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 901–1,000 of 1,007
Marmol, A., Banach, A., & Peynot, T. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2892199 · Cited by 43
“A well-known feature-based implementation including these improvements is ORBSLAM [9].”
BackgroundMethodSynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion
Bozorgtabar, B., Rad, M. S., Mahapatra, D., & Thiran, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00431 · Cited by 48
“Following [51], we measured the Absolute Trajectory Error (ATE) [35] averaged over every 5-frame snippets as the performance metric.”
MethodResultSensor Fusion-Based Approach to Eliminating Moving Objects for SLAM in Dynamic Environments
Dang, X., Zheng, R. Y., & Liang, X. (2021) · Sensors · doi:10.3390/s21010230 · Cited by 45
“DynaSLAM [15], built on ORB-SLAM2, has the capabilities of dynamic object detection and background inpainting, and the resulting accuracy outperforms the standard visual SLAM baselines in highly dynamic scenarios.”
BackgroundInfluentialA Lane-Level Road Marking Map Using a Monocular Camera
Jang, W., Hyun, J., An, J., Cho, M., & Kim, E. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1004293 · Cited by 51
“[15] proposed VPGNet to detect RLs and SRMs simultaneously.”
BackgroundMethodResultInfluentialNaseer, F., Khan, M. N., & Altalbe, A. A. (2023) · Sustainability · doi:10.3390/su15043585 · Cited by 43
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 61
“After the solvers, we optionally run inlier filtering using the obtained pose, followed by a motion-only bundle adjustment, inspired by the localization modules of ORB-SLAM2 [26] or COLMAP [34].”
BackgroundMethodInfluentialEDPLVO: 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
“Instead, we adopt the optimization strategy that is similar to the local bundle adjustment described in [9].”
BackgroundMethodInfluentialZhang, S., Zhang, J., & Tao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_9 · Cited by 58
Samadzadeh, A., & Nickabadi, A. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3268591 · Cited by 47
“One of the most straightforward methods uses random sample consensus (RANSAC) to detect outliers [16], [22].”
RGBD-SLAM Based on Object Detection With Two-Stream YOLOv4-MobileNetv3 in Autonomous Driving
Li, G., Fan, H., Jiang, G., Jiang, D., Liu, Y., Tao, B., & Yun, J. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3284228 · Cited by 44
“There is an increasing demand for the improvement of SLAM capabilities today, such as the ability to understand, build maps in a large range, and update maps in real-time [9], [10], [11], [12].”
BackgroundRecurrent Homography Estimation Using Homography-Guided Image Warping and Focus Transformer
Cao, S.-Y., Zhang, R., Luo, L., Yu, B., Sheng, Z., Li, J., & Shen, H. (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/cvpr52729.2023.00948 · Cited by 80
“It has been widely applied in computer vision tasks ranging from the monocular camera system to the multi-camera system, such as image/video stitching [4, 17, 19], multi-scale gigapixel photography [3,34], multispectral image fusion [41,49], planar object tracking [44,45], SLAM [14,31], and GPS-denied UAV localization…”
MethodA Stable and Accurate Marker-Less Augmented Reality Registration Method
Gao, Q. H., Wan, T. R., Tang, W. J., & Chen, L. F. (2017) · International Conference on Cyberworlds (CW) · doi:10.1109/cw.2017.44 · Cited by 46
“A detailed description of the approach is given in [14].”
BackgroundKernelized Subspace Pooling for Deep Local Descriptors
Wei, X., Zhang, Y., Gong, Y., & Zheng, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00200 · Cited by 40
“It is often used as an essential step in a wide range of vision tasks such as structure from motion [26], stereo matching [43], image stitching [7], image retrieval [27] and image classification [21], to name a few.”
BackgroundQuenzel, J., Nieuwenhuisen, M., Droeschel, D., Beul, M., Houben, S., & Behnke, S. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0791-y · Cited by 43
“Hence, we rees-timate the MAV trajectory from the onboard stored stereo camera stream using a modified multi-camera variant [15] of ORB-SLAM [23].”
MethodTian, G., Liu, L., Ri, J., Liu, Y., & Sun, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.088 · Cited by 45
Real-Time Wide-Baseline Place Recognition Using Depth Completion
Maffra, F., Teixeira, L., Chen, Z., & Chli, M. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2895826 · Cited by 47
“Following the same approach as in [2], the proposed pipeline implements a covisibility graph, where each node is a frame and an edge be-tween two nodes exists if they share enough observations of the same 3D points in the SLAM map.”
