The DOI matches its Crossref record; 20 of the 21 references it cites were found in a registry or an index.
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“As an input-driven system, the stochastic input sequences of edge-assisted SLAM cause a considerable impact on the state dynamics and rewards, which then incur high variance during the training of policy gradient methods [13], [14].”
From Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM (2025) · cites this paper as [14]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“In such an input-driven system, traditional state-dependent DRL algorithms suffer from high state dynamics, leading to inherent bias in policy gradient estimates and increased gradient variance during training [13], [14].”
From Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM (2025) · cites this paper as [14]
Experimental — accuracy not yet measured
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
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 1×
“The system uses the same ORB features [17] for tracking, mapping, and place recognition tasks.”
MethodVision 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×
“We use two different metrics, the absolute translation root-mean-square error (RMSE) tabs proposed in [3], and the average relative translation trel and rotation rrel errors proposed in [2].”
BackgroundMethodORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 7×
“Left: Monocular ORB-SLAM [1], right: ORB-SLAM2 (stereo).”
BackgroundMethodResultInfluentialSelf-citationA benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385773 · Cited by 4,230 · cited 4×
“The RGB-D case shows the keyframe poses estimated in sequence fr1_room from the TUM RGB-D Dataset [3], and a dense pointcloud, rendered by backprojecting sensor depth maps from the estimated keyframe poses.”
MethodInfluentialKinectFusion: Real-time dense surface mapping and tracking
Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092378 · Cited by 4,008 · cited 2×
“Note that our SLAM does not perform any fusion like KinectFusion [4] or similar, but the good definition indicates the accuracy of the keyframe poses.”
BackgroundThe EuRoC micro aerial vehicle datasets
Burri, M., Nikolic, J., Gohl, P., Schneider, T., Rehder, J., Omari, S., Achtelik, M., & Siegwart, R. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915620033 · Cited by 2,086 · cited 1×
“The recent EuRoC dataset [21] contains 11 stereo sequences recorded from a microaerial vehicle (MAV) flying around two different rooms and a large industrial environment.”
BackgroundBags of Binary Words for Fast Place Recognition in Image Sequences
Gálvez‐López, D., & Tardós, J. D. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2197158 · Cited by 1,890 · cited 2×
“The system has embedded a Place Recognition module based on DBoW2 [16] for relocalization, in case of tracking failure (e.g. an occlusion) or for reinitialization in an already mapped scene, and for loop detection.”
Dense visual SLAM for RGB-D cameras
Kerl, C., Sturm, J., & Cremers, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696650 · Cited by 941 · cited 5×
“In Table III we compare our accuracy to the following state-of-the-art methods: ElasticFusion [15], Kintinuous [12], DVO-SLAM [14] and RGB-D SLAM [13].”
MethodInfluential3-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 821 · cited 5×
“In Table III we compare our accuracy to the following state-of-the-art methods: ElasticFusion [15], Kintinuous [12], DVO-SLAM [14] and RGB-D SLAM [13].”
MethodInfluentialVisual-Inertial Monocular SLAM With Map Reuse
Mur-Artal, R., & Tardós, J. D. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2653359 · Cited by 790 · cited 1×
“As shown in [22], this sequence can be processed using IMU information.”
MethodSelf-citation
Research works printed but not linked: 2
- 10.1177/0278364914551008 · DOI
- kuemmerle, 0, g2o: A general framework for graph optimization, Proc IEEE Int Conf Robot Autom, 3607
Cited by
Sorted by citations
Items 601–700 of 1,004
UniVIO: Unified Direct and Feature-Based Underwater Stereo Visual-Inertial Odometry
Miao, R., Qian, J., Yang, S. S., Ying, R., & Liu, P. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3136259 · Cited by 46
“The feature-based sparse methods, such as monoSLAM [12], parallel tracking and mapping (PTAM) [13], oriented FAST and rotated BRIEF (ORB)-SLAM/ORB-SLAM2 [14], [15], fix the precision of features matching after the front-end.”
BackgroundMethodRobust SLAM Systems: Are We There Yet?
Bujanca, M., Shi, X., Spear, M., Zhao, P., Lennox, B., & Luján, M. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636814 · Cited by 44
“ORB-SLAM2 and ORB-SLAM3 are severely affected in textureless environments.”
