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 801–900 of 1,004
Learning-Based Visual-Strain Fusion for Eye-in-Hand Continuum Robot Pose Estimation and Control
Wang, X., Dai, J., Tong, H., Wang, K., Fang, G., Xie, X., Liu, Y., Au, K. W. S., & Kwok, K. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3240556 · Cited by 38
“ORB-SLAM2 has three common modules: tracking, local mapping, and loop closing [35].”
Integration of Low-Cost GNSS and Monocular Cameras for Simultaneous Localization and Mapping
Chen, X., Hu, W., Zhang, L., Shi, Z., & Li, M. (2018) · Sensors · doi:10.3390/s18072193 · Cited by 35
“For example, the method in this article can be extended to stereo, panorama, and RGB-D cameras [37] or can be combined with IMU [41] to further improve the accuracy and robustness of the system.”
MethodTransVLAD: Multi-Scale Attention-Based Global Descriptors for Visual Geo-Localization
Xu, Y., Shamsolmoali, P., Granger, É., Nicodème, C., Gardes, L., & Yang, J. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00286 · Cited by 36
“Visual geo-localization is an important task with a broad range of applications in, e.g., automatic driving [14, 18] and robot navigation [20, 26].”
BackgroundYu, L., Yang, E., Yang, B., Fei, Z., & Niu, C. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3279458 · Cited by 34
“Since then, the ORB is adopted into the most famous ORB-SLAM series [12], [13], [14].”
MethodCamera-Sonar Combination for Improved Underwater Localization and Mapping
Cardaillac, A., & Ludvigsen, M. (2023) · IEEE Access · doi:10.1109/access.2023.3329834 · Cited by 35
“To improve the results a second camera, a depth camera or an IMU can be added [5], [6], [7].”
BackgroundVPL-SLAM: A Vertical Line Supported Point Line Monocular SLAM System
Chen, Q., Cao, Y., Hou, J., Li, G., Qiu, S., Chen, B., Xue, X., Lu, H., & Pu, J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3369168 · Cited by 34
“The left factor graph shows the pure ORB point feature BA described in [8], the middle factor graph shows the point-line feature BA mentioned in [23], and the right factor graph is the structure-constrained point-line BA presented in our system.”
BackgroundMethodInfluentialA semantic SLAM-based method for navigation and landing of UAVs in indoor environments
Yang, L., Ye, J. B., Zhang, Y., Wang, L., & Qiu, C. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111693 · Cited by 35
Cong, P., Li, J., Liu, J., Xiao, Y., & Zhang, X. (2024) · Sensors · doi:10.3390/s24072102 · Cited by 36
NGEL-SLAM: Neural Implicit Representation-based Global Consistent Low-Latency SLAM System
Mao, Y., Yu, X., Zhang, Z., Wang, K., Wang, Y., Xiong, R., & Liao, Y. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611269 · Cited by 34
“TraditionalSLAM systems, such as [1], [2], [3], exhibit low latency, high-precision tracking, and employ loop detection to ensure global consistency.”
BackgroundAutomated reality capture for indoor inspection using BIM and a multi-sensor quadruped robot
Chen, Z., Song, C., Wang, B., Tao, X., Zhang, X., Lin, F., & Cheng, J. C. P. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105930 · Cited by 36
H-SLAM: Rao-Blackwellized Particle Filter SLAM Using Hilbert Maps
Vallicrosa, G., & Ridao, P. (2018) · Sensors · doi:10.3390/s18051386 · Cited by 34
CubemapSLAM: A Piecewise-Pinhole Monocular Fisheye SLAM System
Wang, Y., Cai, S., Li, S., Liu, Y., Guo, Y.-Y., Li, T., & Cheng, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20876-9_3 · Cited by 34
Dense piecewise planar RGB-D SLAM for indoor environments
Le, P.-H., & Košecká, J. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206375 · Cited by 34
Network Uncertainty Informed Semantic Feature Selection for Visual SLAM
Ganti, P., & Waslander, S. L. (2019) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2019.00024 · Cited by 36
“Figure 1: ORB SLAM2 [9] feature selection on KITTI [10] sequence 00.”
