VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
One camera and one low-cost inertial measurement unit (IMU) form a monocular visual-inertial system (VINS), which is the minimum sensor suite (in size, weight, and power) for the metric six degrees-of-freedom (DOF) state estimation. In this paper, we present VINS-Mono: a robust and versatile monocular visual-inertial state estimator. Our approach starts with a robust procedure for estimator initialization. A tightly coupled, nonlinear optimization-based method is used to obtain highly accurate visual-inertial odometry by fusing preintegrated IMU measurements and feature observations. A loop detection module, in combination with our tightly coupled formulation, enables relocalization with minimum computation. We additionally perform 4-DOF pose graph optimization to enforce the global consistency. Furthermore, the proposed system can reuse a map by saving and loading it in an efficient way. The current and previous maps can be merged together by the global pose graph optimization. We validate the performance of our system on public datasets and real-world experiments and compare against other state-of-the-art algorithms. We also perform an onboard closed-loop autonomous flight on the microaerial-vehicle platform and port the algorithm to an iOS-based demonstration. We highlight that the proposed work is a reliable, complete, and versatile system that is applicable for different applications that require high accuracy in localization. We open source our implementations for both PCs (https://github.com/HKUST-Aerial-Robotics/VINS-Mono) and iOS mobile devices (https://github.com/HKUST-Aerial-Robotics/VINS-Mobile).
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In terms of vision-IMU-GPS fusion, VINS-Fusion has become a mainstream solution for large-scale, high-precision localization and is widely used in UAVs and mobile robots.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [151]
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
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 3×
“Relative pose error [42] in MH_05_difficult.”
MethodInfluential(1981) · Cited by 11,963
Shi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 1×
“features are detected [32] to maintain a minimum number (100– 300) of features in each image.”
BackgroundRobust estimation of a location parameter
Huber, P. J. (1964) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177703732 · Cited by 7,228
ORB-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×
“ORB-SLAM [4] is able to close loops and reuse the map, which takes advantage of Bag-of-World [6].”
BackgroundMethodInfluentialParallel 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
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 1×
“Finally, a global full bundle adjustment [36] is applied to minimize the total reprojection error of all feature observations.”
MethodA 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 3×
“TABLE I RMSE [43] IN EUROC DATASETS IN METERS”
BackgroundMethodInfluentialLSD-SLAM: Large-scale direct monocular SLAM
Engel, J., Schöps, T., & Cremers, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_54 · Cited by 3,851 · cited 3×
“Noticeable approaches include PTAM [1], SVO [2], LSD-SLAM [3], DSO [5], and ORB-SLAM [4].”
BackgroundMethod
Cited by
Items 801–900 of 1,001
Using Image Sequences for Long-Term Visual Localization
Stenborg, E., Sattler, T., & Hammarstrand, L. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00104 · Cited by 28
“Other solvers also make use of inertial constraints, e.g., the extension to ORB-SLAM [61], Kasyanov et al. [36], Okvis [48], VINS-Mono [63] and ROVIO [5].”
A survey on visual servoing for wheeled mobile robots
Li, C., Li, B., Wang, R., & Zhang, X. (2021) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-021-00177-0 · Cited by 30
“For example, measurements from the IMU can be aligned with image feedback to recover metric information like Qin et al. (2018).”
BackgroundSquare Root Marginalization for Sliding-Window Bundle Adjustment
Demmel, N., Schubert, D., Sommer, C., Cremers, D., & Usenko, V. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01301 · Cited by 36
“Usually, they are implemented as a fixed-lag smoother, where old or redundant state variables are removed from the optimization window in order to keep the system real-time capable [25, 13, 7, 22, 28].”
Visual Localization for Autonomous Driving using Pre-built Point Cloud Maps
Yabuuchi, K., Wong, D., Ishita, T., Kitsukawa, Y., & Kato, S. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575569 · Cited by 26
Point-line feature fusion based field real-time RGB-D SLAM
Li, Q., Wang, X., Wu, T., & Yang, H. (2022) · Computers & Graphics · doi:10.1016/j.cag.2022.06.013 · Cited by 24
Research on Underground Coal Mine Map Construction Method Based on LeGO-LOAM Improved Algorithm
Xue, G., Li, R., Liu, S., & Wei, J. (2022) · Energies · doi:10.3390/en15176256 · Cited by 25
“…cloud map and progressively refines the pose transformation, uses L-M optimization to obtain the final transformed poses and adds spatial constraints between the new nodes and historical ones in the point cloud map, before performing Euclidean distance-based loopback detection at a lower…”
MethodWang, Y., & Ma, H. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3226074 · Cited by 26
“Shan et al. [13] presented LVI-SAM, an LVIO framework with a loop detection module and global mapping built atop an LIS [5] and a VIS [1].”