BackgroundInfluentialHigh-Definition Map Representation Techniques for Automated Vehicles
Soorchaei, B. E., Razzaghpour, M., Valiente, R., Raftari, A., & Fallah, Y. P. (2022) · Electronics · doi:10.3390/electronics11203374 · Cited by 50
Multi-Modal Feature Constraint Based Tightly Coupled Monocular Visual-LiDAR Odometry and Mapping
Shu, C., & Luo, Y.-T. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3215141 · Cited by 40
“For visual odometry methods, we choose the stereo version of ORB-SLAM2 [28] because it is one of the popular visual odometry approaches, and SOFT-SLAM [30] because it is one of the best published visual SLAM methods.”
MethodContinuous-Time Fixed-Lag Smoothing for LiDAR-Inertial-Camera SLAM
Lv, J.-J., Lang, X.-L., Xu, J., Wang, M.-M., Liu, Y., & Zuo, X. (2023) · IEEE/ASME transactions on mechatronics · doi:10.1109/tmech.2023.3241398 · Cited by 59
“Among all of the sensors, camera, IMU and LiDAR are three of the most ubiquitous sensors leveraged in SLAM algorithms [1], [2], [3], [4], [5], [6].”
BackgroundFogROS2: An Adaptive Platform for Cloud and Fog Robotics Using ROS 2
Ichnowski, J., Chen, K., Dharmarajan, K., Adebola, S., Danielczuk, M., Mayoral-Vilches, V., Jha, N., Zhan, H., Llontop, E., Xu, D. C., et al. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161307 · Cited by 63
“We evaluate FogROS2 in a benchmark on 3 example robot applications: SLAM with ORB-SLAM2 [43], Grasp Planning with Dex-Net [44], and Motion Planning with Motion Planning Templates (MPT) [45].”
MethodLVIO-Fusion:Tightly-Coupled LiDAR-Visual-Inertial Odometry and Mapping in Degenerate Environments
Zhang, H., Du, L., Bao, S., Yuan, J., & Ma, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3371383 · Cited by 44
“Based on ORB-SLAM, Mur-Artal presents ORB-SLAM2 [13] that utilizes scale information provided by stereo or RGB-D cameras.”
MethodDeng, T., Wang, Y., Xie, H., Wang, H., Guo, R., Wang, J., Wang, D., & Chen, W. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3541064 · Cited by 55
“Compared with the traditional SLAM system [1], We can achieve competitive camera tracking performance, while providing dense and high-fidelity scene reconstruction performance.”
InfluentialAn Effective Multi-Cue Positioning System for Agricultural Robotics
Imperoli, M., Potena, C., Nardi, D., Grisetti, G., & Pretto, A. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2855052 · Cited by 44
“2 system [30], a best-in-class Visual SLAM system, with its mapping and loop closures back-ends activated.”
BackgroundVLASE: Vehicle Localization by Aggregating Semantic Edges
Yu, X., Chaturvedi, S., Feng, C., Taguchi, Y., Lee, T., Fernandes, C., & Ramalingam, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594358 · Cited by 44
Bayesian DeNet: Monocular Depth Prediction and Frame-Wise Fusion With Synchronized Uncertainty
Yang, X. Y., Gao, Y., Luo, H., Liao, C., & Cheng, K.-T. T. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2912121 · Cited by 44
“[20] R. Mur-Artal and J. D. Tardós, “ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras,” IEEE Trans.”
MethodInfluentialPerception-aware trajectory generation for aggressive quadrotor flight using differential flatness
Murali, V., Spasojevic, I., Guerra, W., & Karaman, S. (2019) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2019.8814697 · Cited by 44
“Typical visual-inertial navigation systems such as ORB-SLAM2 [3] employ a keyframe-based optimization technique to estimate the state of the robot from multiple visual features tracked across keyframes, as illustrated in Figure 1.”
MethodSheng, L., Xu, D., Ouyang, W., & Wang, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00440 · Cited by 44
“The keyframe selection has been adopted in several state-of-the-art traditional SLAM approaches, such as RDSLAM [39] and ORBSLAM [30, 31].”
MethodUniversal Flying Objects: Modular Multirotor System for Flight of Rigid Objects
Mu, B., & Chirarattananon, P. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2954679 · Cited by 44
“This has brought about significant progress in research and development in several related directions, including localization and mapping [3], swarm robotics [4], [5], design and fabrication [6], [7], and dynamics and control [8]–[10].”
