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
Flagged first, then by citations
1 of the 21 references couldn’t be matched to a known paper.
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 701–800 of 1,004
FogROS: An Adaptive Framework for Automating Fog Robotics Deployment
Chen, K. E., Liang, Y., Jha, N., Ichnowski, J., Danielczuk, M., Gonzalez, J. E., Kubiatowicz, J. D., & Goldberg, K. Y. (2021) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49439.2021.9551628 · Cited by 39
“ORB-SLAM2 [27] is a visual simultaneous localization and mapping system that uses monocular video input.”
InfluentialEIL‐SLAM: Depth‐enhanced edge‐based infrared‐LiDAR SLAM
Chen, W., Wang, Y., Chen, H., & Liu, Y. (2021) · Journal of Field Robotics · doi:10.1002/rob.22040 · Cited by 38
“…images, find the feature correspondences between images, and finally track features to estimate camera motion; examples of these methodologies include oriented FAST and rotated BRIEF (ORB), speeded ‐ up robust features, and scale ‐ invariant feature transform (Mur ‐ Artal & Tardós, 2017).”
MethodChaffre, T., Moras, J., Chan-Hon-Tong, A., & Marzat, J. (2020) · Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics · doi:10.5220/0009821603140323 · Cited by 38
Experimental evaluation of Visual‐Inertial Odometry systems for arable farming
Cremona, J., Comelli, R., & Pire, T. (2022) · J. Field Robotics · doi:10.1002/rob.22099 · Cited by 36
“However, to the best of our knowledge, there is no publicly available evaluation of this kind more than the limited one given in the same publication, between a localization system proposed by the authors and a modified version of ORB-SLAM2 (Mur-Artal & Tardós, 2017b).”
MethodVoice Interaction Recognition Design in Real-Life Scenario Mobile Robot Applications
Li, S., Liu, Y., Chen, Y.-C., Feng, H.-M., Shen, P.-K., & Wu, Y.-C. (2023) · Applied Sciences · doi:10.3390/app13053359 · Cited by 41
Samadzadeh, A., & Nickabadi, A. (2022) · IEEE Transactions on robotics · doi:10.1109/tro.2023.3268591 · Cited by 30
“These residuals are prominent in state-of-art VIO and SLAM frameworks [8], [10], [16].”
End-to-End RGB-D SLAM With Multi-MLPs Dense Neural Implicit Representations
Li, M., He, J., Wang, Y., & Wang, H. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3311365 · Cited by 40
Review on SLAM algorithms for Augmented Reality
Sheng, X., Mao, S., Yan, Y., & Yang, X. (2024) · Displays · doi:10.1016/j.displa.2024.102806 · Cited by 41
How NeRFs and 3-D Gaussian Splatting Are Reshaping SLAM: A Survey
Tosi, F., Zhang, Y., Gong, Z., Sandström, E., Mattoccia, S., Oswald, M. R., & Poggi, M. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3666139 · Cited by 109
“This is facilitated by the coordination with the camera tracking component of ORB-SLAM2 [82].”
BackgroundMethodInfluentialPIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
Solin, A., Cortés, S., Rahtu, E., & Kannala, J. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00073 · Cited by 38
A Compatible Framework for RGB-D SLAM in Dynamic Scenes
Zhao, L., Liu, Z., Chen, J., Cai, W., Wang, W., & Zeng, L. (2019) · IEEE Access · doi:10.1109/access.2019.2922733 · Cited by 38
A Survey of Simultaneous Localization and Mapping.
Huang, B., Zhao, J., & Liu, J. (2019) · Cited by 38
Computer Vision-Assisted 3D Object Localization via COTS RFID Devices and a Monocular Camera
Wang, Z., Xu, M., Ye, N., Xiao, F., Wang, R., & Huang, H. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2954830 · Cited by 38
“However, without additional depth information for the monocular camera, the existing monocular VO (MVO) [14], [15] only recovers the camera trajectory in the camera view from 2D images.”
