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 401–500 of 1,001
Decoupled Right Invariant Error States for Consistent Visual-Inertial Navigation
Yang, Y., Chen, C., Lee, W., & Huang, G. P. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3140054 · Cited by 63
“In spite of many great works on batch optimization-based VINS [2], [3], [7], [9], the filter-based algorithms [6], [10]–[14] are still extensively used mainly due to their simplicity and efficiency.”
BackgroundA comprehensive overview of dynamic visual SLAM and deep learning: concepts, methods and challenges
Beghdadi, A., & Mallem, M. (2022) · Machine Vision and Applications · doi:10.1007/s00138-022-01306-w · Cited by 56
“Finally, it gets shorter execution times compared to other methods, and accuracy similar to the VINS-Mono method [30,31].”
MethodInfluentialLearning Selective Sensor Fusion for State Estimation
Chen, C., Rosa, S., Lu, C. X., Wang, B., Trigoni, N., & Markham, A. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3176677 · Cited by 58
“…of learning models [i.e., Vision-Only (DeepVO) and VIO Direct (VINet)] and classical algorithms (i.e., MSCKF [18], OKVIS [24], and mono-VINS [34]) on the trajectory MH_05_Difficult in the presence of normal data, all combined visual degradation (10% occlusion, 10% motion blur, and 10%…”
InfluentialLee, Y.-J., Hwang, Y., Ahn, J. Y., Seo, J., & Park, B. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3256040 · Cited by 59
“As a more advanced type, the GNSS–inertial measurement unit (IMU)–camera combined system has also been proposed for better dynamic application of vision sensors to provide accurate relative positions [20][21].”
MethodA Review of Recurrent Neural Network Based Camera Localization for Indoor Environments
Alam, M. S., Mohamed, F., Selamat, A., & Hossain, A. B. (2023) · IEEE Access · doi:10.1109/access.2023.3272479 · Cited by 52
“Monocular Visual-Inertial System: A monocular visual-inertial state estimator is the Monocular Visual-Inertial System (Mono-VINS) [190].”
BackgroundFunabiki, N., Morrell, B. J., Nash, J., & Agha–mohammadi, A. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3026659 · Cited by 51
Tightly-Coupled Single-Anchor Ultra-wideband-Aided Monocular Visual Odometry System
Nguyen, T. H., Nguyen, T., & Xie, L. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196794 · Cited by 50
“Many state-of-the-art approaches [15]–[17] can demonstrate very high accuracy and robustness in a wide range of environments.”
BackgroundShu, F., Lesur, P., Xie, Y., Pagani, A., & Stricker, D. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00180 · Cited by 58
UAV-LiDAR-Based Measuring Framework for Height and Stagger of High-Speed Railway Contact Wire
Geng, Y., Pan, F., Jia, L., Wang, Z., Qin, Y., Tong, L., & Li, S. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3071445 · Cited by 50
MC-Calib: A generic and robust calibration toolbox for multi-camera systems
Rameau, F., Park, J., Bailo, O., & Kweon, I. S. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103353 · Cited by 53
Leveraging Structural Information to Improve Point Line Visual-Inertial Odometry
Xu, B., Wang, P., He, Y.-J., Chen, Y., Chen, Y.-N., & Zhou, M. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3146893 · Cited by 36
“To assess the advantages of our proposed approach, we compared our method with VINS-Mono without loop closure [2], PL-VIO [7], PL-VINS without loop closure [26], open-VINS with monocular mode [27], and BASALT [28].”