BackgroundMethodQuadrotor UAV: Collision Resilience Behaviors
Fan, D., Guo, K., Lyu, S., Yu, X. Y., Xie, L., & Guo, L. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3211479 · Cited by 24
“Meanwhile, the integration of perception and planning [6], [7], [8] provides another option to achieve collision free.”
BackgroundRobust Predictor-Based Control for Multirotor UAV With Various Time Delays
Lee, S.-M., Shin, M., & Son, H. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3224130 · Cited by 24
“With an increase in demands in UAV autonomous navigation, the UAVs have been implemented with vision-based approaches [12], [13], [14] and simultaneous localization and mapping [15], [16], [17] to generate a reference trajectory for UAV tracking control.”
MethodMulti-Sensor Fusion-Based Indoor Single-Track Semantic Map Construction and Localization
Chai, W., Li, C., & Li, Q. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3226821 · Cited by 24
“…accelerometer measurement ˜ a k and gyro measurement ˜ g k to calculate the relative state increments (α ) in continuous IMU frames I f − 1 and I f [35], which are given by the following equation : where In (1), α I f , and γ denote the relative state increments in position, velocity, and attitude…”
BackgroundMethodA Novel Deep Learning Approach to 5G CSI/Geomagnetism/VIO Fused Indoor Localization
Yang, C. J., Cheng, Z., Jia, X., Zhang, L., Li, L., & Zhao, D. (2023) · Sensors · doi:10.3390/s23031311 · Cited by 25
“Campos, C.; Elvira, R.; Rodríguez, J.J.G.; Montiel, J.M.; Tardós, J.D. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM.”
MethodInfluentialBioSLAM: A Bioinspired Lifelong Memory System for General Place Recognition
Yin, P., Abuduweili, A., Zhao, S., Xu, L., Liu, C., & Scherer, S. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3306615 · Cited by 38
“Although the topic of long-term SLAM [5], [6], [7], [8], [9] has been well studied in the past decade, in this work, we narrow down the scope to the lifelong PR in long-term navigation and proposed BioSLAM, that can continuously relocalize to new environments without sacrificing recognizing ability…”
BackgroundSong, J., Li, W., & Zhu, X. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3334979 · Cited by 27
“Therearemanyimpressivevisual-inertialalgorithmssuchas filtering-basedOpen-VINS[6],andoptimization-basedVINS series[7],[8],[9],ORB-SLAMseries[10]andotherexcel-lent open source frameworks.”
BackgroundSun, W., Li, Y., Ding, W., & Zhao, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3335514 · Cited by 24
“Qin et al. [13] proposed an optimization-based approach that employs a nonlinear fusion of the inertial measurement unit (IMU) and camera data.”
MethodMultimodal Dataset for Localization, Mapping and Crop Monitoring in Citrus Tree Farms
Teng, H., Wang, Y., Song, X., & Karydis, K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47969-4_44 · Cited by 38
LIWO: LiDAR-Inertial-Wheel Odometry
Yuan, Z., Lang, F., Xu, T., & Yang, X. Y. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342258 · Cited by 34
“In this work, we employ the discrete-time quaternion-based derivation of IMU-odometer pre-integration approach [8], and incorporate IMU bias using the method in [10].”
MethodHigh Precision and Robust Vehicle Localization Algorithm With Visual-LiDAR-IMU Fusion
Cheng, J. T., Zhang, L., Chen, Q., Fu, Z., & Du, L. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3379435 · Cited by 27
“At present, more attention has been paid to the nonlinear optimization-based method, the well-known methods include OKVIS [25], VIORB [26], VINS-MONO [27], VINS-Fusion [28], BASALT [29], ICE-BA [30], and ORB-SALM3 [31].”
MethodA Unifying View of Geometry, Semantics, and Data Association in SLAM
Atanasov, N., Bowman, S. L., Daniilidis, K., & Pappas, G. J. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/722 · Cited by 31
“They can track visual-inertial systems over long trajectories in real time [Bloesch et al. , 2015; Forster et al. , 2016; Qin et al. , 2017], while recovering the sparse [Engel et al. , 2014; Mur-Artal and Tard´os, 2017] or dense [Whelan et al. , 2016; Hornung et al. , 2013 ] environment structure.”