BackgroundExperiment for pose estimation of uncooperative space debris using stereo vision
Jongh, W. C. D., Jordaan, H. W., & van Daalen, C. E. (2019) · Acta Astronautica · doi:10.1016/j.actaastro.2019.12.006 · Cited by 38
Comparative Study of Deep Learning Based Features in SLAM
Deng, C., Qiu, K., Xiong, R., & Zhou, C. (2019) · Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) · doi:10.1109/acirs.2019.8935995 · Cited by 39
“Now, the following experiment embed these methods of feature detection into one same system of which backbone is ORB-SLAMv2 [5].”
MethodAn Efficient and Accurate Algorithm for the Perspecitve-n-Point Problem
Zhou, L., & Kaess, M. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968482 · Cited by 38
“This algorithm is adopted in the ORB-SLAM system [24].”
MethodAugmenting Visual Place Recognition With Structural Cues
Oertel, A., Cieslewski, T., & Scaramuzza, D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3009077 · Cited by 46
“We verify our method throughout several experiments by comparing its retrieval performance to state-of-the-art baselines such as NetVLAD [18], SeqSLAM [26], and DenseVLAD [27].”
InfluentialAntonini, A., Guerra, W., Murali, V., Sayre-McCord, T., & Karaman, S. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920908331 · Cited by 40
SGC-VSLAM: A Semantic and Geometric Constraints VSLAM for Dynamic Indoor Environments
Yang, S., Fan, G., Bai, L., Zhao, C., & Li, D. (2020) · Sensors · doi:10.3390/s20082432 · Cited by 38
“Because the ORB features are prone to concentrate in the strong texture region, the quadtree-based method was adopted by ORB-SLAM2 to extract uniform ORB features [5].”
BackgroundMethodInfluentialMGC-VSLAM: A Meshing-Based and Geometric Constraint VSLAM for Dynamic Indoor Environments
Yang, S., Fan, G., Bai, L., Li, R., & Li, D. (2020) · IEEE Access · doi:10.1109/access.2020.2990890 · Cited by 40
“These methods are similar to the processing flow in the ORB-SLAM2 [3], [4] system, and will not be repeated here.”
BackgroundMethodInfluentialMakansi, O., Çiçek, Ö., Buchicchio, K., & Brox, T. (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/cvpr42600.2020.00441 · Cited by 37
Ground and Aerial Collaborative Mapping in Urban Environments
He, J., Zhou, Y., Huang, L., Kong, Y., & Cheng, H. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3032054 · Cited by 38
“Three other odometry meth-ods are compared, including LiDAR-based method LOAM [15] and LeGO-LOAM [24] as well as visual-based method ORB-SLAM2 (mono) [34].”
MethodA mapping of visual SLAM algorithms and their applications in augmented reality
Covolan, J. P. M., Sementille, A. C., & Sanches, S. R. R. (2020) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr51698.2020.00019 · Cited by 38
“7) ORB-SLAM 2: No trabalho de Mur-Artal e Tardós [22], é proposta uma nova versão do ORB-SLAM, denominada ORB-SLAM 2, que generaliza o algoritmo original para lidar também com a entrada de visão estéreo e câmeras RGB-D.”
BackgroundCORAL: Colored structural representation for bi-modal place recognition
Pan, Y., Xu, X., Li, W., Cui, Y., Wang, Y., & Xiong, R. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635839 · Cited by 39
“Traditionally, some salient image parts are encoded as handcrafted local features, such as SURF [3], SIFT [14], or ORB [16, 17], and then these local features can be aggregated to a global descriptor leveraging feature aggregated methods, such as Bag-of-visual-words [6], VLAD [10] and Fisher Vectors [9].”
MethodSampling-Based Path Planning for High-Quality Aerial 3D Reconstruction of Urban Scenes
Yan, F., Xia, E., Li, Z., & Zhou, Z. (2021) · Remote Sensing · doi:10.3390/rs13050989 · Cited by 38
“As ORB features are extremely fast to compute and match [31], the key image selection can be finished immediately (i.”
BackgroundLiveMap: Real-Time Dynamic Map in Automotive Edge Computing
Liu, Q., Han, T., Xie, J. L., & Kim, B. (2021) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom42981.2021.9488872 · Cited by 38
“, ORB SLAM2 [7], or high-accuracy GPS, which could achieve centimeter-level estimation errors of vehicle locations.”