BackgroundMethodInfluentialIbrahim, A. S., Sabet, A., & Golparvar‐Fard, M. (2019) · Computing in construction · doi:10.35490/ec3.2019.195 · Cited by 49
“The experiment also shows the scalability of Hector SLAM for mapping large indoor construction spaces and the usability of the resulting occupancy map for autonomous navigation.”
MethodInfluentialLeveraging Structural Regularity of Atlanta World for Monocular SLAM
Li, H., Xing, Y., Zhao, J. Y., Bazin, J., Liu, Z., & Liu, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793716 · Cited by 42
“Besides, we report the result of TL-AE optimized by our MAP-based strategy (cf. Section IV-B), which is denoted by TL-MAP-AE. b) SLAM: ORB-SLAM [2] is a point-based method.”
BackgroundInfluentialImproving 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
H-DrunkWalk: Collaborative and Adaptive Navigation for Heterogeneous MAV Swarm
Chen, X., Ruiz, C., Zeng, S., Gao, L., Purohit, A., Carpin, S., & Zhang, P. (2020) · ACM Transactions on Sensor Networks · doi:10.1145/3382094 · Cited by 45
“Robust navigation methods for MAV swarms that work in GPS denied areas are recently introduced [8, 9].”
BackgroundDELTAS: Depth Estimation by Learning Triangulation and Densification of Sparse Points
Sinha, A., Murez, Z., Bartolozzi, J., Badrinarayanan, V., & Rabinovich, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58589-1_7 · Cited by 51
Mixed reality applications in urology: Requirements and future potential
Reis, G., Yılmaz, M., Rambach, J. R., Pagani, A., Suarez-Ibarrola, R., Miernik, A. J., Lesur, P., & Minaskan, N. (2021) · Annals of Medicine and Surgery · doi:10.1016/j.amsu.2021.102394 · Cited by 51
“Although several monocular SLAM systems have been introduced so far, an important disadvantage is the inability to retrieve the real scale of the reconstructed map and to function in dynamic or featureless environments [6,7].”
BackgroundDPLVO: Direct Point-Line Monocular Visual Odometry
Zhou, L., Wang, S., & Kaess, M. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3097052 · Cited by 42
“Points are the most common features used in VSLAM and VO algorithms [1]–[3], [19], [20].”
MethodResultInfluentialRuhkamp, P., Gao, D., Chen, H., Navab, N., & Busam, B. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00092 · Cited by 52
“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.”
BackgroundYu, L., Yang, E., & Yang, B. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01645-w · Cited by 51
“Then, the scale, orientation invariance and BRIEF descriptor will be calculated by following the approach in [32].”
MethodBimodal Camera Pose Prediction for Endoscopy
Rau, A., Bhattarai, B., Agapito, L., & Stoyanov, D. V. (2023) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2023.3320267 · Cited by 51
“Feature-based Structure-from-Motion (SfM) or Simultaneous Mapping And Localization (SLAM) are standard approaches for reconstructing outdoor or indoor scenes offline [3] or online [4].”
BackgroundSundstedt, V., & Garro, V. (2022) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2022.910019 · Cited by 54
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
Zhao, W., Liu, S., Guo, H., Wang, W., & Liu, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19824-3_31 · Cited by 101
Optimization 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 47
“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.”
MethodConvMatch: Rethinking Network Design for Two-View Correspondence Learning
Zhang, S., & Ma, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25456 · Cited by 43
TextSLAM: Visual SLAM With Semantic Planar Text Features
Li, B., Zou, D., Huang, Y., Niu, X., Pei, L., & Yu, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3324320 · Cited by 55
“We apply bundle adjustment from time to time in a local window of keyframes similar to existing SLAM systems [4].”
BackgroundMethodInfluentialLONER: LiDAR Only Neural Representations for Real-Time SLAM
Isaacson, S., Kung, P.-C., Ramanagopal, M. S., Vasudevan, R., & Skinner, K. A. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3324521 · Cited by 54
“For all experiments, each method and configuration was run 5 times and we report the median result, as in [24].”
BackgroundMethod3D 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 51
“In this work, the cubemap model has been embedded into the ORB-SLAM.”