InfluentialVisual SLAM for Unmanned Aerial Vehicles: Localization and Perception
Zhuang, L., Zhong, X., Xu, L., Tian, C., & Yu, W. (2024) · Sensors · doi:10.3390/s24102980 · Cited by 56
“…[98] feature-based EKF-based - OKVIS [100] feature-based Local BA - ROVIO [99] direct EKF-based - ORB-SLAM-VI [101] feature-based Local BA PGBA VINS-Mono [102] feature-based Local BA PGBA VI-DSO [103] direct Local BA - ORB-SLAM3 [24] feature-based Local BA, GBA PGBA DM-VIO [104] direct Local BA -”
BackgroundMethodGLIM: 3D range-inertial localization and mapping with GPU-accelerated scan matching factors
Koide, K., Yokozuka, M., Oishi, S., & Banno, A. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104750 · Cited by 57
“Loose vs. tight IMU coupling: With progress in visual-inertial SLAM [17]–[19], IMU fusion has become an important technique for range-based SLAM [10].”
BackgroundMethodInfluentialRodríguez-Martínez, E. A., Flores‐Fuentes, W., Achakir, F., Sergiyenko, O., & Murrieta-Rico, F. N. (2025) · Eng—Advances in Engineering · doi:10.3390/eng6070153 · Cited by 63
“VINS-Fusion extends this idea by supporting stereo, monocular, and GPS factors; its solver has become a staple on micro-air-vehicles where the mass and power are constrained [52].”
DMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors
Liu, G., Zeng, W., Feng, B., & Xu, F. (2019) · Sensors · doi:10.3390/s19173714 · Cited by 52
IDOL: A Framework for IMU-DVS Odometry using Lines
Gentil, C. L., Tschopp, F., Alzugaray, I., Vidal‐Calleja, T., Siegwart, R., & Nieto, J. I. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341208 · Cited by 61
Autonomous Obstacle Avoidance for UAV based on Fusion of Radar and Monocular Camera
Yu, H., Zhang, F., Huang, P., Wang, C., & Li, Y. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341432 · Cited by 45
“Chen Wang is with the Key Laboratory for Highway Construction Technology and Equ ipment of Ministry of Education, Chang’an University, middle-sec tion of Nan’er Huan Road, Xi’an, ShaanXi Province, 710064, China (email: wangchenjustin@chd.edu.cn). pletely unknown environments [1-3].”
BackgroundLIRO: Tightly Coupled Lidar-Inertia-Ranging Odometry
Nguyen, T., Cao, M., Yuan, S., Lyu, Y., Nguyen, T. H., & Xie, L. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560954 · Cited by 55
A fast, complete, point cloud based loop closure for LiDAR odometry and mappingPreprint
Lin, J., & Zhang, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11811 · Cited by 62
“This kind of method has been used in most of the state of the art visual SLAM system (e.g. [8, 9]) and have achieved great success in the past years.”
MethodJiang, S., Wu, Y. Q., & Zhang, J. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104685 · Cited by 48
Xue, C., Huang, Y., Zhao, C. B., Li, X., Mihaylova, L. S., Li, Y., & Chambers, J. A. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3213787 · Cited by 48
“The tightly-coupled VIO methods consist of optimization-based methods and filter-based methods, where the former methods can achieve better accuracy performance while at the cost of greater computation, these include the PTAM [1], OKVIS [2], VINS-mono [3], and VINS-fusion [4].”
BackgroundMethodContinuous-Time Fixed-Lag Smoothing for LiDAR-Inertial-Camera SLAM
Lv, J., Lang, X., Xu, J., Wang, M., Liu, Y., & Zuo, X. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3241398 · Cited by 57
“Among all of the sensors, camera, IMU and LiDAR are three of the most ubiquitous sensors leveraged in SLAM algorithms [1], [2], [3], [4], [5], [6].”
BackgroundMethodInfluentialLi, S., Li, X., Chen, S., Zhou, Y., & Wang, S. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3270506 · Cited by 51
“The representative works include S-MSCKF [18], VINS-Mono [19], and ROVIO[20].”
InfluentialNTU4DRadLM: 4D Radar-Centric Multi-Modal Dataset for Localization and Mapping
Zhang, J., Zhuge, H., Liu, Y., Peng, G., Wu, Z., Zhang, H., Lyu, Q., Li, H., Zhao, C., Kırcalı, D., et al. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422606 · Cited by 44
“Currently, most research is focused on LiDAR-and visual-SLAM [6], [7].”
