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 901–1,000 of 1,001
A survey on localization, mapping, and trajectory planning for quadruped robots in vineyards
Ferreira, J. G. G., Moreira, A. P., Silva, M. F., & dos Santos, F. N. (2022) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc55462.2022.9784796 · Cited by 22
Hierarchical Estimation-Based LiDAR Odometry With Scan-to-Map Matching and Fixed-Lag Smoothing
Liang, S., Cao, Z., Wang, C., & Yu, J. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3173665 · Cited by 24
“The former estimates the pose of visual sensor by image matching, which attracts the researchers by virtue of abundant visual information as well as its low price and lightweight [1].”
BackgroundInfluentialVariable Observability Constrained Visual-Inertial-GNSS EKF-Based Navigation
Liu, C., Jiang, C., & Wang, H. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3175600 · Cited by 21
“Though g-MSCKF and GVINS are based on different vision systems, stereo MSCKF based VIO (e.g. S-MSCKF [3]) and VINS-Mono [2] without loop closure have similar RMSE performances [7], meaning the difference in camera numbers would not bias the comparison when adding GNSS sensors.”
BackgroundA SLAM Method Based on Multi-Robot Cooperation for Pipeline Environments Underground
Lu, D., Zhang, Y., Gong, Z., & Wu, T. (2022) · Sustainability · doi:10.3390/su142012995 · Cited by 22
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
Wei, P.-J., Yan, G., Li, Y.-K., Fang, K., Cai, X.-Y., Yang, J., & Liu, W. (2022) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros47612.2022.9981558 · Cited by 21
“They also proposed to estimate the calibration of cameraIMU transformation by visual-inertial navigation systems in an online manner [17].”
BackgroundHu, J., Zhu, F., Zhuo, D., Xu, Q., Liu, W., & Zhang, X. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3234216 · Cited by 23
“A lot of research demonstrates that the combination of vision and SINS can enhance the robustness of the navigation system [24], [25], [26].”
BackgroundHFNet-SLAM: An Accurate and Real-Time Monocular SLAM System with Deep Features
Liu, L., & Aitken, J. M. (2023) · Sensors · doi:10.3390/s23042113 · Cited by 25
“HFNet-SLAM and ORB-SLAM3 use mid-term data association to reuse previous regions, leading to low trajectory errors of 2 cm, while VINS-Mono only optimises frame states over a bounded-size sliding window, which causes a considerable drift in the trajectory.”
BackgroundMethodResultInfluentialHybrid Indoor Positioning Method of BLE and Monocular VINS-Based Smartphone
Kong, X., Wu, C. W., You, Y., Lv, Z., & Zhao, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3295010 · Cited by 28
“The vision and IMU measurements are the same as VINS-Mono [20].”
BackgroundMethodInfluentialReal-Time Dense Construction With Deep Multiview Stereo Using Camera and IMU Sensors
Liu, Y., Wu, H., Wang, C., Wei, Y., Ren, M., & Feng, T. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3295000 · Cited by 21
“Notice, VINS-Mono [25], VINS-Stereo [26], ORBSLAM3-Mono [17], and ORBSLAM3-Stereo [17] remove loop-closing, and their values are the median after ten executions on our CPU.”
BackgroundMethodInfluentialVision-IMU multi-sensor fusion semantic topological map based on RatSLAM
Liu, X., Wen, S., Pan, Z., Xu, C., Hu, J., & Meng, H. (2023) · Measurement · doi:10.1016/j.measurement.2023.113335 · Cited by 21
Yin, J., Li, T., Yin, H., Yu, W., & Zou, D. (2023) · Geo-spatial Information Science · doi:10.1080/10095020.2023.2191649 · Cited by 30
Ground-Challenge: A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots
Yin, J., Yin, H., Liang, C., Jiang, H., & Zhang, Z. (2023) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio58561.2023.10354969 · Cited by 30
“In Sequence Hall1, VINS-Mono [5] and VINS-RGBD [26] drift significantly due to ground reflection and faraway feature points.”
BackgroundMethodInfluentialVid2Cuts: A Framework for Enabling AI-Guided Grapevine Pruning
Häring, S., Folawiyo, S., Podguzova, M., Krauß, S., & Stricker, D. (2024) · IEEE Access · doi:10.1109/access.2024.3350432 · Cited by 25
“ORB-SLAM [65] and VINS-Mono [66] are examples for feature-based methods whereas LSD-SLAM [67] is based on direct image alignment.”
MethodGuan, W., Chen, P., Zhao, H., Wang, Y., & Lu, P. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202400243 · Cited by 29
“Quantitative comparison of mapping performance in terms of mean depth error (m) and the density percentage of the recovery (%), which is assessed against the dense ground truth depth.”
DVDS: A deep visual dynamic slam system
Xie, T., Sun, Q., Sun, T., Zhang, J., Dai, K., Zhao, L.-J., Wang, K., & Li, R. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125438 · Cited by 23
OmniNxt: A Fully Open-source and Compact Aerial Robot with Omnidirectional Visual Perception
Liu, P., Chen, F., Xu, Y., Ning, Y., Xu, H., & Shen, S. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802134 · Cited by 40
“Detailed information is available on our project page.”