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.”
MethodReview 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 58
Piao, J.-C., & Kim, S. (2017) · Sensors · doi:10.3390/s17112567 · Cited by 47
“There may also be an additional loop-closure detection module [4].”
BackgroundMethodORB-SLAM Applied to Spacecraft Non-Cooperative Rendezvous
Dor, M., & Tsiotras, P. (2018) · AAS/AIAA Space Flight Mechanics Meeting · doi:10.2514/6.2018-1963 · Cited by 48
Cloud-Based Framework for Scalable and Real-Time Multi-Robot SLAM
Zhang, P., Wang, H., Ding, B., & Shang, S. (2018) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2018.00026 · Cited by 41
“We choose ORB[22] as the extracted feature for real-time performance, whose efficiency has been demonstrated by ORB-SLAM[23].”
MethodInfluentialQiu, L., & Ren, H. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00295 · Cited by 41
Good Feature Selection for Least Squares Pose Optimization in VO/VSLAM
Zhao, Y., & Vela, P. (2018) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros.2018.8593641 · Cited by 40
“By integrating the proposed feature selection to the real-time tracking thread of ORB-SLAM, we demonstrate significant improvement in pose tracking accuracy, while the time cost of pose tracking only increases slightly.”
InfluentialStereo 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.”
BackgroundImproved 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
“[9] proposed the use of quadtree to improve the uniformity of feature distribution, but this was only to optimize the extraction results; this method essentially used the original FAST algorithm.”
BackgroundMethodRouček, T., Pecka, M., Čížek, P., Petříček, T., Bayer, J., Šalanský, V., Azayev, T., Heřt, D., Petrlík, M., Báča, T., et al. (2022) · Field Robotics · doi:10.55417/fr.2022055 · Cited by 56
Hindsight Intermediate Targets for Mapless Navigation With Deep Reinforcement Learning
Jang, Y., Baek, J., & Han, S. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3118407 · Cited by 45
“To design a map of an unknown environment, simultaneous localization and mapping (SLAM) techniques can be used [7], [8].”
MethodPlanar fiducial markers: a comparative study
Jurado-Rodríguez, D., Muñoz‐Salinas, R., Garrido-Jurado, S., & Medina-Carnicer, R. (2023) · Virtual Reality · doi:10.1007/s10055-023-00772-5 · Cited by 47
“In recent years, several techniques have been proposed for developing AR applications by utilizing SLAM algorithms to create a map of the environment based on natural features (Klein and Murray 2007; Mur-Artal et al. 2015; Engel et al. 2017).”
MethodParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point Clouds
Chen, F., Ying, R., Xue, J., Wen, F., & Liu, P. (2023) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10070940 · Cited by 50
“To address this problem, we propose a parallel keyframe-based kNN search algorithm inspired by the keyframe idea of classical Simultaneous Localization And Mapping (SLAM) frameworks [15], [25], as presented in Algorithm 2.”
MethodViewpoint-Tolerant Place Recognition Combining 2D and 3D Information for UAV Navigation
Maffra, F., Chen, Z., & Chli, M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460786 · Cited by 40
“Following the approach of [25], the set NQ of immediate neighbours of Q in the Covisibility Graph (i.”
MethodInfluentialDynamic objects elimination in SLAM based on image fusion
Fan, Y., Han, H. W., Tang, Y., & Zhi, T. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.10.024 · Cited by 45
Reactive 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 43
Collaborative 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 49
“Schmuck et al. [14] proposed a collaborative SLAM system for multiple MAVs based on ORBSLAM2.”
BackgroundRetrieving Scale on Monocular Visual Odometry Using Low-Resolution Range Sensors
Chiodini, S., Giubilato, R., Pertile, M., & Debei, S. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2964066 · Cited by 40
“To compare the accuracy of our algorithm to widely known and available Visual SLAM solutions, ORB-SLAM2 [20] is run on our data sets in stereo mode.”
MethodMerrill, 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].”
MethodAntonini, A., Guerra, W., Murali, V., Sayre-McCord, T., & Karaman, S. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920908331 · Cited by 57
“Note that for both VINS-Fusion and ORB-SLAM2 the parameters used are the default parameters for the EuRoC dataset with appropriate modifications for parameters such as image size and camera calibration.”