BackgroundRahman, S., Li, A. Q., & Rekleitis, I. M. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967697 · Cited by 32
“Vision is often combined with IMU for more accurate estimation of pose, for example, MSCKF [25], OKVIS [26], VisualInertial ORB-SLAM [27], and VINS-Mono [28].”
BackgroundGaussian Process Preintegration for Inertial-Aided State Estimation
Gentil, C. L., Vidal‐Calleja, T., & Huang, S. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2970940 · Cited by 34
Bai, X., Wen, W., & Hsu, L. (2020) · Remote Sensing · doi:10.3390/rs12101686 · Cited by 24
LiDAR-Visual-Inertial Odometry Based on Optimized Visual Point-Line Features
He, X., Gao, W., Sheng, C., Zhang, Z., Pan, S., Duan, L., Zhang, H., & Lu, X. (2022) · Remote Sensing · doi:10.3390/rs14030622 · Cited by 24
“Visual Point Feature Factor In this study, the visual feature factors are built with reference to VINS-Mono [5].”
MethodInfluentialShao, X., Zhang, L., Zhang, T., Shen, Y., Li, H., & Zhou, Y. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413867 · Cited by 23
“…aspects, sensor modalities used (’S’ V (Visual) Semantic × Civera et al. [3] V Semantic × Mur-Artal et al. [15] V + I (IMU) Geometric × Qin et al. [17] V + I Geometric × Tateno et al. [21] V Semantic × Yang et al. [25] V Semantic × Yu et al. [26] V Semantic √ Zhao et al. [30] V + I + T (Tag)…”
BackgroundMethodWang, Z., Yang, K., Shi, H., Li, P., Gao, F., Bai, J. Y., & Wang, K. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3324495 · Cited by 32
“Qin et al. [20] proposed VINS, a robust and versatile monocular vision inertial state estimator.”
BackgroundMethodInfluentialSelf-citationWang, X., Li, X., Yu, H., Chang, H., Zhou, Y., & Li, S. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3403661 · Cited by 37
“We compare the proposed VILO with LOAM [32], LIO-SAM [38], VINS-Mono [39], and LVI-SAM [10] on public datasets and our self-collected datasets.”
Stereo visual-inertial localization algorithm for orchard robots based on point-line features
Xu, X., Liang, J., Li, J., Wu, G., Duan, J., Jin, M., & Fu, H. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109202 · Cited by 23
Less is More: Physical-Enhanced Radar-Inertial Odometry
Huang, Q., Liang, Y., Qiao, Z., Shen, S., & Yin, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611471 · Cited by 42
“To circumvent the need for re-propagation, we employ IMU pre-integration, a technique that allows us to streamline the process, as introduced in [11].”
Self-citationCMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration
Cattaneo, D., & Valada, A. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3546784 · Cited by 46
“We compare the performance of CMRNext with tradition meth-ods for stereo SLAM [3], [66], [67], stereo localization in LiDAR maps [68], [69], [70], [71], monocular localization in LiDAR maps [9], [14], [71], [72], as well as learning-based methods [21], [27], [65], [73].”
Online Temporal Calibration Based on Modified Projection Model for Visual-Inertial Odometry
Liu, Y., & Meng, Z. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2951863 · Cited by 26
“Optimization-based methods [5]–[9] obtain the optimal state estimation by jointly minimizing the residual originating from camera and IMU measurements.”
MethodRobots’ State Estimation and Observability Analysis Based on Statistical Motion Models
Xu, W. D., He, D., Cai, Y., & Zhang, F. (2022) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2021.3133080 · Cited by 25
“The multisensor fusion approach has also motivated extrinsic calibration: offline methods include maximum likelihood (ML) [17], pose graph optimization [14], and EKF smoother [6]; online methods typically view the extrinsic parameter as a state and use the same EKF/UKF formulation as in state estimation to additionall…”
BackgroundMethodInfluential3D plant root system reconstruction based on fusion of deep structure-from-motion and IMU
Lu, Y., Wang, Y., Chen, Z., Khan, A., Salvaggio, C., & Lu, G. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10069-3 · Cited by 27
Tightly-Coupled Multi-Sensor Fusion for Localization with LiDAR Feature Maps
Pan, L., Ji, K., & Zhao, J. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561547 · Cited by 24
“The residual for motion constraint of wheel encoders is defined as Once the LiDAR poses in a sliding window are obtained, we calculate the gyroscope bias b g , gravity vector g , and velocity v of each frame in the sliding window by following the initialization strategy of [26].”