MethodGe, Y., Zhang, L., Wu, Y., & Hu, D. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3366815 · Cited by 52
“The current popular VI-SLAM systems mainly use tightly coupling optimization algorithms [1], [2], where it is crucial to establish the loss function by utilizing both inertial and visual constraints.”
BackgroundMethodInfluentialLVIO-Fusion:Tightly-Coupled LiDAR-Visual-Inertial Odometry and Mapping in Degenerate Environments
Zhang, H., Du, L., Bao, S., Yuan, J., & Ma, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3371383 · Cited by 54
“Aerial Vehicles, etc. Existing SLAM methods have been demonstrated satisfactory performance in environments that have abundant textures or geometric features by employing single sensors such as camera [1], [2], [3] or light detection and ranging (LiDAR) sensor [4], [5], [6].”
MethodAQUA-SLAM: Tightly Coupled Underwater Acoustic-Visual-Inertial SLAM With Sensor Calibration
Xu, S., Zhang, K., & Wang, S. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3554396 · Cited by 46
“FusingvisualSLAMwithaninertialmeasurementunit (IMU),knownasvisual-inertialSLAM(VI-SLAM)[4],[5], canalleviatesomeofthechallengesarisingfromtransient, noise-affectedvisualinputsfromanopticalcamera,suchas momentarymotionblur.”
Semantic Visual Simultaneous Localization and Mapping: A Survey
Chen, K., Xiao, J., Liu, J., Tong, Q., Zhang, H., Liu, R., Zhang, J., Ajoudani, A., & Chen, S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3556928 · Cited by 61
“In addition to these, VINS-Mono [27] introduces a tightly coupled optimization framework that significantly improved positioning accuracy and robustness, making it a key method in the visual-inertial fusion domain.”
Wang, K., Zhou, J., Zhang, W., & Zhang, B. (2021) · Sensors · doi:10.3390/s21020339 · Cited by 45
“where Ft is the error state transfer matrix, Gt is the noise Jacobi matrix, and w is the Gaussian noise vector; more details can be found in the literature [15].”
BackgroundMethodInfluentialAvoiding Degeneracy for Monocular Visual SLAM with Point and Line Features
Lim, H., Kim, Y., Jung, K., Hu, S., & Myung, H. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560911 · Cited by 58
“The proposed method has better localization accuracy than VINS-Mono and PL-VINS.”
MethodInfluentialEudoxus: Characterizing and Accelerating Localization in Autonomous Machines Industry Track Paper
Gan, Y., Bo, Y., Tian, B., Xu, L., Hu, W., Liu, S., Liu, Q., Zhang, Y., Tang, J., & Zhu, Y. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00074 · Cited by 57
“We use the widely-used VINS-Fusion framework [73], [14] for experiments.”
MethodPLC-VIO: Visual–Inertial Odometry Based on Point-Line Constraints
Liu, Z., Shi, D., Li, R., Qin, W., Zhang, Y., & Ren, X. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3077026 · Cited by 49
“What is more, by introducing the proposed point-line constraints for VIO, our PLV-VIO w/o loop closure performs better than most systems (both points only based and point-line based) without loop (i.e., VINS-Mono, PL-VIO, and MSCKF lines) and even better than some systems with loop closure (i.e., VINS-Mono_loop).”
BackgroundMethodInfluentialA Multi-User Collaborative AR System for Industrial Applications
Wang, J., & Qi, Y. (2022) · Sensors · doi:10.3390/s22041319 · Cited by 51
“A variety of SLAM systems utilize the BA process to reduce accumulative errors [42,43].”
BackgroundPFD-SLAM: A New RGB-D SLAM for Dynamic Indoor Environments Based on Non-Prior Semantic Segmentation
Zhang, C., Zhang, R., Jin, S., & Yi, X. (2022) · Remote Sensing · doi:10.3390/rs14102445 · Cited by 46
AdaptSLAM: Edge-Assisted Adaptive SLAM with Resource Constraints via Uncertainty Minimization
Chen, Y., İnaltekin, H., & Gorlatova, M. A. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229009 · Cited by 44
“(x̃e) ⊤ Iex̃e is the Mahalanobis norm [20], [21] of the estimated measurement noise for e with respect to Ie.”