BackgroundULSD: Unified line segment detection across pinhole, fisheye, and spherical cameras
Li, H., Yu, H., Wang, J., Yang, W. T., Yu, L., & Scherer, S. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.06.004 · Cited by 37
A Smart Sterilization Robot System With Chlorine Dioxide for Spray Disinfection
Zhao, Y.-L., Huang, H., Chen, T.-L., Chiang, P., Chen, Y.-H., Yeh, J.-H., Huang, C.-H., Lin, J.-F., & Weng, W. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3101593 · Cited by 40
Kachurka, V., Rault, B., Muñoz, F. I. I., Roussel, D., Bonardi, F., Didier, J.-Y., Hadj-Abdelkader, H., Bouchafa, S., Alliez, P., & Robin, M. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3101121 · Cited by 38
“To fullfill the characteristics described above two families emerge as popular choices: ORB-SLAM [42], ORB-SLAM2 [42] and more particularly its visual-inertial successors VI-ORB-SLAM [43] and ORB-SLAM3 [44] as well as VINS-Mono [28] and its successor VINS-Fusion [8].”
Hybrid Visual SLAM for Underwater Vehicle Manipulator Systems
Billings, G., Camilli, R., & Johnson‐Roberson, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3176448 · Cited by 39
“Since its inception, ORB-SLAM [1] and its later adaptation to stereo, ORB-SLAM2 [2], remains one of the most widely adopted and complete feature based SLAM”
BackgroundLi, X., Li, S., Li, S., Zhou, Y., Sun, M., Xu, Q., & Xu, Z. (2022) · GPS Solutions · doi:10.1007/s10291-022-01306-3 · Cited by 39
“In a typical visual method, the positions of the features are included in the state vector and estimated together with camera poses (Mur-Artal and Tardós 2017; Qin et al. 2018).”
MethodADOP: Approximate Differentiable One-Pixel Point RenderingPreprint
Rückert, D., Franke, L., & Stamminger, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06635 · Cited by 38
“To further improve the pose estimation of our inverse rendering pipeline, we follow state-of-the-art SLAM systems [Engel et al. 2017; Mur-Artal and Tardós 2017; Rückert and Stamminger 2021] that optimize the rigid transformation ( 𝑅,𝑡 ) ∈ 𝑆𝐸 ( 3 ) in tangent-space.”
MethodAutomatic three‐dimensional mapping for tree diameter measurements in inventory operations
Tremblay, J., Béland, M., Gagnon, R., Pomerleau, F., & Giguère, P. (2020) · Journal of Field Robotics · doi:10.1002/rob.21980 · Cited by 37
“Even in the simplest forest in their dataset, only ORBSLAM2 (Mur ‐ Artal & Tardós, 2017) and Direct Sparse Odometry (Engel, Koltun, & Cremers, 2018) managed to localize.”
BackgroundLai, T. (2022) · Sensors · doi:10.3390/s22197265 · Cited by 48
“• ORB-SLAM2 (2017) [48] make use of multiple features from Monocular, Stereo and RGB-D cameras which greatly enhance the versatility of the method.”
MethodA Semantic Slam-Based Dense Mapping Approach for Large-Scale Dynamic Outdoor Environment
Yang, L., & Wang, L. (2022) · Measurement · doi:10.1016/j.measurement.2022.112001 · Cited by 38
SWformer-VO: A Monocular Visual Odometry Model Based on Swin Transformer
Wu, Z., & Zhu, Y. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3384911 · Cited by 38
“…SWformer-VO’s superior performance on the KITTI dataset compared to DeepVO [3], SFMlearner [6], TSformer-VO [11], GeoNet [16], ORB-SLAM2 [20], Depth-VO-Feat [21], Bian et al. [22], Masked Gans [23], Wang et al. [24], Masked Gans, and Wang et al. Additionally, its effectiveness is…”
MethodKlenk, S., Motzet, M., Koestler, L., & Cremers, D. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00036 · Cited by 42
“Drawing inspiration from the classical methods [12, 38], a beneficial approach has emerged to first predict correspondences and subsequently use these in a principled, geometry-based manner for pose prediction [52, 53, 60, 65].”