MethodInfluentialMGC-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 44
“These methods are similar to the processing flow in the ORB-SLAM2 [3], [4] system, and will not be repeated here.”
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 46
“A visual constraint is widely used as a geometric error term for many feature-based visual SLAMandVIO systems [1], [3], [12], [13], [25].”
MethodLong-Term Temporally Consistent Unpaired Video Translation from Simulated Surgical 3D Data
Rivoir, D., Pfeiffer, M., Docea, R., Kolbinger, F. R., Riediger, C., Weitz, J., & Speidel, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00333 · Cited by 54
“For instance, evaluating a SLAM (Simultaneous Localization and Mapping) algorithm [33, 43] on laparoscopic video data poses several problems since the patient’s ground truth geometry is typically not accessible in the operating room (OR) and recreating artificial testing environments with realistic and diverse patient…”
BackgroundA 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 42
An Integrated Mobile Augmented Reality Digital Twin Monitoring System
He, F., Ong, S. K., & Nee, A. Y. C. (2021) · Computers · doi:10.3390/computers10080099 · Cited by 46
“The development in environmental perception algorithms, such as visual simultaneous localization and mapping (SLAM) and visual-inertia odometry (VIO), made it easy for fusing virtual and reality [22,23].”
BackgroundSBAS: 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 46
Improving Monocular Visual Odometry Using Learned Depth
Sun, L., Yin, W., Xie, E., Li, Z., Sun, C., & Shen, C. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3164834 · Cited by 48
“Compared with stereo [43], [45] and RGB-D SLAM [46], [44], [47], monocular SLAM [48], [9], [39], [40] only requires one camera to achieve localization and mapping and has attracted extensive studies.”
InfluentialMonocular Camera-Based Complex Obstacle Avoidance via Efficient Deep Reinforcement Learning
Ding, J., Gao, L., Liu, W., Piao, H., Pan, J., Du, Z., Yang, X., & Yin, B. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3203974 · Cited by 42
“There are a variety methods of vision-based navigation and obstacle avoidance, such as through optical flow [30], [41], detection of vanishing points [3], visual SLAM [32] and end-to-end mapping based on deep learning [15], [23].”
C2FNet: A Coarse-to-Fine Network for Multi-View 3D Point Cloud Generation
Lei, J., Song, J., Peng, B., Li, W., Pan, Z., & Huang, Q. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3203213 · Cited by 41
“Traditional multi-view 3D model generation methods, such as Shape from Motion (SfM) [5], [6] and Simultaneous Localization and Mapping (SLAM) [7], [8] focused on mining dense correspondence among multi-view images.”
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 54
“[47]), (b) pure geometric constraint based approaches (ORB-SLAM [32], VISO2-M [41]) and with (c) BiLevelOpt [25], a method implementing the epipolar constraint via a differentiable layer.”
MethodEvaluation of the modern visual SLAM methods
Huletski, A., Kartashov, D., & Krinkin, K. V. (2015) · Artificial Intelligence and Natural Language · doi:10.1109/ainl-ismw-fruct.2015.7382963 · Cited by 40
Optical-flow based self-supervised learning of obstacle appearance applied to MAV landing
Ho, H. W., Wagter, C. D., Remes, B. D. W., & de Croon, G. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.10.004 · Cited by 42
“Although the computational efficie ncy and accuracy of visual SLAM have been improved over the years ([10], [17], [18], [19], [20]), this approach still us e more computational resources than are strictly necessary.”
BackgroundUsing extended measurements and scene merging for efficient and robust point cloud registration
Serafin, J., & Grisetti, G. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.008 · Cited by 42
“More recently other full graph-based SLAM systems have been proposed like Kintinuous [39], DynamicFusion [40], RTABSLAM [41] and ORB-SLAM [42].”
Fast semi-dense 3D semantic mapping with monocular visual SLAM
Li, X., Ao, H., Belaroussi, R., & Gruyer, D. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317942 · Cited by 44
“Feature-based methods only exploits limited feature points - typically image corners and blobs or line segments, such as classic MonoSLAM [3] and ORBSLAM [14].”
MethodLearning hierarchical relationships for object-goal navigationPreprint
Qiu, Y., Pal, A., & Christensen, H. I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06749 · Cited by 48
“This is done either in the form of offline maps [6], [7], [8], [9], or online maps [10], [11], [12], [13], [14], [15] generated through Simultaneous Localization and Mapping (SLAM) techniques.”