BackgroundZhong, L., Zhao, X., Zhang, Y., Zhang, S., & Zhang, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2973512 · Cited by 44
“…tracking method; UDP [56], a monocular 3D object detection method; ElasticFusion [57], a visual SLAM approach which relies on RGB-D data; ORB-SLAM2 [58], another visual SLAM approach which uses gradient-based features; TPAMI19 [7], one of the most recent state-of-art region-based 3D object pose…”
MethodSimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Kim, U.-H., Kim, S.-H., & Kim, J.-H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3007546 · Cited by 43
Autonomous Obstacle Avoidance for UAV based on Fusion of Radar and Monocular Camera
Yu, H., Zhang, F., Huang, P., Wang, C., & Li, Y. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341432 · Cited by 45
PLC-VIO: Visual–Inertial Odometry Based on Point-Line Constraints
Liu, Z., Shi, D., Li, R., Qin, W., Zhang, Y., & Ren, X. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3077026 · Cited by 44
“Direct-based methods [5], [29]–[32] minimize photometric error and feature-based methods [33]–[35] minimize geometric displacement.”
MethodLIRO: Tightly Coupled Lidar-Inertia-Ranging Odometry
Nguyen, T., Cao, M., Yuan, S., Lyu, Y., Nguyen, T. H., & Xie, L. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560954 · Cited by 45
An Optimization-Based UWB-IMU Fusion Framework for UGV
Zheng, S., Li, Z., Liu, Y., Zhang, H., & Zou, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3144660 · Cited by 44
PFD-SLAM: A New RGB-D SLAM for Dynamic Indoor Environments Based on Non-Prior Semantic Segmentation
Zhang, C., Zhang, R., Jin, S., & Yi, X. (2022) · Remote Sensing · doi:10.3390/rs14102445 · Cited by 44
Overview of deep learning application on visual SLAM
Li, S., Zhang, D., Xian, Y., Li, B., Zhang, T., & Zhong, C. (2022) · Displays · doi:10.1016/j.displa.2022.102298 · Cited by 47
A comprehensive overview of dynamic visual SLAM and deep learning: concepts, methods and challenges
Beghdadi, A., & Mallem, M. (2022) · Machine Vision and Applications · doi:10.1007/s00138-022-01306-w · Cited by 49
“DynaSLAM [21]: is a method built on the ORB-SLAM2 [61] framework and detection of dynamic objects that complete the occluded background with static information from previous keyframes.”
MethodInfluentialEDPLVO: Efficient Direct Point-Line Visual Odometry
Zhou, L., Huang, G. P., Mao, Y., Wang, S., & Kaess, M. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812133 · Cited by 42
“The well established ORB-SLAM framework for points [9], [25], [26] can be easily extended to lines [13].”
BackgroundContinuous Scene Representations for Embodied AI
Gadre, S. Y., Ehsani, K., Song, S., & Mottaghi, R. (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/cvpr52688.2022.01443 · Cited by 50
“Classical mapping and localization work in the robotics literature [16, 19, 35] relies on low-level geometric features and does not encode semantic information.”
BackgroundGe, Y., Zhang, L., Wu, Y., & Hu, D. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3366815 · Cited by 47
“Subsequent representative work includes LSD-SLAM [13] and ORB-SLAM2 [14].”
BackgroundMethodAQUA-SLAM: Tightly Coupled Underwater Acoustic-Visual-Inertial SLAM With Sensor Calibration
Xu, S., Zhang, K., & Wang, S. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3554396 · Cited by 44
“However, mostofthechallengesforunderwatervision,suchasthelimited visibilityandthe“marinesnow,”arelong-termeffectsthatlast atleastfromtensofsecondstoafewminutesbeforebeing mitigated.”
A Stable and Accurate Marker-Less Augmented Reality Registration Method
Gao, Q.-H., Wan, T.-R., Tang, W., & Chen, L. (2017) · International Conference on Cyberworlds · doi:10.1109/cw.2017.44 · Cited by 35
“We develop our new approach based on our observations that, although RGBD images can be used [15], the advantage of the depth information provided by the RGBD image has only been used during initialization step.”
MethodRobust Robot Pose Estimation for Challenging Scenes With an RGB-D Camera
Yu, H., Fu, Q., Yang, Z., Tan, L., Sun, W., & Sun, M. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2884321 · Cited by 43
“As the ORB extractor requires less computation and has a good rotation and scale invariance, it is wildly used in pose estimation systems [22]–[24].”
MethodDMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors
Liu, G.-H., Zeng, W.-L., Feng, B., & Xu, F. (2019) · Italian National Conference on Sensors · doi:10.3390/s19173714 · Cited by 43
“We proposed a DMS-SLAM system which is based on the state-of-the-art ORB-SLAM2 [7].”