BackgroundMethodInfluentialMulti-Sensor Fusion based Robust Row Following for Compact Agricultural Robots
Velasquez, A. E. B., Higuti, V. A. H., Gasparino, M. V., Sivakumar, A. N. V., Becker, M., & Chowdhary, G. V. (2022) · Field Robotics · doi:10.55417/fr.2022043 · Cited by 43
360VO: Visual Odometry Using A Single 360 Camera
Huang, H., & Yeung, S.-K. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812203 · Cited by 63
Deep Learning for Visual SLAM: The State-of-the-Art and Future Trends
Favorskaya, M. N. (2023) · Electronics · doi:10.3390/electronics12092006 · Cited by 47
Robust High Accuracy Visual-Inertial-Laser SLAM System
Wang, Z., Zhang, J., Chen, S., Yuan, C., Zhang, J., & Zhang, J. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967702 · Cited by 47
“VINS-Mono [2] is a tightly-coupled visual-inertial state estimator, using a nonlinear optimization-based approach to acquire accurate visual-inertial odometry by fusing pre-integrated inertial measurements and visual observations.”
BackgroundMethodInfluentialMonocular Visual-Inertial-Wheel Odometry Using Low-Grade IMU in Urban Areas
Jung, J. H., Cha, J., Chung, J. Y., Kim, T. I., Seo, M. H., Park, S. Y., Yeo, J. Y., & Park, C. G. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3018167 · Cited by 46
Sensor 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
“Visual SLAM such as MonoSLAM [3], DSO [4], ORB-SLAM [5] and VINS-Mono [6], where the primary sensor is the camera, can get rich information from the environment, but they are sensitive to texture richness and illumination.”
BackgroundDeepAVO: Efficient pose refining with feature distilling for deep Visual Odometry
Zhu, R., Yang, M., Liu, W., Song, R., Yan, B., & Xiao, Z. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.029 · Cited by 50
Integrity of Visual Navigation—Developments, Challenges, and Prospects
Zhu, C., Meurer, M., & Günther, C. G. (2022) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.518 · Cited by 47
“…error propagation in the depth estimation must be additionally considered, and the global scale must be estimated if a monocular camera is applied, normally with the aid of other sensors like inertial sensors (Lynen et al., 2020 ; Qin et al., 2018) or ranging measurements (Zhu et al., 2017 , 2018).”
Thermal-Inertial SLAM for the Environments With Challenging Illumination
Jiang, J., Chen, X., Dai, W., Gao, Z., & Zhang, Y. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3185385 · Cited by 53
“However, the traditional loop closing strategy [37], [38] cannot be directly applied to the infrared domain for the following problems.”
BackgroundZhang, S., Zhang, J., & Tao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19839-7_9 · Cited by 58
A Robust LiDAR SLAM Method for Underground Coal Mine Robot with Degenerated Scene Compensation
Yang, X., Lin, X., Yao, W., Ma, H., Zheng, J., & Ma, B. (2022) · Remote Sensing · doi:10.3390/rs15010186 · Cited by 49
LE-VINS: A Robust Solid-State-LiDAR-Enhanced Visual-Inertial Navigation System for Low-Speed Robots
Tang, H., Niu, X., Zhang, T., Wang, L., & Liu, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3260279 · Cited by 54
“An IMU can be incorporated to construct a visual-inertial navigation system (VINS) [2], [3] and retrieve the scale.”