Exploring Deep Learning-Based Visual Localization Techniques for UAVs in GPS-Denied Environments
Al-Jarrah, O. Y., Shatnawi, A. S., Shurman, M. M., Ramadan, O. A., & Muhaidat, S. (2024) · IEEE Access · doi:10.1109/access.2024.3440064 · Cited by 37
“Therefore, the momentum of the research effort has shifted towards AVL methods, which are more immune to drifting errors observed in RVL methods [16].”
MethodAdaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
Cheng, J., Yin, W., Wang, K., Chen, X., Wang, S., & Yang, X. Y. (2024) · 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/cvpr52733.2024.00966 · Cited by 46
“We selected a representative slam system, i.e. ORBSLAM2[25], and used two versions of it to obtain poses respectively, one monocular version (denoted as ORB1) and one stereo version (denoted as ORB2).”
BackgroundMethodFrom the Calibration of a Light-Field Camera to Direct Plenoptic Odometry
Zeller, N., Quint, F., & Stilla, U. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2737965 · Cited by 37
“Since in this case absolute depth is received from a static recording, such approaches are able to measure the scale of the scene without using any additional sensors [21]–[24].”
BackgroundMethodEfficient 2D-3D Matching for Multi-Camera Visual Localization
Geppert, M., Liu, P., Cui, Z., Pollefeys, M., & Sattler, T. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794280 · Cited by 37
“y [2] and that multicamera systems significantly boost localization performance in challenging conditions [31]. Existing work on multi-camera localization has mainly focused on stereo SLAM [13], [21], [28], camera calibration [12], [13], and camera pose estimation [6], [17], [39], [41]. The latter two types of approach…”
BackgroundLearning to Capture a Film-Look Video with a Camera Drone
Huang, C. X., Yang, Z., Kong, Y., Chen, P., Yang, X. Y., & Cheng, K.-T. T. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793915 · Cited by 36
“ORB-SLAM [7, 8]) can estimate the camera pose (without the absolute scale), the ambiguous scale makes it infeasible to feed the camera pose with different scales into the training network.”
BackgroundElaborate Monocular Point and Line SLAM With Robust Initialization
Lee, S. J., & Hwang, S. S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00121 · Cited by 37
“Therefore, KLT-based SLAM only utilizes RANSAC-based n-points algorithms [25, 26, 27] for pose estimation that is less accurate than state-of-the-art indirect SLAM systems [10, 11].”
MethodRolling-Shutter Modelling for Direct Visual-Inertial Odometry
Schubert, D., Demmel, N., von Stumberg, L., Usenko, V., & Cremers, D. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968539 · Cited by 39
“A visual-inertial extension of ORB-SLAM [19], [6], a state-of-the-art keyframe-based SLAM approach, is given in [20].”
Autonomous navigation for UAVs managing motion and sensing uncertainty
González-Sieira, A., Cores, D., Mucientes, M., & Bugarín, A. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103455 · Cited by 37
“For this experiment the UAV state was estimated from the on-board RGB-D camera, using ORB-SLAM2 [35] with loop closure, combined with the inertial unit using an Extended Kalman Filter.”
MethodInfluentialAn UWB/Vision Fusion Scheme for Determining Pedestrians’ Indoor Location
Liu, F., Zhang, J., Wang, J., Han, H., & Deng, Y. (2020) · Sensors · doi:10.3390/s20041139 · Cited by 37
“Secondly, a visual positioning scheme based on ORB‐SLAM is adopted [23,24], including the preprocessing of the video stream and the epipolar geometry constraint.”
BackgroundMethodDynamic-DSO: Direct Sparse Odometry Using Objects Semantic Information for Dynamic Environments
Sheng, C., Pan, S., Gao, W., Tan, Y. S., & Zhao, T. (2020) · Applied Sciences · doi:10.3390/app10041467 · Cited by 36
“Cui et al. [3] proposed Semantic Optical Flow SLAM (SOF-SLAM), which is built on RGB-D mode of ORB-SLAM2 [8].”
BackgroundMethodInfluentialSemantic SLAM With More Accurate Point Cloud Map in Dynamic Environments
Fan, Y., Zhang, Q., Liu, S., Tang, Y., Jing, X., Yao, J., & Han, H. W. (2020) · IEEE Access · doi:10.1109/access.2020.3003160 · Cited by 37
“Recent years have seen the great development of visual SLAM, which can be classified into feature-based indirect SLAM systems [3]–[5] and direct ones based on photometric error [6], [7].”