MethodPLS-VINS: Visual Inertial State Estimator With Point-Line Features Fusion and Structural Constraints
Yang, G., Wang, Q., Liu, P., & Yan, C. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3123973 · Cited by 24
Wang, Y., Lou, Y., Song, W., & Tu, Z. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3142041 · Cited by 23
“…time case, the preintegration terms can be computed recursively using: where 𝑹(𝜸̂ 𝐵 𝐵 𝑘 ) is the rotation matrix representation of 𝜸̂ 𝐵 𝐵 𝑘 , 𝒂̂ 𝑖 and 𝝎̂ 𝑖 are the raw gyroscope and accelerometer measurements denoted in [18], 𝒔 𝑂𝐵 𝑖+1 𝑂𝐵 𝑖 is the odometer increment measurement.”
Perception-Aware Planning for Active SLAM in Dynamic Environments
Zhao, Y., Xiong, Z., Zhou, S., Wang, J., Zhang, L., & Campoy, P. (2022) · Remote Sensing · doi:10.3390/rs14112584 · Cited by 28
Wang, Y., Lou, Y., Song, W., Tu, Z., Wang, Y., & Zhang, S. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3181264 · Cited by 26
A Progressive Bayesian Filtering Framework for Nonlinear Systems With Heavy-Tailed Noises
Zhang, J., Yang, X., & Zhang, W. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3172165 · Cited by 23
“Nonlinear Bayesian filtering has been widely used in a variety of fields, such as target tracking [1], [2], robotics [3], and signal processing [4].”
MethodAccurate and Robust Visual Localization System in Large-Scale Appearance-Changing Environments
Yu, Y., Peng, Y., Xue, B., Jiao, J., Fan, R., & Liu, M. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3177237 · Cited by 26
“studied in [2] by simultaneous estimation of extrinsics and ego-motion in a tightly coupled optimization module.”
BackgroundVisual/Inertial/GNSS Integrated Navigation System under GNSS Spoofing Attack
Gu, N., Xing, F., & You, Z. (2022) · Remote Sensing · doi:10.3390/rs14235975 · Cited by 23
Meng, Q., Yang, S. S., Li, S.-Y., & Zhuang, Y. (2022) · Defence Technology · doi:10.1016/j.dt.2022.12.013 · Cited by 23
FEJ-VIRO: A Consistent First-Estimate Jacobian Visual-Inertial-Ranging Odometry
Jia, S., Jiao, Y., Zhang, Z., Xiong, R., & Wang, Y. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981413 · Cited by 29
Camera Attributes Control for Visual Odometry With Motion Blur Awareness
Han, B., Lin, Y., Dong, Y., Wang, H., Zhang, T., & Liang, C. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3234316 · Cited by 23
“TheimagesintheFig.11scenewereprocessedbythestate-of-the-artVOmethod[29].”
QISO-SLAM: Object-Oriented SLAM Using Dual Quadrics as Landmarks Based on Instance Segmentation
Wang, Y., Xu, B., Fan, W., & Xiang, C. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3251222 · Cited by 23
“Such visual SLAM frameworks, including ORB-SLAM [1], VINS-Mono [2] and LSD-SLAM [3] have achieved notable success in robot navigation.”
MethodBai, S., Lai, J., Lyu, P., Wang, B., Sun, X., & Yu, W. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3270424 · Cited by 23
“The IMU pre-integration can be expressed as [26] In view of the asynchronism between variable node and GNSS position, the association model needs to be derived for associating asynchronous measurement with variable node to formulate the factor.”
CPnP: Consistent Pose Estimator for Perspective-n-Point Problem with Bias Elimination
Zeng, G., Chen, S., Mu, B., Shi, G., & Wu, J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160942 · Cited by 36
“It has widespread applications in robotics [1]– [3], computer vision [4], augmented reality [5], etc.”
BackgroundZhang, Z., Song, Y., Huang, S., Xiong, R., & Wang, Y. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3272847 · Cited by 29
Mailka, H., Abouzahir, M., & Ramzi, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17595-w · Cited by 24
“Tong Qin Algorithm 3 Extended kalman filter: update step. et al. [52] proposed a novel approach based on a monocular visual-inertial state estimator.”