MethodSamadzadeh, A., & Nickabadi, A. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3268591 · Cited by 47
“The base error function used in VINS-Mono [8] can then be written as”
InfluentialXu, Z., Zhan, X., Chen, B., Xiu, Y., Yang, C., & Shimada, K. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161194 · Cited by 48
Real-time localization and 3D semantic map reconstruction for unstructured citrus orchards
Xiong, J., Liang, J., Zhuang, Y., Hong, D., Zheng, Z., Liao, S., Hu, W., & Yang, Z. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108217 · Cited by 43
Wang, F., Zou, Y., Zhang, C., Buzzatto, J., Liarokapis, M. V., Castillo, E. D. R., & Lim, J. B. P. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.105139 · Cited by 49
Hu, C. J., Huang, P. S., & Wang, W. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3328367 · Cited by 42
“Because visual factor and inertial factor are covered in detail in VINS-Mono [4], this letter only gives a brief introduction to them.”
BackgroundMethodSchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System
Fan, Y., Zhao, T., & Wang, G. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01701 · Cited by 62
“Typical optimization-based methods [4, 17, 21, 24, 33, 34] model poses and the corresponding observed landmarks jointly.”
BackgroundMethodSLAM-based localization of 3D gaze using a mobile eye tracker
Wang, H., Pi, J., Qin, T., Shen, S., & Shi, B. E. (2018) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3204493.3204584 · Cited by 47
“We use a SLAM algorithm [Qin et al. 2017] to estimate T ks , t from the past gyroscope, accelerometer and image data.”
MethodSelf-citationPseudo-3D Vision-Inertia Based Underwater Self-Localization for AUVs
Wang, Y., Ma, X., Wang, J., & Wang, H. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2993715 · Cited by 43
DVIO: An Optimization-Based Tightly Coupled Direct Visual-Inertial Odometry
Jiang, J., Yuan, J., Zhang, X., & Zhang, X. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3036243 · Cited by 47
“For indirect methods, visual measurements are transformed into feature observations by extracting and matching the parametric representations of the geometric primitives, which are utilized for the subsequent estimation of the geometry and robot motion [6]–[8].”
BackgroundMethodInfluentialImage-Based Visual Servoing of Rotorcrafts to Planar Visual Targets of Arbitrary Orientation
Li, J., Hui, X., Low, K. H., Yong, J., & Li, B. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3101878 · Cited by 42
“Actually, the velocity estimation using a motion capture system can be replaced by other velocity estimation methods, such as monocular visual-inertial state estimation [37] and dynamics-inertial state estimation [38], that the proposed visual servoing scheme can be implemented purely based on an onboard inertial meas…”
MethodLiu, W., Bo, Y., Gan, Y., Liu, Q., Tang, J., Liu, S., & Zhu, Y. (2021) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3466752.3480077 · Cited by 55
“For instance, the popular localization framework VINS [5, 66] has about a hundred thousand lines of code.”
BackgroundHASTE: multi-Hypothesis Asynchronous Speeded-up Tracking of Events
Alzugaray, I., & Chli, M. (2020) · British Machine Vision Conference (BMVC) · doi:10.5244/c.34.164 · Cited by 68
Doer, C., & Trommer, G. F. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636799 · Cited by 55
“An analysis is carried out for different approaches to compare state of the art with our proposed approach: • VINS: A state of the art sliding window optimization approach for VIO [3].”
BackgroundMethodInfluentialA Loosely Coupled Extended Kalman Filter Algorithm for Agricultural Scene-Based Multi-Sensor Fusion
Lv, M., Wei, H., Fu, X., Wang, W., & Zhou, D. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2022.849260 · Cited by 46
GRACO: A Multimodal Dataset for Ground and Aerial Cooperative Localization and Mapping
Zhu, Y., Kong, Y., Jie, Y., Xu, S., & Cheng, H. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3234802 · Cited by 60
“With the help of these single-robot datasets, many excellent single-agent SLAM algorithms have emerged this year, such as LOAM [13] and VINS-mono [14].”