BackgroundMethodGSLAM: A General SLAM Framework and Benchmark
Zhao, Y., Xu, S., Bu, S., Jiang, H., & Han, P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00120 · Cited by 34
“SLAM. Several frameworks including Ceres [1], G2O [30] and GTSAM [12] are proposed to solve general graph optimization problems. These frameworks are popular used by different SLAM systems. ORB-SLAM [49,51], SVO [21,22] use G2O for bundle adjustment and pose graph optimization. OKVIS [44], VINS [56] use Ceres for grap…”
InfluentialVisual-Based Semantic SLAM with Landmarks for Large-Scale Outdoor Environment
Zhao, Z., Mao, Y., Ding, Y., Ren, P., & Zheng, N. (2019) · China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI) · doi:10.1109/cchi.2019.8901910 · Cited by 34
“Mur-Artal and Tards proposed ORB-SLAM [1], [2], which is one of visual SLAM systems with full sensor support and best performance, with applying ORB features in parallel tracking, mapping, and loop closure detection, and using pose graph optimization and bundle adjustment [9] based optimization.”
MethodA scene-adaptive descriptor for visual SLAM-based locating applications in built environments
Xu, L., Feng, C., Kamat, V. R., & Menassa, C. C. (2020) · Automation in Construction · doi:10.1016/j.autcon.2019.103067 · Cited by 34
Liu, Z., Suo, C., Liu, Y., Shen, Y., Qiao, Z., Wei, H., Zhou, S., Li, H., Liang, X., Wang, H., et al. (2020) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2020.2977290 · Cited by 34
“In Figure 10, we compare the mapping performance of the proposed approach presented in the section “Deep Learning-Enhanced Large-Scale Mapping and Localization” with the state-of-the-art laser-based approach LeGOLOAM [7] and the visual-based approach ORB-SLAM2 [6].”
BackgroundMethodInfluentialUnsupervised semantic clustering and localization for mobile robotics tasks
Balaska, V. E., Bampis, L., Boudourides, M. A., & Gasteratos, A. C. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103567 · Cited by 37
GMMLoc: Structure Consistent Visual Localization With Gaussian Mixture Models
Huang, H., Ye, H.-Y., Sun, Y., & Liu, M. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3005130 · Cited by 33
“Compared to VINS-Mono or ORB-SLAM2, which uses visual-inertial or pure visual information, our method introduces structural constraints and generally improves the localization performance.”
BackgroundMethodInfluentialRGB-D Object SLAM Using Quadrics for Indoor Environments
Liao, Z., Wang, W., Qi, X., & Zhang, X. (2020) · Sensors · doi:10.3390/s20185150 · Cited by 34
“ORB-SLAM2, as a state-of-the-art SLAM method based on feature points, can adequately represent the performance of conventional SLAM.”
BackgroundMethodInfluentialAn Adaptive Visual Dynamic-SLAM Method Based on Fusing the Semantic Information
Jiao, J., Wang, C., Li, N., Deng, Z., & Xu, W. D. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3051691 · Cited by 34
“method [2], [3] and indirect method [6], [7].”
BackgroundMethodUnsupervised Monocular Visual Odometry Based on Confidence Evaluation
Liu, Y., Wang, H., Wang, J., & Wang, X. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3053412 · Cited by 34
PLD-SLAM: A New RGB-D SLAM Method with Point and Line Features for Indoor Dynamic Scene
Zhang, C., Huang, T., Zhang, R., & Yi, X. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10030163 · Cited by 34
“As a result, many wellknown SLAM schemes have adopted the TUM dataset as their benchmark dataset, such as ORB-SLAM2 [10].”
BackgroundMethodInfluentialQuantifying the design-space tradeoffs in autonomous drones
Hadidi, R., Asgari, B., Jijina, S., Amyette, A., Shoghi, N., & Kim, H. (2021) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3445814.3446721 · Cited by 34
“Our hardware platforms for implementing SLAM include a separate RPi4 [63], Nvidia Jetson TX2 [64, 72, 78], and a ZYNQ XC7Z020 FPGA on a PYNQ-Z1 embedded board.”