Advanced 3D Navigation System for AGV in Complex Smart Factory Environments
Li, Y., Wang, D., Li, Q., Cheng, G., Li, Z., & Li, P. (2023) · Electronics · doi:10.3390/electronics13010130 · Cited by 23
Self-citationReal-Time Dynamic SLAM Using Moving Probability Based on IMU and Segmentation
Zhang, H., Wang, D., & Huo, J. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3365822 · Cited by 23
“A popular sensor configuration for this purpose involves the combination of a camera and an IMU, known as visual-inertial SLAM (VI-SLAM) [20], [21].”
BackgroundZhang, H., Xiao, R., Li, J., Yan, C., & Tang, H. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3382751 · Cited by 25
ORIANNA: An Accelerator Generation Framework for Optimization-based Robotic Applications
Hao, Y., Gan, Y., Bo, Y., Liu, Q., Han, Y., Wan, Z., & Liu, S. (2024) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3620665.3640379 · Cited by 27
“Even using factor graphs as the same hardware abstraction, different algorithms necessitate completely distinct accelerators due to their unique mathematical formulations and execution pipelines [28, 37, 52].”
BackgroundMethodInfluentialDevelopment of vision–based SLAM: from traditional methods to multimodal fusion
Zheng, Z., Su, K., Lin, S., Fu, Z., & Yang, C. (2024) · Robotic Intelligence and Automation · doi:10.1108/ria-10-2023-0142 · Cited by 29
NeRF-VINS: A Real-time Neural Radiance Field Map-based Visual-Inertial Navigation System
Katragadda, S., Lee, W., Peng, Y., Geneva, P., Chen, C., Guo, C., Li, M., & Huang, G. P. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610051 · Cited by 34
“Visual-inertial localization uses two main approaches: graph optimization [36], [47] and filter-based methods [10], [12], [48].”
MethodPLE-SLAM: A Visual-Inertial SLAM Based on Point-Line Features and Efficient IMU Initialization
He, J., Li, M., Wang, Y., & Wang, H. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3523039 · Cited by 30
“4, including VINS-Mono [5], ORB-SLAM2/3 [2], [7], Dynamic-VINS [29], and DGM-VINS [30].”
Alternating-Stereo VINS: Observability Analysis and Performance Evaluation
Paul, M. K., & Roumeliotis, S. I. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00497 · Cited by 28
Stereo Visual-Inertial SLAM With Points and Lines
Liu, Y., Yang, D., Li, J., Gu, Y., Pi, J., & Zhang, X. (2018) · IEEE Access · doi:10.1109/access.2018.2880689 · Cited by 24
“In contract, tightly-coupled methods [4]–[8] jointly optimize over all the sensor states by one estimator, which receive more accuracy and robustness.”
MethodAn Automatic Key-Frame Selection Method for Monocular Visual Odometry of Ground Vehicle
Lin, X., Wang, F., Guo, L., & Zhang, W. (2019) · IEEE Access · doi:10.1109/access.2019.2916901 · Cited by 25
“Similar to key-frame selection of VINS-Mono, Eren et al. [13] weights parallax-based metric information, it only requires the minimum expected parallax between two key-frames, without the need for persistence characteristics and motion state discrimination, which can reduce computational complexity and be applied to d…”
BackgroundTerrainFusion: Real-time Digital Surface Model Reconstruction based on Monocular SLAM
Wang, W., Zhao, Y., Han, P., Zhao, P., & Bu, S. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967663 · Cited by 28
“aided methods [44], [45], [24]), and learning based SLAM system (supervised [46], [47], [48] and unsupervised [49], [50]).”
MethodCollaborative Augmented Reality on Smartphones via Life-long City-scale Maps
Platinsky, L., Szabados, M., Hlasek, F., Hemsley, R., Pero, L. D., Pancik, A., Baum, B., Grimmett, H., & Ondrúška, P. (2020) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar50242.2020.00081 · Cited by 24
“For odometry, we experimented with VINS [26] and ORBSLAM [25], but we ended up using a commercial version (ARKit [1]), as it performed best for our handheld AR use case and provided the most robust experience on the tested smartphones.”
MethodZhang, C., Chen, M.-S., Wang, G.-Q., Lin, Y. C., Li, K., Wu, M., Li, Z., & Wang, Q. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3431102 · Cited by 23
“As mentioned in VINS-Mono [25], the additional noise in the gyroscope ( n at ) and accelerometer ( n w t ) is modeled as Gaussian white noise, n at ∼ N ( 0 , σ 2 a δ( t )), n w t ∼ N ( 0 , σ 2 w δ( t )) , where σ a and σ b are the standard deviations of Gaussian white noise.”