MethodCerberus: Low-Drift Visual-Inertial-Leg Odometry For Agile Locomotion
Yang, S., Zhang, Z., Fu, Z., & Manchester, Z. R. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160486 · Cited by 46
“The error dynamics [21] of rrr as where n n n a and n n n ω are IMU sensor measurement noises and ] is a vector describing the errors between preintegration terms and their “true” values after each IMU measurement integration [21].”
BackgroundMethodInfluentialDRIO: Robust Radar-Inertial Odometry in Dynamic Environments
Chen, H., Liu, Y., & Cheng, Y. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3301290 · Cited by 43
“Following the widely-used odometry benchmark [2], we adopt the Absolute Trajectory Error (ATE) and Relative Pose Error (RPE) to evaluate the proposed method.”
BackgroundMethodMSC-RAD4R: ROS-Based Automotive Dataset With 4D Radar
Choi, M., Yang, S.-H., Han, S., Lee, Y., Lee, M., Choi, K. H., & Kim, K.-S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3307005 · Cited by 50
H$_{2}$-Mapping: Real-Time Dense Mapping Using Hierarchical Hybrid Representation
Jiang, C., Zhang, H., Liu, P., Yu, Z., Cheng, H., Zhou, B., & Shen, S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3313051 · Cited by 58
“Specifically, we employ the Realsense L515 as the vision sensor to provide RGB-D images, and a modified VINS-Mono [26] incorporating depth constraints as the tracking module to estimate the pose.”
MethodSelf-citationReview 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
Wei, H., Jiao, J., Hu, X., Yu, J., Xie, X., Wu, J., Zhu, Y., Liu, Y., Wang, L., & Liu, M. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241303525 · Cited by 69
“…has set new benchmarks and hastened the enhancement of SOTA algorithms, spanning both handcrafted and data-driven methods such as VINS-Mono (Qin et al., 2018), FAST-LIO2 (Xu et al., 2022), VILENS (Wisth et al., 2022), DROID-SLAM (Teed and Deng, 2021), and Gaussian Splatting SLAM (Matsuki…”
General Place Recognition Survey: Toward Real-World Autonomy
Yin, P., Jiao, J., Zhao, S., Xu, L., Huang, G. P., Choset, H., Scherer, S., & Han, J. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3550771 · Cited by 71
“Typical SLAM systems, such as ORB-SLAM [152] and VINS-Mono [153] are designed with the PR module to maintain the global consistency of poses, mainly rely on the DBoW2 library [25] and use the BoW representation with specific global descriptors to quickly detect loop candidates.”
Trajectory Replanning for Quadrotors Using Kinodynamic Search and Elastic Optimization
Ding, W., Gao, W., Wang, K., & Shen, S. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8463188 · Cited by 41
“The localization module is based on our Monocular Visual Inertial Navigation System (VINS-Mono) [5], and mapping module is based on monocular dense mapping and TSDF fusion.”
MethodSelf-citationInformation Sparsification in Visual-Inertial Odometry
Hsiung, J., Hsiao, M., Westman, E., Valencia, R., & Kaess, M. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594007 · Cited by 54
“We compare our method against stereo OKVIS [28] and monocular VINS-MONO [33], which are the state-of-the-art fixed-lag VIO systems.”
BackgroundMethodInfluentialA Linear-Complexity EKF for Visual-Inertial Navigation with Loop Closures
Geneva, P., Eckenhoff, K., & Huang, G. P. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793836 · Cited by 49
“3: The estimated trajectories of the proposed SchmidtMSCKF, standard MSCKF [1], and VINS-Mono [18, 19].”
BackgroundMethodInfluentialAutonomous aerial robot using dual‐fisheye cameras
Gao, W., Wang, K., Ding, W., Gao, F., Qin, T., & Shen, S. (2020) · Journal of Field Robotics · doi:10.1002/rob.21946 · Cited by 51
“In this section, we improve the state‐of‐the‐art tightly coupled visual‐inertial navigation system (Qin et al., 2018) to satisfy ultrawide FOV dual‐fisheye cameras.”