MethodPLJ-SLAM: Monocular Visual SLAM With Points, Lines, and Junctions of Coplanar Lines
Ren, G., Cao, Z., Liu, X., Tan, M. H., & Yu, J. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3185122 · Cited by 34
Li, R., Ji, P., Xu, Y., & Bhanu, B. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3207105 · Cited by 35
“Some other methods then resort to remedy this problem by generating pseudo ground-truth depth labels with traditional 3D reconstruction methods [32], [33], such as SfM [15] and SLAM [13], [34], or 3D movies [35].”
BackgroundMethodProphet: Realizing a Predictable Real-time Perception Pipeline for Autonomous Vehicles
Liu, L., Dong, Z., Wang, Y., & Shi, W. (2022) · IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss55097.2022.00034 · Cited by 34
“Four tasks are considered for perception: ORB-SLAM2 [31] for monocular camera-based localization, executed on CPU; Faster R-CNN, LaneNet, and Deeplabv3 are executed with the same GPU device.”
MethodSoK: Rethinking Sensor Spoofing Attacks against Robotic Vehicles from a Systematic View
Yuan, X., Han, X., Deng, G., Li, J., Liu, Y., & Zhang, T. (2023) · IEEE European Symposium on Security and Privacy · doi:10.1109/eurosp57164.2023.00067 · Cited by 41
“We implement prototypes on the KITTI [79] dataset with the PointRCNN model [80] and ORBSLAM2 [81] simulator to prove these attacks are practical.”
MethodInfluentialArdeshir, S., & Borji, A. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2832121 · Cited by 34
“the addressed problem using visual odometry [42], [43] at first, however, the results were not accurate enough perhaps”
MethodDarkSLAM: GAN-assisted Visual SLAM for Reliable Operation in Low-light Conditions
Savinykh, A., Kurenkov, M., Kruzhkov, E., Yudin, E., Potapov, A., Karpyshev, P., & Tsetserukou, D. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-spring54318.2022.9860754 · Cited by 33
“D. Contribution In this paper, we propose a novel visual SLAM algorithm, dubbed DarkSLAM, capable of working robustly in lowlight conditions without changing the classic ORB-SLAM2 [18] localization pipeline.”
BackgroundMethodInfluentialDecomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion
Wang, Y., Mao, Y., Liu, Q., & Dai, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3292398 · Cited by 33
“D ENSE and accurate depth is essential for various applications, such as obstacle avoidance [1], virtual reality [2], and autonomous driving [3].”
BackgroundUAV‐based simultaneous localization and mapping in outdoor environments: A systematic scoping review
Wang, K., Kooistra, L., Pan, R., Wang, W., & Valente, J. R. P. (2024) · Journal of Field Robotics · doi:10.1002/rob.22325 · Cited by 38
Herrera-Granda, E. P., Torres, J. C., & Peluffo-Ordóñez, D. H. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e37356 · Cited by 43
Hailu, T. G., Guo, X., Si, H., Li, L., & Zhang, Y. (2024) · Sensors · doi:10.3390/s24216876 · Cited by 36
“By implementing a split architecture based on ORB-SLAM2 [201], tracking remains on the mobile device, while local mapping and loop closing are offloaded to the edge, facilitating long-term operation with limited resources while maintaining accuracy.”
MethodSemantic Metric 3D Reconstruction for Concrete Inspection
Yang, L., Li, B., Li, W., Jiang, B., & Xiao, J. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00204 · Cited by 32
“Direct approach of minimizing Photometric Error [10, 8] performs pose estimation over all pixels, which is more robust in certain circumstance including image blur compared with feature approach [19].”