BackgroundVisual-Inertial-Acoustic Sensor Fusion for Accurate Autonomous Localization of Underwater Vehicles
Huang, Y., Li, P., Ma, S., Yan, S., Tan, M. H., Yu, J., & Wu, Z. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3488077 · Cited by 22
“In recent years, visual and visual-inertial-based simultaneous localization and mapping (V/VI-SLAM) systems [6], [7], [8], [9], [10] have been extensively investigated and promising results have been achieved in terrestrial and aerial environments [11], [12], [13], [14].”
Self-citationHuang, W., Wan, W., & Liu, H. (2021) · Sensors · doi:10.3390/s21082673 · Cited by 25
“In their extended batch-based monocular VINS (termed VINS-Mono) [40], the IMU biases are included in a sliding window nonlinear estimator.”
BackgroundMethodInfluentialGMSK-SLAM: a new RGB-D SLAM method with dynamic areas detection towards dynamic environments
Wei, H., Zhang, T., & Zhang, L. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11168-5 · Cited by 23
Sung, C., Jeon, S., Lim, H., & Myung, H. (2021) · Intelligent Service Robotics · doi:10.1007/s11370-021-00395-2 · Cited by 24
“LIO-mapping is designed similar to the visual-inertial odometry framework [14].”
BackgroundMethodHe, M., & Rajkumar, R. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636776 · Cited by 27
“VINS-Mono (Visual Inertial Navigation System with Monocular camera) has been well-studied [1], [2], [3], [4] as a relative localization method, since its complementary camera-IMU (Inertial Measurement Unit) configuration is a small-sized, low-cost and easily-deployed system.”
MethodInfluentialAutomated camera-exposure control for robust localization in varying illumination environments
Wang, Y., Chen, H., Zhang, S., & Lu, W. (2022) · Autonomous Robots · doi:10.1007/s10514-022-10036-x · Cited by 24
“…realize localization due to low cost and rich information, and several visual odometry (VO) and simultaneous localization and mapping (SLAM) algorithms are developed, e.g., ORB-SLAM (Mur-Artal et al., 2015), DSO (Engel et al., 2017), VINS-Mono (Qin et al., 2018), and Canny-VO (Zhou et al., 2019).”
BackgroundMethodInfluentialHe, X., Pan, S., Gao, W., & Lu, X. (2022) · Remote Sensing · doi:10.3390/rs14092104 · Cited by 26
“Optimization-based methods have been applied in [31,32] and so on.”
MethodEfficient and adaptive lidar–visual–inertial odometry for agricultural unmanned ground vehicle
Zhao, Z., Zhang, Y., Long, L., Lu, Z., & Shi, J. (2022) · International Journal of Advanced Robotic Systems · doi:10.1177/17298806221094925 · Cited by 22
“After calculating by (11), we get the position f iðxi; yi; ziÞ of each visual feature in the lidar frame.”
MethodPKS: A photogrammetric key-frame selection method for visual-inertial systems built on ORB-SLAM3
Azimi, A., Ahmadabadian, A. H., & Remondino, F. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.07.003 · Cited by 26
Inertial Odometry Using Hybrid Neural Network With Temporal Attention for Pedestrian Localization
Wang, Y., Cheng, H., & Meng, M. Q. ‐. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3186704 · Cited by 22
Yu, Y., Shi, W., Chen, R., Chen, L., Bao, S., & Chen, P. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3190387 · Cited by 22
ESVIO: Event-Based Stereo Visual-Inertial Odometry
Liu, Z., Shi, D., Li, R., & Yang, S. (2023) · Sensors · doi:10.3390/s23041998 · Cited by 30
Robust Visual-Inertial Odometry Based on a Kalman Filter and Factor Graph
Wang, Z., Pang, B. J., Song, Y. H., Yuan, X., Xu, Q., & Li, Y. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3258526 · Cited by 24
“Current popular filter-based methods include MSCKF [5] and ROVIO [6]; optimization-based methods include OKVIS [7] and VINS_Mono [8].”
MethodZhang, L., Wen, W., Hsu, L., & Zhang, T. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3282623 · Cited by 22
“Such as the integration of INS and visual [20], LiDAR [21], GNSS [22], and so on.”
