial Intelligence, Automation and Control Technologies (AIACT) · doi:10.1145/3080845.3080867 · Cited by 53
Automatic reconstruction method for large scene based on multi-site point cloud stitching
Xu, H., Yu, L., Hou, J., & Fei, S. (2018) · Measurement · doi:10.1016/j.measurement.2018.09.022 · Cited by 52
Li, J., Wang, C., Kang, X., & Zhao, Q. (2019) · International Journal of Digital Earth · doi:10.1080/17538947.2018.1564379 · Cited by 56
“For example, the recent noteworthy development in real-time SLAM algorithms is called ORB-SLAM (Raúl, Montiel, and Tardós 2015) which incorporates the state-of-the-art techniques in recent years, and uses real-time ORB features for tracking, mapping, localization and loop closure in large indoor and outdoor environmen…”
MethodInfluentialTowards Robust Visual Odometry with a Multi-Camera System
Liu, P., Geppert, M., Heng, L., Sattler, T., Geiger, A., & Pollefeys, M. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593561 · Cited by 56
“[19] extend the system to handle large-scale environments by”
Real-Time CPU-Based Large-Scale Three-Dimensional Mesh Reconstruction
Piazza, E., Romanoni, A., & Matteucci, M. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2800104 · Cited by 59
Extremely Dense Point Correspondences Using a Learned Feature Descriptor
Liu, X., Zheng, Y., Killeen, B. D., Ishii, M., Hager, G. D., Taylor, R. H., & Unberath, M. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00490 · Cited by 66
RGB-D Point Cloud Registration Based on Salient Object Detection
Wan, T., Du, S., Cui, W., Yao, R., Ge, Y., Li, C., Gao, Y., & Zheng, N. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053274 · Cited by 58
Learning Monocular Visual Odometry with Dense 3D Mapping from Dense 3D Flow
Zhao, C., Sun, L., Purkait, P., Duckett, T., & Stolkin, R. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594151 · Cited by 59
Xu, F., Li, Q., Zhu, J., Chen, Z., Zhang, D., Wu, K., Ding, K., & Li, Q. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104494 · Cited by 57
Cluster-based loop closing detection for underwater slam in feature-poor regions
Negre, P. L., Font, F. B., & Oliver, G. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487416 · Cited by 57
Zhang, Z., Zhao, R., Liu, E., Yan, K., & Ma, Y. (2018) · Sensors · doi:10.3390/s18061948 · Cited by 53
“Following the SFM [40] method, the estimation of the fundamental matrix or homography is performed on the image sequence [4], and the pose relationship of all frames [ , ] i i s R t ( s is the scale factor) are optimized for achieving the bundle adjustment (BA) [43].”
MethodInfluentialVehicle Localization at an Intersection Using a Traffic Light Map
Wang, C., Huang, H., Ji, Y., Wang, B., & Yang, M. Z. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2851788 · Cited by 54
“For the computation consideration, keyframe-based approaches are developed such as famous ORB-SLAM [7].”
MethodFeature-constrained Active Visual SLAM for Mobile Robot Navigation
Deng, X., Zhang, Z., Sintov, A., Huang, J. L., & Bretl, T. W. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460721 · Cited by 54
“In this paper, we identify one specific type of failure termed tracking failure [5].”
BackgroundMethodAdaptive View Planning for Aerial 3D Reconstruction
Peng, C., & Isler, V. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793532 · Cited by 50
“These approaches are hard to implement on existing systems due to the need for significant on board processing to accurately localize on the go with a real-time SLAM approach [4]–[6], a decision making mechanism running on board to decide on the next best view, and a controller to execute the strategy.”
BackgroundMethodVisual-Odometric Localization and Mapping for Ground Vehicles Using SE(2)-XYZ Constraints
Fan, Z., & Liu, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793928 · Cited by 51
“We compare our work (termed SE2 here) with 1) the SE(2)-constrained system (termed SE2C) in [19] and 2) an odometric-aided version of the state-of-the-art visual estimation system ORB-SLAM2 [5] on the two datasets.”
MethodInfluentialUncertainty Estimation for Data-Driven Visual Odometry
Costante, G., & Mancini, M. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.3001674 · Cited by 57
“To show that, we decide to fuse the predictions of the UA-VO models with two popular geometrical VO approaches (namely, ORBSLAM [5] and DSO [8]).”
BackgroundMethodInfluentialResearch on SLAM Algorithm of Mobile Robot Based on the Fusion of 2D LiDAR and Depth Camera
Mu, L., Yao, P., Zheng, Y., Chen, K., Wang, F., & Qi, N. (2020) · IEEE Access · doi:10.1109/access.2020.3019659 · Cited by 55
“VSLAM then entered a period of rapid development and a large number of excellent algorithmic frameworks emerged, ORB-SLAM [22], [23], DTAM [24], LSD-SLAM [25]–[27], SVO [28] and DVO-SLAM [29].”
BackgroundGeometric Consistency for Self-Supervised End-to-End Visual Odometry
Iyer, G., Jatavallabhula, K. M., Gupta, G., Krishna, K. M., & Paull, L. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00064 · Cited by 58
GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering
Trevithick, A., & Yang, B. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · Cited by 82
Robust Lidar-Based Localization Scheme for Unmanned Ground Vehicle via Multisensor Fusion
Wu, Y., Li, Y., Li, W., Li, H., & Lu, R. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027983 · Cited by 49
Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner?
Wang, L., Wang, Y., Wang, L., Zhan, Y., Wang, Y., & Lu, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01249 · Cited by 58
“Sequence 9 Sequence 10 Frames ORB-Slam [21] 0.014 ± 0.008 0 .012 ± 0.011 – SfMLearner [36] 0.021 ± 0.017 0 .020 ± 0.015 5 DF-Net [37] 0.017 ± 0.007 0 .015 ± 0.009 5 CC [23] 0.012 ± 0.007 0 .012 ± 0.008 5 DDVO [27] 0.045 ± 0.108 0 .033 ± 0.074 3 Mahjourian [20] 0.013 ± 0.010 0 .012 ± 0.011 3…”
InfluentialLearning a Structured Latent Space for Unsupervised Point Cloud Completion
Cai, Y., Lin, K.-Y., Zhang, C., Wang, Q., Wang, X., & Li, H. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00546 · Cited by 64
“Point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud, which is an important task and can assist downstream applications such as shape classification [17,26–28,34], robotics navigation [12, 31] and scene understanding [1, 2, 10, 19], as raw point clouds are often noi…”
BackgroundOverview of Multi-Robot Collaborative SLAM from the Perspective of Data Fusion
Chen, W., Wang, X., Gao, S., Shang, G., Zhou, C., Li, Z., Xu, C., & Hu, K. (2023) · Machines · doi:10.3390/machines11060653 · Cited by 61
“The front-end of the system uses the ORB-SLAM system based on keyframes and, at the same time, uses the bag-of-words library model to query the keyframe library.”
BackgroundMethodInfluentialA Survey of Visual SLAM Methods
Sahili, A. R., Hassan, S. A., Sakhrieh, S., Mounsef, J., Maalouf, N., Arain, B., & Taha, T. (2023) · IEEE Access · doi:10.1109/access.2023.3341489 · Cited by 63
Zhong, M., Hong, C., Jia, Z., Wang, C., & Wang, Z. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104634 · Cited by 52
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.