BackgroundMethodSeed: A Segmentation-Based Egocentric 3D Point Cloud Descriptor for Loop Closure Detection
Fan, Y., He, Y., & Tan, U.-X. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341517 · Cited by 37
“For example, the similarity between different places captured by camera can be calculated by means of the state-of-art method, bag-of-words (e.g. [1], [2]), and it has shown great success in real-world applications.”
MethodWöhle, L., & Gebhard, M. (2021) · Sensors · doi:10.3390/s21051798 · Cited by 37
“In this work we use a state of the art and open source V-SLAM approach, namely ORB-SLAM 2 [21].”
BackgroundMethodInfluentialEudoxus: Characterizing and Accelerating Localization in Autonomous Machines Industry Track Paper
Gan, Y., Bo, Y., Tian, B., Xu, L., Hu, W., Liu, S., Liu, Q., Zhang, Y., Tang, J., & Zhu, Y. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00074 · Cited by 44
“, constrained optimization-based SLAM [67], [29], [71], probabilistic estimation-based VIO [61], [64], [49], [60], and registration against the map [67], [65]) is sufficiently flexible to adapt to different real-world operating scenarios.”
BackgroundMethodAccurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry
Tian, R., Zhang, Y., Zhu, D., Liang, S., Coleman, S., & Kerr, D. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561215 · Cited by 37
“The quantitative comparison between our method and the baseline methods, including [1], [10], [11], [16], [17], [22], is presented in Table II.”
BackgroundResultTowards Accurate Loop Closure Detection in Semantic SLAM With 3D Semantic Covisibility Graphs
Qian, Z., Fu, J., & Xiao, J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3145066 · Cited by 37
“The similarity score is obtained by computing the L 1 -score between the two BoW vectors d c and d l of frame K c and K l : (1) We also impose the same temporal consistency in ORB-SLAM2 [1] on generating loop closure candidates.”
MethodResultInfluentialBare-hand gesture occlusion-aware interactive augmented reality assembly
Fang, W., & Hong, J. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.09.009 · Cited by 38
Coarse-to-fine Semantic Localization with HD Map for Autonomous Driving in Structural Scenes
Guo, C., Lin, M., Guo, H., Liang, P., & Cheng, E. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635923 · Cited by 36
“Lidar point [5] and vision feature point [6] are two main categories of point cloud-based prior map.”
BackgroundBalancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
Zhang, L., Wisth, D., Camurri, M., & Fallon, M. F. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3137910 · Cited by 36
“For example, the combination of feature extraction and stereo matching in ORB-SLAM2 [21] takes ∼ 24.8 ms which is significant for a 30 Hz image stream.”
InfluentialExploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation
Karpov, A., & Makarov, I. (2022) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar55827.2022.00089 · Cited by 36
“Moreover, depth maps have a wide range of applications including, 3D photography [24] visual SLAM [34, 35], 3D scene reconstruction [43] and mobile scanners [51].”
BackgroundZhu, F., Li, H., Li, J., Zhu, B., & Lei, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106944 · Cited by 37
Li, Z., Feng, L., Liang, C., Huang, Y., & Fan, M. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3610903 · Cited by 37
“Taking advantage of development in display techniques [31] and computer vision (CV) techniques (including SLAM [55], hand tracking [25], and object detection [79]), modern head-mounted AR devices allow users to see and interact with virtual objects in the immersive environment, which served as an important medium to e…”
BackgroundMin, F., Wu, Z., Li, D., Wang, G., & Liu, N. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3317056 · Cited by 36
“COEB-SLAM adopts ORB-SLAM2 [17] as the global SLAM solution and combines object detection, epipolar geometry constraint, and blur filtering to detect dynamic objects.”
MethodWei, Y., Zhou, B., Duan, Y., Liu, J., & An, D. U. (2023) · Applied Intelligence · doi:10.1007/s10489-023-05070-w · Cited by 36
“Most dynamic SLAM systems are based on ORB-SLAM2 [20] or Kinect-Fusion.”