BackgroundMethod3D Vision Aided GNSS Real-Time Kinematic Positioning for Autonomous Systems in Urban Canyons
Wen, W., Bai, X., & Hsu, L. (2023) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.590 · Cited by 24
“To make use of the visual measurements, we will refer to the work of Qin et al. (2018).”
BackgroundMethodInfluentialA Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
He, Y., Xu, B., Ouyang, Z., & Li, 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/cvpr52729.2023.00078 · Cited by 36
“We can observe that the initialization speed of DRT-l is the fastest, and it only takes 3.89 ms, which is 72 times faster than the tightly-coupled method CS-VISfM and 8 times faster than the loosely-coupled method VINS-Mono.”
BackgroundMethodInfluentialLi, H., Zhong, H., Gao, J., Lv, Y., Sha, J., Liang, J., Zhang, H., & Wang, Y. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3317444 · Cited by 22
360-VIO: A Robust Visual–Inertial Odometry Using a 360° Camera
Wu, Q., Xu, X., Chen, X., Pei, L., Long, C., Deng, J., Liu, G., Yang, S. Y., Wen, S., & Yu, W. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3337541 · Cited by 31
“In this section, we present a comparative evaluation of our proposed 360-VIO method with state-of-the-art VIO approaches, including VINS-Mono [7], ORB-SLAM3 [4], and MC-VIO [25], on the proposed 360-VIO datasets.”
MethodInfluentialJi, Q., Zhang, Z., Chen, Y., & Zheng, E. (2024) · IEEE Access · doi:10.1109/access.2024.3379269 · Cited by 28
“Furthermore, some advanced visual SLAM algorithms have demonstrated superior performance, such as ORB-SLAM2 [1], LSD-SLAM [2], and others [3], [4].”
BackgroundGround-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases
Yin, J., Li, A., Xi, W., Yu, W., & Zou, D. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610070 · Cited by 42
“Vision anomalies: Our system employs the KLT sparse optical flow algorithm [26] for tracking feature points as adapted from [12].”
BackgroundMethodInfluentialModeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry
Ling, Y., Bao, L., Jie, Z., Zhu, F., Li, Z., Tang, S., Liu, Y., Liu, W., & Zhang, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_30 · Cited by 25
“However, neither OKVIS or VINS-Mono provides reasonable estimates.”
ResultInfluentialVisual-Inertial Odometry with Robust Initialization and Online Scale Estimation
Hong, E., & Lim, J. (2018) · Sensors · doi:10.3390/s18124287 · Cited by 23
“Thus, we follow the pre-integration method, which represents IMU measurements to the poses of the consecutive frames by adding IMU factors incrementally as in [7,8].”
MethodHeteroFusion: Dense Scene Reconstruction Integrating Multi-Sensors
Yang, S. Y., Li, B., Liu, M., Lai, Y., Kobbelt, L. P., & Hu, S. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2919619 · Cited by 22
“In this method, odometry estimation is solved through a cost function integrating information from multiple sensors [34], where measurements are regarded as priors and camera as well as laser frames are used for scan-matching based on iterative closest point (ICP) algorithms [35].”
Robust Motion Compensation for Event Cameras With Smooth Constraint
Xu, J., Jiang, M., Yu, L., Yang, W. T., & Wang, W. (2020) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2020.2964255 · Cited by 26
“Then different image frame sequences are evaluated with the classical SLAM algorithm Vins-mono [28].”
MethodIndoor multi-sensor fusion positioning based on federated filtering
Li, H., Ao, L., Guo, H., & Yan, X. (2020) · Measurement · doi:10.1016/j.measurement.2020.107506 · Cited by 23
Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network
Zhao, X., Liu, J., Wu, X., Chen, W., Guo, F., & Li, Z. G. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3068761 · Cited by 23
PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and LinePreprint
Fu, Q., Wang, J., Yu, H., Ali, I., Guo, F., & Zhang, H. (2020) · arXiv (Cornell University) · Cited by 31
Simultaneous Localization and Mapping Related Datasets: A Comprehensive SurveyPreprint
Liu, Y., Fu, Y., Chen, F., Goossens, B., Tao, W., & Zhao, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04036 · Cited by 31
“> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) 16 Mount Etna [100] 2018 11 2gray (stereo) Y N/A DGPS N/A MVSEC [101] 2018 91 2event (stereo) 2gray (stereo) Y 1Velodyne-16 MoCap/ LiDAR+IMU+GPS N/A SPO [102] 2018 5 2gray (stereo) 1plenoptic N/A N/A Loop Drift N/A TUM VI [103] 2018…”
InfluentialFast Swarming of UAVs in GNSS-Denied Feature-Poor Environments Without Explicit Communication
Horyna, J., Krátký, V., Pritzl, V., Báča, T., Ferrante, E., & Saska, M. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3390596 · Cited by 26
“The proposed swarm framework was designed upon the UVDAR smart sensor [11], [12], and VINS-Mono [31], [32].”