BackgroundMethodInfluentialDynamic Attention-based Visual Odometry
Kuo, X.-Y., Liu, C., Lin, K.-C., & Lee, C. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00026 · Cited by 43
“These baseline methods include non-DCNN based visual SLAM framework ORB-SLAM2 [18] (without enabling the loop closing for a fair comparison with the baseline VO algorithms), the open-source visual odometry library VISO2 [50], as well as the related learning-based VO works discussed in Section 2,…”
MethodRobust and Efficient RGB-D SLAM in Dynamic Environments
Yang, X. Y., Yuan, Z., Zhu, D., Chi, C., Li, K., & Liao, C. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3038323 · Cited by 43
Lin, X., Wang, F., Yang, B., & Zhang, W. (2021) · Remote Sensing · doi:10.3390/rs13030506 · Cited by 43
“frames are estimated by stereo visual odometry based on the state-of-the-art Oriented FAST and Rotated BRIEF (ORB)-SLAM2 framework [38], where i represents the last”
MethodDeepAVO: Efficient pose refining with feature distilling for deep Visual Odometry
Zhu, R., Yang, M., Liu, W., Song, R., Yan, B., & Xiao, Z. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.029 · Cited by 45
Uncertainty-Aware Camera Pose Estimation from Points and Lines
Vakhitov, A., Ferraz, L., Agudo, A., & Moreno-Noguer, F. (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/cvpr46437.2021.00463 · Cited by 42
“In point+line experiment, the new methods clearly outperform the baselines.”
MethodMFF-Net: Towards Efficient Monocular Depth Completion With Multi-Modal Feature Fusion
Liu, L., Song, X., Sun, J., Lyu, X., Li, L., Liu, Y., & Zhang, L. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3234776 · Cited by 42
“Following DenseLiDAR [4], we choose ORB-SLAM2 [42] as the evaluation baseline, which is a popular real-time SLAM library for Monocular, Stereo and RGB-D cameras.”
MethodOverview 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 51
MSC-RAD4R: ROS-Based Automotive Dataset With 4D Radar
Choi, M., Yang, S.-H., Han, S., Lee, Y., Lee, M., Choi, K. H., & Kim, K.-S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3307005 · Cited by 41
Real-time localization and 3D semantic map reconstruction for unstructured citrus orchards
Xiong, J., Liang, J., Zhuang, Y., Hong, D., Zheng, Z., Liao, S., Hu, W., & Yang, Z. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108217 · Cited by 43
Vision-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 51
“[174, 175] proposed ORB-SLAM2 and ORB-SLAM3 and extended them to binoculars, RGBD, and fisheye cameras.”
Bian, J., Hui, X., Zhao, X., & Tan, M. H. (2019) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881418820227 · Cited by 43
Ground robotics in tunnels: Keys and lessons learned after 10 years of research and experiments
Tardioli, D., Riazuelo, L., Sicignano, D., Rizzo, C., Lera, F., Villarroel, J. L., & Montano, L. (2019) · Journal of Field Robotics · doi:10.1002/rob.21871 · Cited by 45
Improving Visual Localization Accuracy in Dynamic Environments Based on Dynamic Region Removal
Cheng, J., Zhang, H., & Meng, M. Q. ‐. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.2964938 · Cited by 42
“In terms of the feature-based visual SLAM system, we adopt the state-of-the-art algorithm ORB-SLAM [42] as our baseline scheme.”
MethodMobile Robot Localization using GPS, IMU and Visual Odometry
Cai, G.-S., Lin, H., & Kao, S.-F. (2019) · International Automatic Control Conference · doi:10.1109/cacs47674.2019.9024731 · Cited by 42
“Recently, ORB-SLAM2 was released [18].”
Online coverage and inspection planning for 3D modeling
Song, S., Kim, D., & Jo, S. (2020) · Autonomous Robots · doi:10.1007/s10514-020-09936-7 · Cited by 42
“We employed a ZED SDK 2 for depth sensing and ORB-SLAM (Mur-Artal and Tardós 2017) for pose estimation.”
MethodInfluentialDVIO: An Optimization-Based Tightly Coupled Direct Visual-Inertial Odometry
Jiang, J.-Q., Yuan, J., Zhang, X.-T., & Zhang, X.-B. (2021) · IEEE transactions on industrial electronics (1982. Print) · doi:10.1109/tie.2020.3036243 · Cited by 37
“Based on patch correspondences and the relative pose between image frames, the depth of each patch can be estimated by the triangulation [6], [8], [31].”