MethodTzoumanikas, D., Li, W., Grimm, M., Zhang, K., Kovač, M., & Leutenegger, S. (2018) · Journal of Field Robotics · doi:10.1002/rob.21821 · Cited by 35
GEN-SLAM: Generative Modeling for Monocular Simultaneous Localization and Mapping
Chakravarty, P., Narayanan, P., & Roussel, T. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793530 · Cited by 33
“The original ORBSLAM2 code [39] does not come with the ability to save maps.”
MethodInfluentialGarg, S., Babu, M., V, Dharmasiri, T., Hausler, S., Sünderhauf, N., Kumar, S., Drummond, T. W., & Milford, M. J. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794178 · Cited by 35
“The use of single-view depth enables a good compromise between image-space only methods [4], [12], [14] and those based on full 3D reconstruction [15], [16], where it can be challenging for the latter to deal with non-uniform appearance”
Semantic Mapping with Simultaneous Object Detection and Localization
Zeng, Z., Zhou, Y., Jenkins, O. C., & Desingh, K. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594205 · Cited by 33
OpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions
Talbot, B., Garg, S., & Milford, M. J. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593761 · Cited by 34
Automatic Extrinsic Self-Calibration of Mobile Mapping Systems Based on Geometric 3D Features
Hillemann, M., Martin Weinmann, A., Mueller, M., & Jutzi, B. (2019) · Remote Sensing · doi:10.3390/rs11161955 · Cited by 33
“The visual SLAM framework we use is called ORB-SLAM2 [45].”
MethodA Novel Texture-Less Object Oriented Visual SLAM System
Dong, Y., Wang, S., Yue, J., Chen, C., He, S., Wang, H., & He, B. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2952159 · Cited by 33
“We first compare camera localization accuracy between DSO [1], ORB_SLAM2 [3] and proposed system on 7 different synthetic datasets.”
BackgroundMethodInfluentialCamera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment
Shin, U., Park, J., Shim, G., Rameau, F., & Kweon, I. S. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968590 · Cited by 33
“In fact, these conditions are desirable to achieve various tasks such as visual-SLAM [11]–[13], which requires robust and repeatable keypoint detection,”
BackgroundSoares, J. C. V., Gattass, M., & Meggiolaro, M. A. (2019) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar46387.2019.8981617 · Cited by 33
“All the tests were made five times and the median results were used for the evaluation, as proposed by Mur-Artal and Tardós [1], to consider the non-deterministic nature of the system.”
BackgroundMethodInfluentialCo-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry
Li, X., Li, Y., Örnek, E. P., Lin, J., & Tombari, F. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3027230 · Cited by 33
“The average RMSE values, for fairness computed without taking sequence V203 into account, show that our method obtains 25.7% and 38.7% improvements compared to ORB-SLAM2 and FMD-SLAM, respectively.”
MethodInfluentialEnhancing continuous control of mobile robots for end-to-end visual active tracking
Devo, A., Dionigi, A., & Costante, G. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103799 · Cited by 34
Comparison of ROS-Based Monocular Visual SLAM Methods: DSO, LDSO, ORB-SLAM2 and DynaSLAM
Mingachev, E., Lavrenov, R., Tsoy Tatyana, G., Matsuno, F., Svinin, M. M., Suthakorn, J., & Magid, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60337-3_22 · Cited by 33
Leveraging Deep Learning for Visual Odometry Using Optical Flow
Pandey, T., Peña, D., Byrne, J., & Moloney, D. (2021) · Sensors · doi:10.3390/s21041313 · Cited by 33
Enhancing satellite semantic maps with ground-level imagery
Balaska, V. E., Bampis, L., Kansizoglou, I., & Gasteratos, A. C. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103760 · Cited by 34
Wang, C., Xu, A., Sui, X., Hao, Y., Shi, Z., & Chen, Z. (2021) · Remote Sensing · doi:10.3390/rs14010027 · Cited by 35
Visual SLAM Based on Semantic Segmentation and Geometric Constraints for Dynamic Indoor Environments
Yang, S., Zhao, C., Wu, Z., Wang, Y., Wang, G., & Li, D. (2022) · IEEE Access · doi:10.1109/access.2022.3185766 · Cited by 33
“Qtree_ORB algo-rithm proposed by Mur-Artal R [7], [8] et al , improves the uniformity of ORB feature points to a certain extent by introducing the method of quad-tree homogenization.”