MethodSelf-citationObservability Analysis of IMU Intrinsic Parameters in Stereo Visual–Inertial Odometry
Jung, J. H., Heo, S., & Park, C. G. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2985174 · Cited by 45
“On the other hand, while most of the research studies (see [3], [5], [8], [9]) have focused on a monocular system, binocular measurements could yield significant advantages owing to its stereo baseline—this conveys actual scale information from image coordinates to the real metric.”
BackgroundChen, Y., Fu, C., Leung, S. W. W., & Shi, L. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3002203 · Cited by 45
“To avoid using magnetometer data to eliminate drifts, in some researches, other sensors were involved to optimize the results, such as the cameras [16], [17], laser sensor [18] and UWB [19].”
MethodThree Birds, One Stone: Unified Laser-Based 3-D Reconstruction Across Different Media
Gu, C., Cong, Y., & Sun, G. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3039641 · Cited by 41
“RECOVERING 3-D scenes from images is crucial for robot vision, especially for robot navigation [1]–[5] and”
BackgroundYang, B., Li, J., & Zhang, H. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3101322 · Cited by 50
Yu, X., Li, Q., Queralta, J. P., Heikkonen, J., & Westerlund, T. (2021) · IEEE International Conference on Autonomous Systems (ICAS) · doi:10.1109/icas49788.2021.9551177 · Cited by 53
Continuous-time Radar-inertial Odometry for Automotive Radars
Ng, Y. Z., Choi, B., Tan, R. T., & Heng, L. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636014 · Cited by 51
“There are a few existing works on LiDAR-inertial odometry [9, 21, 20] and many more existing works on visualinertial odometry [15, 14, 18, 5, 16, 19].”
BackgroundA Novel Orientation Determination Approach of Mobile Robot Using Inertial and Magnetic Sensors
Xu, X., Sun, Y., Tian, X., Zhou, L., & Li, Y. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3177762 · Cited by 42
Lai, T. (2022) · Sensors · doi:10.3390/s22197265 · Cited by 55
“Similar approaches such as VINSFusion [107] are capable of using IMU fused with monocular visual input for estimating odometry with high reliability.”
MethodVision-Based GNSS-Free Localization for UAVs in the Wild
Gurgu, M.-M., Queralta, J. P., & Westerlund, T. (2022) · International Conference on Mechanical Engineering and Robotics Research (ICMERR) · doi:10.1109/icmerr56497.2022.10097798 · Cited by 55
“The second and third methods prove their utility in environments where GNSS signal is unreliable, for example inside buildings, where localization systems such as UWB [5], [6] or VI-SLAM are preferred [7].”
MethodMax: A Wheeled-Legged Quadruped Robot for Multimodal Agile Locomotion
Zhou, Q., Yang, S., Jiang, X., Zhang, D., Chi, W., Chen, K., Zhang, S., Li, J., Zhang, J., Wang, R., et al. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3345876 · Cited by 43
“The visual localization on Max is provided by a visual-inertial odometry (VIO) system modified from VINSMono [107], which fuses the time domain feature information and IMU measurements at 25 Hz and enables real-time performance even using one thread.”
MethodMa, F., Shi, J., Yu, Y., Li, J., & Dai, K. (2019) · Sensors · doi:10.3390/s19214816 · Cited by 47
MGC-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
ROVINS: 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
“Many monocular VIO methods [12]–[16] have shown superior accuracy in real-world environments, while various multi-camera-based methods have been reported to improve the perception abilities.”
BackgroundMethodInfluentialWen, 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
“There are two predominant visual-inertial system methods: monocular visual-inertial sys-tem [24]–[26] and stereo visual-inertial system [27], [28].”
MethodTang, L., Wang, H., Liu, Z., & Wang, Y. (2020) · Journal of Field Robotics · doi:10.1002/rob.21997 · Cited by 42
“We reduced the number of features tracked by VINS‐Mono and closed its loopback detection module.”