Self-citationWang, S., Kobayashi, Y., Ravankar, A. A., Ravankar, A. A., & Emaru, T. (2019) · Sensors · doi:10.3390/s19102230 · Cited by 24
“The most intuitive way to tackle the scale-drift problem is by fusing other types of sensors to make the metrical information in visual SLAM observable, e.g., the laser distance meter [8–10], IMU [11], or stereo system [12].”
BackgroundA Binocular MSCKF-Based Visual Inertial Odometry System Using LK Optical Flow
Li, G., Yu, L., & Fei, S. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01222-z · Cited by 21
Towards UAV-Based Absolute Hierarchical Localization in Confined Spaces
Brogaard, R. Y., Zajączkowski, M., Kovač, L., Ravn, O., & Boukas, E. (2020) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr50563.2020.9292616 · Cited by 21
“There exist other VIO solutions such as the one in [18] employing similar algorithms.”
MethodVisual-Inertial RGB-D SLAM With Encoders for a Differential Wheeled Robot
Zhu, Z., Kaizu, Y., Furuhashi, K., & Imou, K. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3101370 · Cited by 21
“The well-known tightly coupled SLAM systems include robust visual-inertial odometry, which is based on the EKF [11], Open Keyframe-based Visual-Inertial SLAM (OKVIS) [12], a Monocular Visual-Inertial System (VINS-Mono) [13] and the direct method [14].”
Shin, S., Lee, E. M., Choi, J., & Myung, H. (2021) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas52745.2021.9649888 · Cited by 21
Fan, C., Zhou, W., He, X., Ying, F., Zhang, L., Wu, X., & Hu, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3187052 · Cited by 22
Wang, Z., Qin, C., & Mu, X. (2024) · Sensors · doi:10.3390/s24061937 · Cited by 24
“For instance, MonoSLAM [31], ORB-SLAM3 [32], and VINS-Mono [33] have extensively utilized them.”
BackgroundHybrid-VINS: Underwater Tightly Coupled Hybrid Visual Inertial Dense SLAM for AUV
Ou, Y., Fan, J., Zhou, C., Zhang, P., & Hou, Z. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3440515 · Cited by 20
Zhao, L., Wang, W., He, Q., Yan, L., & Li, X. (2025) · Drones · doi:10.3390/drones9010027 · Cited by 25
“Systems such as VINS-MONO [10], VINS-FUSION [11], and ORB-SLAM3 [12] exemplify these technologies.”
Fusion-Based Localization System Integrating UWB, IMU, and Vision
Deng, Z., Luo, H., Gao, X., & Liu, P. (2025) · Applied Sciences · doi:10.3390/app15126501 · Cited by 26
VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes
Wu, K., Zhang, Z., Tie, M., Ai, Z., Gan, Z., & Ding, W. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3613536 · Cited by 45
“VINS-Mono [19] and ORB-SLAM3 [14] incorporate IMU data to obtain weak scale information, ensuring localization accuracy.”
InfluentialLMVI-SLAM: Robust Low-Light Monocular Visual-Inertial Simultaneous Localization and Mapping
Hao, L., Li, H., Zhang, Q., Hu, X., & Cheng, J. T. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961635 · Cited by 25
“Our experimental results show that the algorithms are prone to pose drift or tracking failure in dim-light scenes when using VINSMono [8], VIORB [2] and OKVIS [1] algorithms to test.”
BackgroundMethodInfluentialWang, Y., Lou, Y., Zhang, Y., Song, W., Huang, F., & Tu, Z. (2021) · Remote Sensing · doi:10.3390/rs13102015 · Cited by 24
LedMapper: Toward Efficient and Accurate LED Mapping for Visible Light Positioning at Scale
Qing, L., Sun, Y., Liu, C., Liu, M., & Wang, L. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3123293 · Cited by 23
“It can be implemented by well-established VIO algorithms, such as VINS-Mono [18] and OpenVINS [30].”
MethodPhotometric Visual-Inertial Navigation With Uncertainty-Aware Ensembles
Jung, J. H., Choe, Y., & Park, C. G. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3139964 · Cited by 26
Neither Fast nor Slow: How to Fly Through Narrow Tunnels
Wang, L., Xu, H., Zhang, Y., & Shen, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3154024 · Cited by 20
“The SOTA VIO, VINS-Mono [22] is adopted for state estimation, while Fiesta [23] is adopted for the map fusion, along with Euclidean distance field (EDF) update for the planning module.”
MethodSelf-citationAn Enhanced Hybrid Visual–Inertial Odometry System for Indoor Mobile Robot
Liu, Y., Zhao, C., & Ren, M. (2022) · Sensors · doi:10.3390/s22082930 · Cited by 26
“The results of tests and experiments were compared with related mainstream algorithms S-MSCKF [10], VINS-Fusion [5,26], and OpenVINS [14].”