MethodSeqPolar: Sequence Matching of Polarized LiDAR Map With HMM for Intelligent Vehicle Localization
Tao, Q., Hu, Z., Zhou, Z. S., Xiao, H., & Zhang, J. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3170627 · Cited by 33
Localization and tracking of stationary users for augmented reality
Baker, L., Ventura, J., Langlotz, T., Gul, S., Mills, S. J., & Zollmann, S. (2023) · The Visual Computer · doi:10.1007/s00371-023-02777-2 · Cited by 35
“To evaluate the tracking component of our system, we compared the rate of successful tracking between state-of-the-art monocular ORB-SLAM2 [12,47] and our approach across multiple sequences in two different real-life environments (a sports stadium, and an outdoor basketball court).”
MethodResultInfluentialRelative Navigation Strategy About Unknown and Uncooperative Targets
Maestrini, M., Luca, M. A. D., & Lizia, P. D. (2023) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g007337 · Cited by 33
Bangunharcana, A., Magd, A., & Kim, K.-S. (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/cvpr52729.2023.00077 · Cited by 35
“This class of models is straightforward, but often less accurate than their traditional counter-parts [17,18,68] due to the absence of geometry constraints.”
BackgroundFactor graph-based high-precision visual positioning for agricultural robots with fiducial markers
Zhang, W., Gong, L., Huang, S., Wu, S., & Liu, C. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107295 · Cited by 33
Structure and Motion from Casual Videos
Zhang, Z., Cole, F. H., Li, Z., Rubinstein, M., Snavely, N., & Freeman, W. T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19827-4_2 · Cited by 32
“This problem is variously called structure from motion (SfM) or visual SLAM, depending on the precise inputs and constraints [8, 26, 21] (e.g., SLAM methods often operate in real time).”
BackgroundULL-SLAM: underwater low-light enhancement for the front-end of visual SLAM
Xin, Z., Wang, Z., Yu, Z., & Zheng, B. (2023) · Frontiers in Marine Science · doi:10.3389/fmars.2023.1133881 · Cited by 32
PLPF‐VSLAM: An indoor visual SLAM with adaptive fusion of point‐line‐plane features
Yan, J., Zheng, Y., Yang, J., Mihaylova, L. S., Yuan, W., & Gu, F. (2023) · Journal of Field Robotics · doi:10.1002/rob.22242 · Cited by 33
“In addition, considering that real ‐ time performance is also an important indicator of a VSLAM, we compared our system to ORB ‐ SLAM2 and Planar ‐ SLAM on five sequences from the total time and mean tracking time (Table 3 and Figure 11).”
BackgroundMethodInfluentialA Review of Dynamic Object Filtering in SLAM Based on 3D LiDAR
Peng, H., Zhao, Z., & Wang, L. (2024) · Sensors · doi:10.3390/s24020645 · Cited by 33
Shoukat, M. U., Yan, L., Deng, D., Imtiaz, M., Safdar, M., & Nawaz, S. A. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102370 · Cited by 38
Dinh, N. V., Phan, D., Park, C. H., & Kim, G.-W. (2024) · Computers & electrical engineering · doi:10.1016/j.compeleceng.2024.109607 · Cited by 31
NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding
Zhai, H., Huang, G., Hu, Q., Li, G., Bao, H., & Zhang, G. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456201 · Cited by 39
“Besides, some methods [10,22,26,48,73] decouple the front and back ends, employing traditional or learning-based VO/VIO [40,52,62] for camera pose tracking and utilizing implicit representation in the back end for dense reconstruction.”