MethodKühne, J., Magno, M., & Benini, L. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3406948 · Cited by 33
“In our work, we use an accelerator for the OF calculation implemented on an ASIC, while running the remaining parts of the VIO pipeline on the main processor of a Raspberry Pi Compute Module 4.”
InfluentialImproving S-MSCKF With Variational Bayesian Adaptive Nonlinear Filter
Zhang, Z., Dong, P., Wang, J., & Sun, Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2989206 · Cited by 23
“There are some famous optimization-based VIO systems, including OKVIS [20], VINS-mono and its developed version VINS-fusion [24], [31]–[33].”
BackgroundMethodComparison of Three Off-the-Shelf Visual Odometry Systems
Alapetite, A., Wang, Z., Hansen, J. P., Zajączkowski, M., & Patalan, M. (2020) · Robotics · doi:10.3390/robotics9030056 · Cited by 27
Multi-Camera-Based Universal Measurement Method for 6-DOF of Rigid Bodies in World Coordinate System
Zhao, Z., Zhu, Y., Li, Y., Zhi, Q., Luo, Y., Xie, C., & Zhang, Z. (2020) · Sensors · doi:10.3390/s20195547 · Cited by 21
“The commonly used measuring instruments or methods include laser, Hall sensor, inertial measurement unit (IMU), total station, and vision.”
MethodImproved IMU Preintegration with Gravity Change and Earth Rotation for Optimization-Based GNSS/VINS
Jiang, J., Niu, X., & Liu, J. (2020) · Remote Sensing · doi:10.3390/rs12183048 · Cited by 22
“The states outside the sliding window are either directly fixed [9,12] or marginalized out [10,11,13].”
BackgroundA Switching-Coupled Backend for Simultaneous Localization and Dynamic Object Tracking
Liu, Y., Liu, J., Hao, Y., Deng, B., & Meng, Z. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3056072 · Cited by 27
“In particular, an existing visual-inertial odometry (VIO) algorithm (VINS-mono [20]) is first performed to estimate the robot states.”
MethodRobust Multispectral Visual-Inertial Navigation With Visual Odometry Failure Recovery
Beauvisage, A., Ahıska, K., & Aouf, N. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3090675 · Cited by 22
UVIP: Robust UWB aided Visual-Inertial Positioning System for Complex Indoor Environments
Yang, B., Li, J., & Zhang, H. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561208 · Cited by 23
Online Spatial and Temporal Initialization for a Monocular Visual-Inertial-LiDAR System
Wang, Y., & Ma, H. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3133578 · Cited by 21
Online Visual-Inertial Extrinsic Calibration Utilizing GNSS Measurements for Vehicle Applications
Zhou, Y., Li, S., Xia, C., Shen, Z., Wang, X., & Li, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3144409 · Cited by 22
VidSfM: Robust and Accurate Structure-From-Motion for Monocular Videos
Cui, H., Tu, D., Tang, F., Xu, P., Liu, H., & Shen, S. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3156375 · Cited by 22
Self-citation
Metadata
- Authors
- Qin, T., Li, P., & Shen, S.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Transactions on Robotics
- Published
- 2018-08
- Volume
- 34
- Issue
- 4
- Pages
- 1004-1020
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2745859992
- Cited by
- 4,669
- References
- 53
- Citations by year
- 2026: 575 · 2025: 856 · 2024: 789 · 2023: 729 · 2022: 571 · 2021: 469 · 2020: 357 · 2019: 248 · 2018: 73
- FWCI
- 233.33
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong Research Grants Council Early Career Scheme (26201616)
- HKUST Proof-of-Concept (PCF.009.16/17)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Aerospace Engineering › Inertial Sensor and Navigation
- Physical Sciences › Engineering › Aerospace Engineering › Aerospace Engineering and Control Systems
- Keywords
- loop detection, relocalization, pose graph optimization, autonomous flight
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.