BackgroundRelative Pose Estimation With a Single Affine Correspondence
Guan, B., Zhao, J. Y., Li, Z., Sun, F., & Fraundorfer, F. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3069806 · Cited by 42
“Our monocular VO is based on ORB-SLAM2 [49].”
MethodLiu, W.-Z., Yu, B., Gan, Y.-M., Liu, Q., Tang, J., Liu, S.-S., & Zhu, Y. (2021) · Micro · doi:10.1145/3466752.3480077 · Cited by 50
“LocalizationAccelerators Prior accelerators target bothASIC [42, 73, 83] and FPGA [9, 11, 24, 25, 45, 46, 86, 88], and accelerate different algorithms including optimization-based algorithms [21, 22, 58, 65] (e.”
MethodRobust AUV Visual Loop-Closure Detection Based on Variational Autoencoder Network
Wang, Y., Ma, X., Wang, J., Hou, S., Dai, J. P., Gu, D., & Wang, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3145860 · Cited by 42
“Due to the difference between underwater and ground terrestrial environments, some terrestrial algorithms SeqLPD [5], ORB-SLAM2 [18] were prone to collapse in underwater datasets, and so far we cannot directly compare the proposed method with related exiting loop closure detection algorithms.”
BackgroundMethodA review of research on slam technology based on the fusion of lidar and vision
Chen, P., Zhao, X., Zeng, L., Liu, L., Liu, S., Sun, L., Li, Z., Chen, H., Liu, G., Qiao, Z., et al. (2025) · Sensors · doi:10.3390/s25051447 · Cited by 46
LE-VINS: A Robust Solid-State-LiDAR-Enhanced Visual-Inertial Navigation System for Low-Speed Robots
Tang, H., Niu, X., Zhang, T., Wang, L., & Liu, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3260279 · Cited by 42
“The depth image with the RGB image is incorporated into ORB_SLAM2 [6] to achieve an RGB-D simultaneous localization and mapping (SLAM).”
BackgroundMethodTextSLAM: Visual SLAM With Semantic Planar Text Features
Li, B., Zou, D., Huang, Y., Niu, X., Pei, L., & Yu, W.-X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3324320 · Cited by 45
“Existing visual SLAM systems usually use the bag-of-visual-words vectors [63], [64] for comparison.”
BackgroundMethodInfluentialVisual SLAM for Unmanned Aerial Vehicles: Localization and Perception
Zhuang, L., Zhong, X., Xu, L., Tian, C., & Yu, W.-S. (2024) · Italian National Conference on Sensors · doi:10.3390/s24102980 · Cited by 46
Lin, S., Cheng, R., Wang, K., & Yang, K. (2018) · Sensors · doi:10.3390/s18082476 · Cited by 41
“For instance, ORBSLAM2 [20] leveraged visual odometry to track unmapped regions and matches with map points that allow for zero-drift localization.”
BackgroundMethodJigsawNet: Shredded Image Reassembly Using Convolutional Neural Network and Loop-Based Composition
Le, C., & Li, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2903298 · Cited by 41
“Such a loop closure constraint has been widely applied on refining or pruning pairwise alignments in many vision-based SLAM and environment reconstruction tasks [10]–[12].”
BackgroundMethodInfluentialMicroservice-based cloud robotics system for intelligent space
Xia, C., Zhang, Y., Wang, L., Coleman, S., & Liu, Y. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.10.001 · Cited by 41
“The ORB-SLAM2 can work in real time on the standard CPUs (Central processing units) in a wide variety of environments from small hand-held indoors scene to drones flying in industrial environments and cars driving around a city for monocular, stereo and RGB-D cameras.”
InfluentialCollaborative Visual SLAM Using Compressed Feature Exchange
Opdenbosch, D. V., & Steinbach, E. G. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2878920 · Cited by 40
“This corresponds to the timings reported by the ORB-SLAM2 authors [10] without the ORB feature extraction which is outsourced to the client.”
BackgroundMethodResultStereo Visual SLAM for Autonomous Vehicles: A Review
Gao, B., Lang, H., & Jing Ren, A. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283161 · Cited by 41
“ProSLAM [3], ORB-SLAM [4, 5] and OpenVSLAM [6] are typical open-source indirect VSLAM frameworks that have achieved diverse applications and splendid performance.”
BackgroundReal-Time Lidar-based Localization of Mobile Ground Robot
Belkin, I., Abramenko, A., & Yudin, D. A. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.04.164 · Cited by 41
Improved Point-Line Feature Based Visual SLAM Method for Complex Environments
Zhou, F., Zhang, L., Deng, C., & Fan, X. (2021) · Sensors · doi:10.3390/s21134604 · Cited by 41
“These methods of features extraction and matching have been relatively complete, and the processing process can be referred to [36], which will not be described here.”