MethodTRAM: Global Trajectory and Motion of 3D Humans from in-the-Wild Videos
Wang, Y., Wang, Z., Liu, L., & Daniilidis, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73247-8_27 · Cited by 71
Damjanović, D., Biočić, P., Prakljačić, S., Činčurak, D., & Balen, J. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01673-0 · Cited by 36
Miiller, M. G., Steidle, F., Schuster, M. J., Lutz, P., Maier, M., Stoneman, S., Tomić, T., & Stürzl, W. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594117 · Cited by 32
“Similar to [18], [19], [20], [21] we are using keyframes for estimating not only the pose of the current camera frame relative to the previous one, but also relative to a set of selected camera frames in the past to increase the accuracy of the overall pose estimation.”
MethodRobust Semantic Mapping in Challenging Environments
Cheng, J., Sun, Y., & Meng, M. Q. ‐. (2019) · Robotica · doi:10.1017/s0263574719000584 · Cited by 32
“Note that we only conduct the semantic segmentation for keyframes of the ORB-SLAM system.”
MethodInfluentialA Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation
Li, F., Chen, W., Xu, W., Huang, L., Li, D., Cai, S., Yang, M., Xiong, X., Liu, Y., & Li, W. (2020) · IEEE Access · doi:10.1109/access.2020.2970238 · Cited by 32
“The feature detection same as the ORB-SLAM2 [3] that we can obtain a homogeneous feature distribution.”
MethodInfluentialTowards End-to-end Learning of Visual Inertial Odometry with an EKF
Li, C., & Waslander, S. L. (2020) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv50864.2020.00033 · Cited by 33
“We compare the four methods: • IMU-Only : sub-component of the network using just IMU data, integrating IMU measurements using the EKF prediction step described in Section III-B; • ORB+MSF : loosely-coupled fusion of stereo ORB-SLAM [21] keyframe poses with IMU using the MSF [11] framework.”
MethodAugmenting Visual Place Recognition With Structural Cues
Oertel, A., Cieslewski, T., & Scaramuzza, D. (2020) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-197709 · Cited by 32
An Efficient Planar Bundle Adjustment Algorithm
Zhou, L., Koppel, D., Ju, H., Steinbrücker, F., & Kaess, M. (2020) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar50242.2020.00035 · Cited by 32
“Generally, visual SLAM algorithms [15, 19,20,23,30] yield sparse or semi-dense maps.”
BackgroundSemantic RGB-D SLAM for Rescue Robot Navigation
Deng, W., Huang, K., Chen, X., Zhou, Z., Shi, C., Guo, R., & Zhang, H. (2020) · IEEE Access · doi:10.1109/access.2020.3031867 · Cited by 32
“Our framework combines the well-known ORB-SLAM2 [1] method and a convolutional neural network (CNN) to generate both geometric and semantic maps of dense point-cloud, using an RGB-D camera.”
MethodDM-SLAM: Monocular SLAM in Dynamic Environments
Lu, X., Wang, H., Tang, S., Huang, H., & Li, C. (2020) · Applied Sciences · doi:10.3390/app10124252 · Cited by 32
Semantic Mapping for Mobile Robots in Indoor Scenes: A Survey
Han, X., Li, S., Wang, X., & Zhou, W. (2021) · Information · doi:10.3390/info12020092 · Cited by 32
“For example, authors in [21] employ ORB-SLAM2 [40] to build a point cloud model of the environment, and several kinds of objects are detected and shown in different colors.”
BackgroundMethodInfluentialCloudSLAM: Edge Offloading of Stateful Vehicular Applications
Wright, K.-L., Sivakumar, A., Steenkiste, P., Bo, Y., & Bai, F. (2020) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec50012.2020.00018 · Cited by 32
“First, the execution of ORB-SLAM is not repeatable due to its multi-threaded design [13], so two executions of ORB-SLAM using the same video input will generate a slightly different trajectory each time due to the non-deterministic scheduling of the modules.”
MethodUnderwater Monocular Image Depth Estimation using Single-beam Echosounder
Roznere, M., & Li, A. Q. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340919 · Cited by 32
“To increase the quality of the estimates calculated by the state estimation algorithms, it is common to fuse data from other sensors, for example multi-calibrated cameras [14], [15] or IMU [16]–[22].”