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 52
“Due to open source graph optimization tools, such as g2o [72], ceres [73], gtsam [74], and SE-sync [75], graph optimization has been widely used in single-robot positioning [76,77] and multi-robot positioning systems [78,79].”
Progressive Neighbor Consistency Mining for Correspondence Pruning
Liu, X., & Yang, J. (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/cvpr52729.2023.00919 · Cited by 62
“Estimating high-quality feature correspondences be-tween two images is of crucial significance to numerous computer vision tasks, such as visual simultaneous localization and mapping (SLAM) [33], structure from motion (SfM) [41, 49], image fusion [31], and image registration [48, 51].”
BackgroundLearning Rotation-Equivariant Features for Visual Correspondence
Lee, J., Kim, B., Kim, S., & Cho, M. (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/cvpr52729.2023.02096 · Cited by 55
“We evaluate the descriptors using their own keypoint detectors [8, 9, 27, 39, 40, 44, 50], or combined with off-the-shelf detectors [24, 26, 42].”
BackgroundMethodEnd-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 47
Detecting and Mitigating Attacks on GPS Devices
Burbank, J. L., Greene, T., & Kaabouch, N. (2024) · Sensors · doi:10.3390/s24175529 · Cited by 56
ESVO2: Direct Visual-Inertial Odometry With Stereo Event Cameras
Niu, J., Zhong, S., Lu, X., Shen, S., Gallego, G., & Zhou, Y. B. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3548523 · Cited by 68
“Indirect Methods: To build on top of existing indirect methods ( e . g ., [43, 44]) using standard cameras, researchers have resorted to developing hand-crafted features from event data, such as event corners [45]–[48], which are typically adapted from the original Harris [49] and FAST [50] methods.”
Robust Multimodal Sequence-Based Loop Closure Detection via Structured Sparsity
Zhang, H., Han, F., & Wang, H. (2016) · Robotics: Science and Systems · doi:10.15607/rss.2016.xii.043 · Cited by 39
“Four types of visual features were employed in our experiments for all datasets, including LDB features [2] applied on 64 × 64 downsampled images, GIST features [24] applied on 320×240 downsampled images, CNN-based deep features [34] applied on 227 × 227 downsampled images, and ORB local features [29] extracted from 3…”
BackgroundMethodEfficient multi-camera visual-inertial SLAM for micro aerial vehicles
Houben, S., Quenzel, J., Krombach, N., & Behnke, S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759261 · Cited by 42
“[1] who introduced ORB-SLAM: a monocular SLAM approach based on ORB features [2].”
BackgroundMethodInfluentialVisual SLAM with a RGB-D Camera on a Quadrotor UAV Using on-Board Processing
Aguilar, W. G., Rodríguez, G. A., Alvarez, L. G., Sandoval, S., Quisaguano, F. J., & Limaico, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59147-6_51 · Cited by 48
UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation
Babu, V. M., Das, K., Majumdar, A., & Kumar, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593864 · Cited by 45
MegaParallax: Casual 360° Panoramas with Motion Parallax
Bertel, T., Campbell, N. D. F., & Richardt, C. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2898799 · Cited by 45
Safe and Robust Mobile Robot Navigation in Uneven Indoor Environments
Wang, C., Wang, J., Li, C., Ho, D., Cheng, J., Yan, T., Meng, L., & Meng, M. Q. ‐. (2019) · Sensors · doi:10.3390/s19132993 · Cited by 41
“Therefore, we utilize all the edges provided by the co− visibility graph [36] rather than using the essentialgraph in ORB-SLAM.”
BackgroundMethodInfluentialRolling-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 46
“A visual-inertial extension of ORB-SLAM [19], [6], a state-of-the-art keyframe-based SLAM approach, is given in [20].”
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
Integrated moment-based LGMD and deep reinforcement learning for UAV obstacle avoidance
He, L., Aouf, N., Whidborne, J. F., & Song, B. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197152 · Cited by 44
“Visual Simultaneous Localization And Mapping (VSLAM) is a promising technique to obtain reliable environment awareness, and it can be applied with only monocular vision, e.g. ORB-SLAM [9], or monocular vision combined with IMU information, e.g. VINS-Mono [10], [11].”
MethodEmpty 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 41
“MOST vision-based localization systems are conceived to work in static environments [1]–[3].”