MethodDesign, Detection, and Tracking of Customized Fiducial Markers
Jurado-Rodríguez, D., Muñoz‐Salinas, R., Garrido-Jurado, S., & Medina-Carnicer, R. (2021) · IEEE Access · doi:10.1109/access.2021.3118049 · Cited by 41
“Once a marker has been detected, a collection of ORB keypoints [35] are obtained from the image I employing the same rationale as in the recent UcoSLAM [25] and ORB-SLAM [26] methods.”
MethodLoop Closure Detection Using Local 3D Deep Descriptors
Zhou, Y., Wang, Y., Poiesi, F., Qin, Q. M., & Wan, Y. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3156940 · Cited by 41
Du, T., Shi, S., Zeng, Y., Yang, J., & Guo, L. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3156976 · Cited by 41
Integrity of Visual Navigation—Developments, Challenges, and Prospects
Zhu, C., Meurer, M., & Günther, C. G. (2022) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.518 · Cited by 43
Magnetic Field-Enhanced Learning-Based Inertial Odometry for Indoor Pedestrian
Wang, Y., Kuang, J., Li, Y., & Niu, X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3186358 · Cited by 40
“Camera-based SLAM includes visual odometry (VO) [3] and visual-inertial odometry (VIO) [4] [5]-based built-in cameras, and the inertial sensor of the smartphone is a low-cost and high-precision positioning solution with the potential to be widely used.”
Shamwell, E. J., Leung, S., & Nothwang, W. D. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593573 · Cited by 41
Yu, L., Yang, E., & Yang, B. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01645-w · Cited by 42
“Compared to the ORBSLAM2 [14], the HE-SLAM was more robust in a harsh environment.”
BackgroundOptimization RGB-D 3-D Reconstruction Algorithm Based on Dynamic SLAM
Pan, Z., Hou, J., & Yu, L. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3248116 · Cited by 41
“Mur-Artal and Tardós [4] proposed the ORB-SLAM2 framework based on ORB-SLAM [11] to meet the requirements for speed and accuracy in this development environment.”
BackgroundMethodPan, C., Li, Z., Zhang, Q., Soja, B. S., & Gao, J. (2024) · Measurement · doi:10.1016/j.measurement.2024.114420 · Cited by 40
Semantic Visual Simultaneous Localization and Mapping: A Survey
Chen, K., Xiao, J., Liu, J., Tong, Q., Zhang, H., Liu, R., Zhang, J., Ajoudani, A., & Chen, S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3556928 · Cited by 52
“Subsequent iterations, ORB-SLAM2 [25] and ORB-SLAM3 [26], further enhance localization accuracy and robustness by integrating support for multi-sensor fusion, such as stereo cameras and IMU data.”
Online Adaptive Keypoint Extraction for Visual Odometry Across Different Scenes
Zhang, R., Wang, Y., Li, Z., Ding, F., Wei, C., & Wu, M. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3575644 · Cited by 43
“[1], [2], [3], [4], [5], [6] These methods usually extract the geometry constraints based on the correspondences between sparse feature points or photometric consistency over pixels.”
Landmark based localization in urban environment
Qu, X., Soheilian, B., & Nicolas Paparoditis, A. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.09.010 · Cited by 40
“A more efficient and accurate approach on feature based VO, is proposed as ORB-SLAM (Mur-Artal and Tardós, 2016).”
BackgroundMethodInfluentialQiu, L., & Ren, H. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00295 · Cited by 41
“In this paper, we propose to use the ORBSLAM [11][12] with a low-cost endoscope to estimate its location and reconstruct the 3D scene in an oral cavity.”
MethodReactive obstacle avoidance of monocular quadrotors with online adapted depth prediction network
Yang, X. Y., Luo, H., Wu, Y., Gao, Y., Liao, C., & Cheng, K.-T. T. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.10.019 · Cited by 40
A Unified Framework for Mutual Improvement of SLAM and Semantic Segmentation
Wang, K., Lin, Y., Wang, L., Han, L., Hua, M., Wang, X., Lian, S., & Huang, B. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793499 · Cited by 40
“Various works on vSLAM have been proposed in recent years, from the seminal work PTAM [4] to the popular ORB-SLAM2 [5].”