MethodDynamic RGB-D SLAM Based on Static Probability and Observation Number
Liu, Y., Wu, Y., & Pan, W. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3089228 · Cited by 33
Wang, Y., Yang, J., Peng, X., Wu, P., Gao, L., Huang, K., Chen, J., & Kneip, L. (2022) · Sensors · doi:10.3390/s22155687 · Cited by 36
“We compare our method against two alternatives, which are the state-of-the-art ORB-SLAM algorithm [33] and the classical 1-point Ransac algorithm—denoted 1pt—for planar motion [34].”
BackgroundMethodInfluentialLinear RGB-D SLAM for Structured Environments
Joo, K., Kim, P., Hebert, M., Kweon, I. S., & Kim, H. J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3106820 · Cited by 32
“Representatives of these are direct LSD-SLAM [20], DSO [21], and feature-based ORB-SLAM2 [6]; however, their performance can be severely degraded in challenging low-texture environments.”
InfluentialWang, G., Zhong, J., Zhao, S., Wu, W., Liu, Z., & Wang, H. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3215587 · Cited by 32
“method, ORB-SLAM2 [25] with back-end optimization and closed-loop optimization.”
Terrain Aided Planetary UAV Localization Based on Geo-referencing
Wan, X., Shao, Y., Zhang, S., & Li, S. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3198745 · Cited by 32
“Then, the pixel deviation obtained by phase matching can be converted into the coordinate deviation relative to the DEM image sequence by referring to formulas 16–20 to obtain the calculated value of coordinates.”
BackgroundMethodCarlaScenes: A synthetic dataset for odometry in autonomous driving
Kloukiniotis, A., Papandreou, A., Anagnostopoulos, C., Lalos, A. S., Kapsalas, P., Nguyen, D.-V., & Μουστάκας, Κ. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00498 · Cited by 36
“The research field of visual odometry (VO) and simultaneous localization and mapping (SLAM) has met immense evolutions [14, 21, 30, 36], especially in the context of autonomous driving (AD) [23, 24, 28, 32, 33].”
BackgroundOptical Flow-Based Stereo Visual Odometry With Dynamic Object Detection
Liu, Y., & Zhou, Z. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3205015 · Cited by 32
“We compare with ORB-SLAM2 [7] and DynaSLAM [27].”
MethodResultMulti-Objective Location and Mapping Based on Deep Learning and Visual Slam
Sun, Y., Hu, J. P., Yun, J., Liu, Y., Bai, D., Liu, X., Zhao, G., Jiang, G., Kong, J., & Chen, B. (2022) · Sensors · doi:10.3390/s22197576 · Cited by 32
“Sequence ORB-SLAM2 [41] Elastic-Fusion [43] DVO-SLAM [38] Fusion++ [40] Ours”
MethodInfluentialNinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
Ng, T., Kim, H. J., Lee, V. T., DeTone, D., Yang, T.-Y., Shen, T., Ilg, E., Balntas, V., Mikolajczyk, K., & Sweeney, 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/cvpr52688.2022.01246 · Cited by 33
“…[7,13,56,73,75] are fundamental to a wide range of computer vision applications such as SLAM [15, 40, 42, 45], SfM [1, 65, 72], wide-baseline stereo [30,43], calibration [49], tracking [24,44,51], image retrieval [3, 4, 32, 46, 47, 67, 78, 79], and camera pose estimation [5,17,54,61,62,76,77].”
An Adaptive ORB-SLAM3 System for Outdoor Dynamic Environments
Zang, Q., Zhang, K., Wang, L., & Wu, L. (2023) · Sensors · doi:10.3390/s23031359 · Cited by 33
“The DS-SLAM proposed by Chao Yu et al. [12] combined the semantic segmentation network with ORB-SLAM2 effectively reducing the trajectory error.”