Zhao, Z., Wu, C. W., Kong, X., Li, Q., Guo, Z., Lv, Z., & Du, X. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3562319 · Cited by 44
“ORB-SLAM [3] and ORB-SLAM2 [4] proposed by Mur-Artal et al. are complete visual SLAM schemes based on the feature-point method.”
MethodFeature-based visual odometry prior for real-time semi-dense stereo SLAM
Krombach, N., Droeschel, D., Houben, S., & Behnke, S. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.08.002 · Cited by 36
“A later extension of ORB-SLAM [9] incorporates stereo and depth cameras by using a dense depth estimation in order to initialize new ORB map points.”
MethodEfficient Object-Oriented Semantic Mapping With Object Detector
Nakajima, Y., & Saitô, H. (2018) · IEEE Access · doi:10.1109/access.2018.2887022 · Cited by 36
“Themethod achieves object-oriented semantic mapping by projecting key depth frames, in which regions are segmented geometrically and annotated with Single Shot Multi-box Detector (SSD) [20], based on the camera pose estimated by ORB-SLAM2 [21].”
MethodA deep learning gated architecture for UGV navigation robust to sensor failures
Patel, N., Choromanska, A., Krishnamurthy, P., & Khorrami, F. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.03.001 · Cited by 36
Bujanca, M., Gafton, P., Sajad Saeedi, G., Nisbet, A. P., Bodin, B., OaBoyle Michael, F. P., Davison, A. J., J., K. P. H., Riley, G. D., Lennox, B., et al. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794369 · Cited by 34
Robust GNSS-denied localization for UAV using particle filter and visual odometry
Jurevičius, R., Marcinkevičius, V., & Šeibokas, J. (2019) · Machine Vision and Applications · doi:10.1007/s00138-019-01046-4 · Cited by 36
A Tight Coupling of Vision-Lidar Measurements for an Effective Odometry
Seo, Y., & Chou, C. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8814164 · Cited by 36
“A visual map is comprised of a number of map points where a map point is a visual descriptor with its estimated 3D position [14].”
BackgroundMethodInfluentialSteReFo: Efficient Image Refocusing with Stereo Vision
Busam, B., Hog, M., McDonagh, S., & Slabaugh, G. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00411 · Cited by 40
“Depth estimation from imagery is a well studied problem with a long history to perform estimation from image pairs [43, 30, 47], from temporal image sequences in classical structure from motion (SfM) [12, 22] and simultaneous localization and mapping (SLAM) [18, 35, 11] and reasoning about overlapping images with vary…”
Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation
Cai, M., & Reid, I. D. (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/cvpr42600.2020.00322 · Cited by 35
“The features, such as ORB [44, 33], SIFT [30] and FAST [43], are descriptors of the local appearance around the key-points.”
A review of the challenges in mobile manipulation: systems design and RoboCup challenges
Sereinig, M., Werth, W., & Faller, L.-M. (2020) · e+i Elektrotechnik und Informationstechnik · doi:10.1007/s00502-020-00823-8 · Cited by 36
Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction
Zhou, L., Luo, Z., Zhen, M., Shen, T., Li, S., Huang, Z., Fang, T., & Quan, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58555-6_22 · Cited by 37
Liang, Y., Müller, S., Schwendner, D., Rolle, D., Ganesch, D., & Schaffer, I. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341419 · Cited by 36
“A popular visual odometry pipeline called ORB-SLAM2 was published by Mur-Artal et al. [11]. that provides a generic bundle adjustment-based simultaneous localization and mapping (SLAM) framework by exploiting ORB [12] features for monocular, stereo and RGB-D cameras, which allows for zero-drift localization.”
MethodSelf-Supervised Depth Completion From Direct Visual-LiDAR Odometry in Autonomous Driving
Song, Z., Lu, J., Yao, Y., & Zhang, J. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3106055 · Cited by 37
Edge Assisted Mobile Semantic Visual SLAM
Cao, H., Xu, J., Li, D., Shangguan, L., Liu, Y., & Yang, Z. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3201000 · Cited by 36
“As another promising alternative, vision-based indoor localization techniques, in particular, visual simultaneous localization and mapping (visual SLAM), attracts more attention in recent years [11], [12].”