BackgroundMethodResultInfluentialShot type constraints in UAV cinematography for autonomous target tracking
Karakostas, I., Mademlis, I., Nikolaidis, N., & Pitas, I. (2019) · Information Sciences · doi:10.1016/j.ins.2019.08.011 · Cited by 40
Merrill, N., & Huang, G. P. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968159 · Cited by 40
“This method is highly successful in real-world applications, and has been deployed in many SLAM systems such as ORB-SLAM [8, 9].”
MethodStereo Visual SLAM Based on Unscented Dual Quaternion Filtering
Bultmann, S., Li, K., & Hanebeck, U. (2019) · Fusion · doi:10.23919/fusion43075.2019.9011391 · Cited by 51
“match while providing similar performance to the popular SIFT and SURF features which makes them a good choice for feature-based SLAM algorithms [1], [27].”
BackgroundMethodInfluentialROVINS: Robust Omnidirectional Visual Inertial Navigation System
Seok, H., & Lim, J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3010457 · Cited by 40
“However, as there was no public SLAM and VIO systems to support the omnidirectional camera system, ORB-SLAM2 [7] was chosen instead, by utilizing the rectified 120◦ stereo images generated from the datasets as inputs, as in [27].”
BackgroundMethodSBAS: Salient Bundle Adjustment for Visual SLAM
Wang, K., Ma, S., Ren, F., & Lǚ, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3105243 · Cited by 41
Ruhkamp, P., Gao, D., Chen, H., Navab, N., & Busam, B. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00092 · Cited by 42
“…to pixel-wise misalignment and ”flying pixels” are significantly reduced. long ago been examined in classical SfM and visual odometry, where usually computationally expensive local and global bundle adjustment aligns sparse triangulated points [33, 34] to account for erroneous initial predictions.”
BackgroundEnergy-Based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning
Gan, L., Grizzle, J., Eustice, R. M., & Ghaffari, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3188100 · Cited by 36
“Specifically, we use ORB-SLAM2 [33] to estimate the robot poses, and build a local robot-centric probabilistic elevation map using point clouds captured by the depth camera.”
MethodDiffPoseNet: Direct Differentiable Camera Pose Estimation
Parameshwara, C. M., Hari, G., Fermuller, C. M., Sanket, N. J., & Aloimonos, Y. (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/cvpr52688.2022.00672 · Cited by 40
Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends
Favorskaya, M. N. (2023) · Electronics · doi:10.3390/electronics12092006 · Cited by 43
Autonomous localized path planning algorithm for UAVs based on TD3 strategy
Feiyu, Z., Da-yan, L., Zhengxu, W., Jianlin, M., & Wang, N. (2024) · Scientific Reports · doi:10.1038/s41598-024-51349-4 · Cited by 46
“…time, adding STATE information preprocessing module, single-step rewarding noise value set to 0.5, and initialization height threshold set to [4–6 m] as the baseline, and meanwhile, in order to increase the algorithm retrospective, the maximum number of steps in a single act is elevated to…”
MethodInfluential3D reconstruction of spherical images: a review of techniques, applications, and prospects
Jiang, S., You, K., Li, Y., Weng, D., & Chen, W. (2024) · Geo-spatial Information Science · doi:10.1080/10095020.2024.2313328 · Cited by 41
“[107] extended the ORB-SLAM [117], [118] system into a multi-fisheye omnidirectional SLAM system, termed MultiCol-SLAM, which supports the arbitrary rigidly coupled multi-camera systems.”
An Adaptive Lighting Indoor vSLAM With Limited On-Device Resources
Hu, Z., Qi, W., Ding, K., Liu, G., & Zhao, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3406816 · Cited by 41
“Mur-Artal et al. [15], [16] further optimized the system performance with ORB-SLAM and ORB-SLAM2, utilizing a three-thread parallel architecture and oriented FAST and rotationally invariant BRIEF (ORB) features.”
MethodMUSt3R: Multi-view Network for Stereo 3D Reconstruction
Cabon, Y., Stoffl, L., Antsfeld, L., Csurka, G., Chidlovskii, B., Revaud, J., & Leroy, V. (2025) · 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/cvpr52734.2025.00106 · Cited by 75
Robust edge-based visual odometry using machine-learned edges
Schenk, F., & Fraundorfer, F. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202305 · Cited by 39
“TABLE II: Comparison of the ATE in [m], the RPE in [m/frame] and the RPE in [ s ] of DVO [6], ORB-SLAM2 [5], RGBD-SLAM [4], D-EA [9] and REVO in key frame (KF) and frame-to-frame (FF) VO on the RGBD TUM datasets [11].”