MethodInfluentialR3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
Schmied, A., Fischer, T., Danelljan, M., Pollefeys, M., & Yu, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00298 · Cited by 32
“Traditional SLAM systems are often split into different stages, where first images are processed into keypoint matches, which subsequently are used to estimate the 3D scene geometry and camera trajectory [9, 10, 6, 34, 35, 5, 39].”
MethodSurvey of connected automated vehicle perception mode: from autonomy to interaction
Shangguan, W., Du, Y., Guo, C. L., Liu, D., & Shu, W. W. (2018) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5239 · Cited by 32
“Implementation of high-precision sensors [1–4] and deep learning algorithms [5–9] has promoted precise environment status perception to a higher level.”
BackgroundMulti-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low LightPreprint
Jung, E., Yang, N., & Cremers, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.06632 · Cited by 32
“VO[1, 2] delivers more reliable and accurate results than monocular systems[3, 4, 1] by eliminating the scale ambiguity[5, 6, 7].”
InfluentialDing, Y., Yang, J. J., Larsson, V., Olsson, C., & Åström, K. (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/cvpr52729.2023.00472 · Cited by 31
“Registering a new image to a given 3D model is a critical step in many computer vision pipelines, e.g. visual positioning and localization [22], augmented reality [23] or autonomous mapping and navigation [18].”
BackgroundObVi-SLAM: Long-Term Object-Visual SLAM
Adkins, A., Chen, T., & Biswas, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3363534 · Cited by 31
“Visualfeatureassociationsandinitialestimatesareobtained using the tracking component of ORB-SLAM2 [28], which generates feature tracks based on ORB descriptors.”
MethodIGE-LIO: Intensity Gradient Enhanced Tightly Coupled LiDAR-Inertial Odometry
Chen, Z., Zhu, H., Yu, B., Jiang, C., Hua, C., Fu, X., & Kuang, X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3427795 · Cited by 30
“Visual odometry (VO) methods use RGB textures [3], [4], [5] and offer the advantages of low cost and lightweight.”
MethodReal-time 3D mapping using a 2D laser scanner and IMU-aided visual SLAM
Chen, M., Yang, S., Yi, X., & Wu, D. (2017) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar.2017.8311877 · Cited by 31
“As for visual SLAM, we use the popular keyframe-based ORB-SLAM2 framework [17] with a RGB-D camera.”
MethodOnline IMU Self-Calibration for Visual-Inertial Systems
Xiao, Y., Ruan, X.-G., Chai, J., Zhang, X.-P., & Zhu, X.-Q. (2019) · Italian National Conference on Sensors · doi:10.3390/s19071624 · Cited by 29
Qian, K., Zhao, W., Li, K., Ma, X., & Yu, H. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2947275 · Cited by 31
“However, when applying the publicly-available implementation of PL-SLAM [5] to substation environments, the system was prone to larger errors and more frequent tracking failures, compared with the classic ORB-SLAM2 system [7].”
BackgroundMethodInfluentialARSpectator: Exploring Augmented Reality for Sport Events
Zollmann, S., Langlotz, T., Loos, M., Lo, W. H., & Baker, L. (2019) · SIGGRAPH Asia Technical Briefs · doi:10.1145/3355088.3365162 · Cited by 31
“In recent years, SLAM approaches have shown promising re-sults also in larger scale environments [Mur-Artal and Tardos 2017].”
BackgroundCrowd-sourced Semantic Edge Mapping for Autonomous Vehicles
Herb, M., Weiherer, T., Navab, N., & Tombari, F. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968020 · Cited by 31
“We employ feature-based visual odometry similar to the ORB-SLAM [1] frontend by tracking a local map of sparse landmarks created from matched ORB-keypoints.”
BackgroundMethodInformation-Driven Direct RGB-D Odometry
Fontan, A., Civera, J., & Triebel, R. (2020) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr42600.2020.00498 · Cited by 30
“The results for ORB-SLAM2-based odometry were taken from [29].”
BackgroundMethodInfluentialChen, H., ZHANG, G., & Ye, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3010580 · Cited by 30
“Representative systems such as ORB-SLAM [2] and DSO [3] have attracted a great deal of attention.”
Background
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