BackgroundMethodPLD-VINS: RGBD visual-inertial SLAM with point and line features
Zhu, Y., Jin, R., Lou, T.-S., & Zhao, L.-Y. (2021) · Aerospace Science and Technology · doi:10.1016/j.ast.2021.107185 · Cited by 34
Autonomous Single-Image Drone Exploration With Deep Reinforcement Learning and Mixed Reality
Devo, A., Mao, J., Costante, G., & Loianno, G. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3154019 · Cited by 36
Huang, J., Wen, S., Liang, W., & Guan, W. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3231332 · Cited by 36
“While an RGB-D camera, termed an RGBD-Cam, collects the images of the surrounding environment to perform the ORB-SLAM2 algorithm [9].”
MethodDistributed Relative Localization Algorithms for Multi-Robot Networks: A Survey
Wang, S., Wang, Y., Li, D., & Zhao, Q. (2023) · Sensors · doi:10.3390/s23052399 · Cited by 39
“Existing SLAM is mainly implemented by camera [93] or LIDAR [94,95] or by adding IMU for multi-sensor fusion [77,96].”
Deep Learning for Omnidirectional Vision: A Survey and New PerspectivesPreprint
Ai, H., Cao, Z., Zhu, J., Bai, H., Chen, Y., & Wang, L. (2022) · doi:10.36227/techrxiv.19807699 · Cited by 36
SP-SLAM: Surfel-Point Simultaneous Localization and Mapping
Cho, H. M., Jo, H., & Kim, E. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3118719 · Cited by 35
“In the experiments, the proposed SP-SLAM is compared with ORB-SLAM2 [12], point-plane (P-P) SLAM [17], ElasticFusion [24], DVO [33], and RGB-D SLAM [34].”
BackgroundMethodInfluentialAslan, M. F., Durdu, A., & Sabancı, K. (2022) · Measurement · doi:10.1016/j.measurement.2022.111030 · Cited by 36
Amos-SLAM: An Anti-Dynamics Two-Stage RGB-D SLAM Approach
Zhuang, Y., Jia, P., Liu, Z., Li, L., Wu, C., Lu, X., Cui, W., & Liu, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3332395 · Cited by 35
“Although certain SLAM algorithms, such as ORB-SLAM2 [11], can eliminate some dynamic features using the RANSAC algorithm to classify a limited number of dynamic points as outliers to the static model, the algorithm becomes ineffective when dealing with a large number of dynamic objects in the…”
MethodVIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance
Solodar, D., & Klein, I. (2023) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2024.108466 · Cited by 36
“In recent years, many simultaneous localization and mapping (SLAM) techniques were developed, leveraging a variety of sensors, including stereo cameras [1], [2], [3], LiDAR [4], [5], [6], depth cameras [7], [8], ultra white-band sensors [9], [10], and magnetic sensors [11].”
BackgroundAn, P., Ding, J., Quan, S.-W., Yang, J.-Q., Yang, Y., Liu, Q., & Ma, J. (2024) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2024.3419758 · Cited by 41
“They exploited ORB-SLAM [89] to reconstruct all the planar boards.”
BackgroundMethodInfluentialWildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Zheng, J., Zhu, Z., Bieri, V., Pollefeys, M., Peng, S., & Armeni, I. (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/cvpr52734.2025.01070 · Cited by 48
“Results for ORB-SLAM2 [32] and NICE-SLAM [68] are taken from NICE-SLAM [68].”
InfluentialCrowdGIS: Updating Digital Maps via Mobile Crowdsensing
Peng, Z., Gao, S., Xiao, B., Guo, S., & Yang, Y. (2017) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2017.2761793 · Cited by 35
“ORB-SLAM2 [3] utilizes monocular, stereo, and RGB-D sensors to perform relocalization, loop closing, and reuse its map in real time on standard CPUs.”
Real-time Depth Estimation Using Recurrent CNN with Sparse Depth Cues for SLAM System
Lee, S. J., Choi, H., & Hwang, S. S. (2019) · International Journal of Control Automation and Systems · doi:10.1007/s12555-019-0350-8 · Cited by 35
“Currently, camera-based Visual SLAM (Simultaneo-usly Localization and Mapping) systems [6, 7] has considered to use depth information.”