BackgroundWen, S., Zhao, Y., Liu, X., Sun, F., Lu, H., & Wang, Z. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3041852 · Cited by 41
“Some feature-based VSLAM methods are not fully applicable to 3D semantic map construction due to finite feature points, for instance, MonoSLAM [18] and ORB-SLAM [19].”
MethodCORAL: 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 47
“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].”
MethodVid2CAD: CAD Model Alignment Using Multi-View Constraints From Videos
Maninis, K.-K., Popov, S., Nießner, M., & Ferrari, V. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3146082 · Cited by 43
“Classical works reconstruct a 3D point cloud from multiple views of a scene based on keypoint correspondences [34], [39], [46], [53].”
BackgroundMethodLearned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
Tomasi, J., Wagstaff, B., Waslander, S. L., & Kelly, J. W. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3058909 · Cited by 39
“We expect that, within dynamic lighting regions, images acquired using our network-based controller will yield more reliable ORB-SLAM2 outputs compared to images acquired using the built-in AG+AE controller.”
MethodInfluentialInformation-Driven Path Planning
Bai, S., Shan, T., Chen, F., Liu, L., & Englot, B. (2021) · Current Robotics Reports · doi:10.1007/s43154-021-00045-6 · Cited by 47
A 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 50
“ORB-SLAM ( [16], [17]) uses g(2)o as a back-end for camera pose optimization, and SVO [18] uses it for visual odometry.”
MethodTransformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach
Françani, A. O., & Maximo, M. R. O. A. (2023) · arXiv · doi:10.48550/arxiv.2305.06121 · Cited by 38
“ORB-SLAM3 is still superior considering the 2 https://github.com/UZ-SLAMLab/ORB_SLAM3 3 https://github.com/ChiWeiHsiao/DeepVO-pytorch rotation metrics, such as r err and RPE rot .”
InfluentialYoon, J., & Raychowdhury, A. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.3028298 · Cited by 47
“In pursuit of practical SLAM systems, many prior arts have focused on keyframe-based visual SLAM [17]–[22].”
BackgroundEstimating Egocentric 3D Human Pose in the Wild with External Weak Supervision
Wang, J., Liu, L., Xu, W., Sarkar, K., Luvizon, D. C., & Theobalt, C. (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/cvpr52688.2022.01281 · Cited by 57
“Aside from egocentric poses, we also estimate the transformation matrix between the egocentric camera poses of two adjacent frames [RSLAMseq | tSLAMseq ] = {[R21 | t21], . . . , [R B B−1 | tBB−1]} using ORB-SLAM2 [26].”
RI-LIO: Reflectivity Image Assisted Tightly-Coupled LiDAR-Inertial Odometry
Zhang, Y., Tian, Y., Wang, W., Yang, G., Li, Z., Jing, F., & Tan, M. H. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3243528 · Cited by 40
“, ORB-SLAM [1], VINS-Mono [2]) methods inapplicable.”
MethodInfluentialState of the Art in Dense Monocular Non‐Rigid 3D Reconstruction
Tretschk, E., Kairanda, N., Mallikarjun, B. R., Dabral, R., Kortylewski, A., Egger, B., Habermann, M., Fua, P., Theobalt, C., & Golyanik, V. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14774 · Cited by 59
Review of Visual Simultaneous Localization and Mapping Based on Deep Learning
Zhang, Y., Wu, Y., Tong, K., Chen, H., & Yuan, Y. (2023) · Remote Sensing · doi:10.3390/rs15112740 · Cited by 42
Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything Model
Luo, Z., Yan, G., Cai, X., & Shi, B. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610983 · Cited by 47
“Ad-ditionally, we implement a motion-based method by pose estimation [38], [39] and hand eye calibration [40].”
MethodQuadruped Robots: Bridging Mechanical Design, Control, and Applications
Li, Q., Cicirelli, F., Vinci, A., Guerrieri, A., Qi, W., & Fortino, G. (2025) · Robotics · doi:10.3390/robotics14050057 · Cited by 53
Sujiwo, A., Ando, T., Takeuchi, E., Ninomiya, Y., & Edahiro, M. (2016) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2016.p0479 · Cited by 38
Model-Based Global Localization for Aerial Robots Using Edge Alignment
Qiu, K., Liu, T., & Shen, S. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2660063 · Cited by 38
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.