MethodInfluentialComparing Representations in Tracking for Event Camera-based SLAM
Jiao, J., Huang, H., Li, L., He, Z., Zhu, Y., & Liu, M. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00151 · Cited by 53
“We hope that these results and conclusions shown in this paper may provide a reference for researchers on event-based SLAM and indicate possible directions to improve the state-of-the-art (SOTA) methods.”
ResultREAL: Rapid Exploration with Active Loop-Closing toward Large-Scale 3D Mapping using UAVs
Lee, E. M., Choi, J., Lim, H., & Myung, H. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636611 · Cited by 44
“For the pose estimation, VINS-Stereo [16] is adopted due to its higher accuracy, which was analyzed in [17].”
BackgroundMethodMagnetic Field-Enhanced Learning-Based Inertial Odometry for Indoor Pedestrian
Wang, Y., Kuang, J., Li, Y., & Niu, X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3186358 · Cited by 48
“We adopted the marginal-ization technique [4] [27] to approximate the information contained in the removed residuals.”
Xia, L., Meng, D., Zhang, J., Zhang, D., & Hu, Z. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3198724 · Cited by 40
“VINS-Mono, as a nonlinear optimization-based benchmark, belongs to such research work [4].”
BackgroundVIRAL SLAM: Tightly Coupled Camera-IMU-UWB-Lidar SLAMPreprint
Nguyen, T., Yuan, S., Cao, M., Nguyen, T. H., & Xie, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03296 · Cited by 61
“Specifically, VINS-Mono2 [11], VINS-Fusion3, A-LOAM 4, LIO-SAM5, M-LOAM6 [14] are considered.”
MethodInfluentialGNSS Spoofing Detection Based on Coupled Visual/Inertial/GNSS Navigation System
Gu, N., Xing, F., & You, Z. (2021) · Sensors · doi:10.3390/s21206769 · Cited by 43
“Based on previous work the litera‐ ture [26,27], a nonlinear optimization algorithm with a key‐frame sliding window is used to form the VIO.”
MethodGlobally Consistent and Tightly Coupled 3D LiDAR Inertial Mapping
Koide, K., Yokozuka, M., Oishi, S., & Banno, A. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812385 · Cited by 42
Experimental evaluation of Visual‐Inertial Odometry systems for arable farming
Cremona, J., Comelli, R., & Pire, T. (2022) · Journal of Field Robotics · doi:10.1002/rob.22099 · Cited by 47
“In recent years, the use of RGB cameras (monocular or stereo) with IMU has shown to be a good combination to solve the localization problem in a wide range of environments (Zou et al., 2019; Sun et al., 2018; Leutenegger et al., 2015; Qin et al., 2018; Campos et al., 2020).”
BackgroundM2C-GVIO: motion manifold constraint aided GNSS-visual-inertial odometry for ground vehicles
Hua, T., Pei, L., Li, T., Yin, J., Liu, G., & Yu, W. (2023) · Satellite Navigation · doi:10.1186/s43020-023-00102-9 · Cited by 44
“Representative approaches include OKVIS (Leutenegger et al., 2013) and VINS-Mono (Qin et al., 2018), which develop an Inertial Measurement Unit (IMU) pre-integration technique (Forster et al., 2015), and ORB_SLAM3 (Campos et al., 2021b) introduces ORB corner extraction method.”
MethodInfluentialGNSS PPP-RTK tightly coupled with low-cost visual-inertial odometry aiming at urban canyons
Wang, F., & Geng, J. (2023) · Journal of Geodesy · doi:10.1007/s00190-023-01749-7 · Cited by 42
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
“Therefore, unlike [63, 81], we attempt to create a compact and efficient back-end, which considers only the linear velocity and IMU’s bias as the optimizing variables.”
Self-citationSensor-Failure-Resilient Multi-IMU Visual-Inertial Navigation
Eckenhoff, K., Geneva, P., & Huang, G. P. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794295 · Cited by 46
“Qin and Shen [31] extended their prior work on batch-based monocular VINS [7] to include estimating the time offset between a camera and a single IMU by interpolating the location of features on the image plane.”
Background
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.