BackgroundMethodData Flow ORB-SLAM for Real-time Performance on Embedded GPU Boards
Aldegheri, S., Bombieri, N., Bloisi, D. D., & Farinelli, A. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967814 · Cited by 35
“The use of parallel threads allows for obtaining realtime processing on an Intel Core i7 desktop PC with 16GB RAM [4].”
BackgroundMethodInfluentialDeep Learning for Underwater Visual Odometry Estimation
Teixeira, B., Silva, H. M., Matos, A. C., & Silva, E. (2020) · IEEE Access · doi:10.1109/access.2020.2978406 · Cited by 37
“ORB-SLAM [57], [58] is one of the most renown SLAM systems, mostly to its versatility and accuracy whether for monocular, stereo or RGB-D camera setups.”
BackgroundSeparated Sonar Localization System for Indoor Robot Navigation
Chen, W., Xu, J., Zhao, X., Liu, Y., & Yang, J. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2994856 · Cited by 35
“One of the famous projects in this field is the ORB-SLAM [24], [25].”
BackgroundUnsupervised Monocular Visual-inertial Odometry Network
Peng, W., Hua, G., Huang, W., Meng, F., & Liu, H. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/325 · Cited by 36
Wen, W., Bai, X., Zhang, G., Chen, S., Yuan, F., & Hsu, L. (2020) · IEEE Access · doi:10.1109/access.2020.3006210 · Cited by 35
“There are many impressive VINS algorithms, such as the [40]–[42].”
BackgroundLSTM and Filter Based Comparison Analysis for Indoor Global Localization in UAVs
Yusefi, A., Durdu, A., Aslan, M. F., & Sungur, C. (2021) · IEEE Access · doi:10.1109/access.2021.3049896 · Cited by 36
“The traditional methods include SVOMSF [95], MSCKF [96], OKVIS [97], ROVIO [98], VINSMONO [99], VINSMONO + LC [100], SVOGTSAM [101], ORBSLAM2 [12], STCM-SLAM [102] and learning based are SelfVIO [103], Kimera [104] and methods proposed by Baldini et al. [94] and Li and Steven [105].”
MethodDepth from Camera Motion and Object Detection
Griffin, B., & Corso, J. J. (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/cvpr46437.2021.00145 · Cited by 36
“Second, movement is already measured on most autonomous hardware platforms and, even if not measured, structure from motion is plausible to recover camera motion [23, 34, 45].”
OFM-SLAM: A Visual Semantic SLAM for Dynamic Indoor Environments
Zhao, X., Zuo, T., & Hu, X. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/5538840 · Cited by 35
“We compare the ATE RMSE (Root Mean Square Error) and RPE RMSE of OFM-SLAM with DSSLAM [17] and ORB-SLAM2 [7] According to Table 1, we can find that OFM-SLAM is competitive in contrast to the two other system, and our method performs better and more accurate in high-dynamic scenes from the six datasets in TUM that cont…”
MethodA survey: which features are required for dynamic visual simultaneous localization and mapping?
Xu, Z., Rong, Z., & Wu, Y. (2021) · Visual Computing for Industry, Biomedicine, and Art · doi:10.1186/s42492-021-00086-w · Cited by 33
SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes
Gómez-Rodríguez, J. J., Lamarca, J., Morlana, J., Tardós, J. D., & Montiel, J. M. M. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561512 · Cited by 37
“ence system among indirect methods by using the combination of arXiv:2010.09409v1 [cs.CV] 19 Oct 2020 FAST-ORB feature-descriptor [3] and BA to optimize the 3D information. In its successive versions [9, 10] it is extended to different type of sensors, ranging from stereo cameras to wide-lens to inertial sensors. As f…”
MethodVIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM
Chen, D., Wang, S., Xie, W., Zhai, S., Wang, N., Bao, H., & Zhang, G. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812354 · Cited by 35
TM3Loc: Tightly-Coupled Monocular Map Matching for High Precision Vehicle Localization
Wen, T., Jiang, K., Wijaya, B., Li, H., Yang, M.-M., & Yang, D. (2022) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2022.3176914 · Cited by 38
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