BackgroundMethodInfluentialMarker-Based Multi-Sensor Fusion Indoor Localization System for Micro Air Vehicles
Xing, B., Zhu, Q., Pan, F., & Feng, X. (2018) · Sensors · doi:10.3390/s18061706 · Cited by 39
“In this section, the location performance of the proposed MMFL system is compared with the ORB-SLAM2 [34], where the benchmark trajectory is provided by the localization system including four UWB base stations.”
MethodInfluentialBioinspired design of a landing system with soft shock absorbers for autonomous aerial robots
Zhang, K., Chermprayong, P., Tzoumanikas, D., Li, W., Grimm, M., Smentoch, M., Leutenegger, S., & Kovač, M. (2018) · Journal of Field Robotics · doi:10.1002/rob.21840 · Cited by 39
“The underlying principle is inspired by ORB-SLAM 2 (Mur-Artal and Tardós, 2017), where we use depth measurements when available to create landmark observations in a virtual stereo camera.”
MethodMagicVO: 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 52
“For example, ORB_SLAM2 is used by many robots as their own positioning and navigation algorithm [9].”
MethodMa, F., Shi, J., Yu, Y., Li, J., & Dai, K. (2019) · Sensors · doi:10.3390/s19214816 · Cited by 40
“On the other hand, visual odometry (VO), which adopts visual sensors, is gaining significant interest by the robotics community owing to the abundant perceptive information, small size and low cost [7–9].”
BackgroundAggressive Perception-Aware Navigation Using Deep Optical Flow Dynamics and PixelMPC
Lee, K., Gibson, J., & Theodorou, E. A. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2965911 · Cited by 39
“a traditional (not end-to-end) navigation, DLaided vision pipeline played a big role in detecting objects and obstacles as a perception module and sometimes as a part of state estimation (e.g. VSLAM [7]). A controller then performed its task of navigation, avoidance, or tracking using the information provided from the…”
MethodPetráček, P., Krátký, V., & Saska, M. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2969935 · Cited by 39
“[10] R. Mur-Artal and J. D. Tards, “ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras,” IEEE Trans.”
BackgroundJacobson, A., Zeng, F., Smith, D., Boswell, N., Peynot, T., & Milford, M. J. (2020) · Journal of Field Robotics · doi:10.1002/rob.21978 · Cited by 40
FinnForest dataset: A forest landscape for visual SLAM
Ali, I., Durmush, A., Suominen, O., Yli-Hietanen, J., Peltonen, S., Collin, J., & Gotchev, A. P. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103610 · Cited by 39
Empty Cities: A Dynamic-Object-Invariant Space for Visual SLAM
Bescos, B., Cadena, C., & Neira, J. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.3031267 · Cited by 39
“Image features are important for localization since many visual SLAM systems rely on them as their core (ORB-SLAM [23]).”
BackgroundMethodInfluentialWen, S.-H., Zhao, Y., Liu, X., Sun, F., Lu, H., & Wang, Z. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3041852 · Cited by 33
“In [29], the stereo-VINS method [30] has better precision and robustness than monocular-VINS because the depth of stereo VS-LAM can be computed in each frame using the disparity via two calibrated cameras.”
MethodA Comparison of Graph Optimization Approaches for Pose Estimation in SLAM
Jurić, A., Kendes, F., Marković, I., & Petrovic, I. K. (2021) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro52101.2021.9596721 · Cited by 42
“ORB-SLAM ( [16], [17]) uses g(2)o as a back-end for camera pose optimization, and SVO [18] uses it for visual odometry.”
Method
Metadata
- Authors
- Mur-Artal, R., & Tardos, J. D.
- Affiliations
- Instituto de Investigación en Ingeniería de Aragón (ES)
- Venue
- IEEE Transactions on Robotics
- Published
- 2017-10
- Volume
- 33
- Issue
- 5
- Pages
- 1255-1262
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2535547924
- Cited by
- 6,898
- References
- 21
- Citations by year
- 2026: 521 · 2025: 851 · 2024: 944 · 2023: 962 · 2022: 910 · 2021: 870 · 2020: 754 · 2019: 636 · 2018: 360 · 2017: 90
- FWCI
- 463.87
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Spanish government (DPI2015-67275)
- Aragón regional government (DGA T04-FSE)
- Ministerio de Educación Scholarship (FPU13/04175)
- 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 Vision and Imaging
- Keywords
- ORB-SLAM2, SLAM, monocular SLAM, stereo SLAM, RGB-D SLAM, loop closure, relocalization, bundle adjustment, visual odometry, trajectory estimation
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