BackgroundMethodA SLAM-based 6DoF controller with smooth auto-calibration for virtual reality
Jiang, X., Zhu, L., Liu, J., & Song, A. (2022) · The Visual Computer · doi:10.1007/s00371-022-02530-1 · Cited by 22
“Combining with the inertia data from an Inertial Measurement Unit (IMU), Visual-Inertial SLAM systems such as VINS-Mono [34], ORB-SLAM3 [6] have been widely studied and adopted.”
A Global ArUco-Based Lidar Navigation System for UAV Navigation in GNSS-Denied Environments
Qiu, Z., Lin, D., Jin, R., Lv, J., & Zheng, Z. (2022) · Aerospace · doi:10.3390/aerospace9080456 · Cited by 20
Visual-Inertial-Aided Online MAV System Identification
Chen, C., Yang, Y., Geneva, P., Lee, W., & Huang, G. P. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982263 · Cited by 23
Auto Filmer: Autonomous Aerial Videography Under Human Interaction
Zhang, Z., Zhong, Y., Guo, J., Wang, Q., Xu, C., & Gao, F. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3231828 · Cited by 20
“VINS [22] runs in real time to estimate the state of the drone.”
BackgroundSi, L., Wang, Z., Li, J., Wei, D., & Zhao, S. (2023) · ISA Transactions · doi:10.1016/j.isatra.2023.01.010 · Cited by 20
A Robust Foot-Mounted Positioning System Based on Dual IMU Data and Ultrasonic Ranging
Qi, L., Yu, Y., Liu, Y., Gao, C., Feng, T., Hui, J., & Wang, S. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3232613 · Cited by 20
“Besides, the visual positioning method is also affected by the light intensity and motion posture and is not suitable for complex and changeable pedestrian positioning scenarios [14].”
MethodDenoising for Dynamic Vision Sensor Based on Augmented Spatiotemporal Correlation
Xu, N., Wang, L., Zhao, J., & Yao, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3249195 · Cited by 20
“We ran VINS monocular visual-inertial odometry [22] using image frames and IMU measurements from DAVIS346 to provide continuous trajectories, combined with raw event”
MethodRen, G., Wu, H., Bao, A., Lin, T., Ting, K.-C., & Ying, Y. B. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1162435 · Cited by 27
“, 2016) and visual–inertial system (VINS) (Qin et al., 2018) are all open-source tools in the ROS (Robot Operating System) community.”
MethodA Robust Visual–Inertial SLAM in Complex Indoor Environments
Zhong, M., You, Y., Zhou, S., & Xu, X. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3274702 · Cited by 20
“RESLAM is a purely visual RBGD SLAM based on edge detection, VINS-Mono is a monocular visual inertia SLAM, and VINS-RGBD is a visual inertia SLAM based on RGBD cameras.”
BackgroundMethodInfluentialSafe Maneuvering Planning for Flights in Complex Environments
Liu, S., Guo, K., Yu, X. Y., Ma, L., Xie, L., & Guo, L. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3285995 · Cited by 21
“VINS [33], a robust visual-inertial odometry framework, is adopted to estimate the pose of the quadrotor in real time.”
MethodRSPT: Reconstruct Surroundings and Predict Trajectory for Generalizable Active Object Tracking
Zhong, F., Bi, X., Zhang, Y., Zhang, W., & Wang, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25482 · Cited by 39
Low-Latency Visual-Based High-Quality 3-D Reconstruction Using Point Cloud Optimization
Chi, P., Wang, Z., Liao, H., Li, T., Zhan, J., Wu, X., Tian, J., & Zhang, Q. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3297232 · Cited by 21
“[13] proposed the VINS-Mono method based on a monocular camera and IMU to achieve a highly robust state estimation.”
MethodDUET: Improving Inertial-Based Odometry via Deep IMU Online Calibration
Liu, H., Wei, X., Perusquía-Hernández, M., Isoyama, N., Uchiyama, H., & Kiyokawa, K. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3306833 · Cited by 20
“For TUM-VI Uncali test sequences (No.5–7), the VINS-Mono failed with raw IMU data.”
MethodLi, S., Li, X., Zhou, Y., Wang, S., & Chen, S. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3319004 · Cited by 20
“Among these, the most representative works were VINS-Mono [43] and its improved VINS-Fusion [5], both of which have joint Camera-IMU spatial/temporal calibration function.”
MethodVIEW: Visual-Inertial External Wrench Estimator for Legged Robot
Kang, J., Kim, H., & Kim, K.-S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3322646 · Cited by 26
“Followings are total objective function for obtaining a maximum posteriori estimate of χ : This includes the prior ( r p ), inertial ( r I ), visual ( r C ), forward kinematics ( r FK ) residuals which were defined in [20] and [24].”
BackgroundMethodLiDAR-IMU Tightly-Coupled SLAM Method Based on IEKF and Loop Closure Detection
Pan, H., Liu, D., Ren, J., Huang, T., & Yang, H. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3357536 · Cited by 23
“Another approach is the tightly-coupled method that directly fuses LiDAR information and IMU data by joint optimization, which can be further divided into optimization-based [27], [28] and extended KF-based approaches [4], [29].”
MethodZhao, X., Wen, C., Prakhya, S. M., Yin, H., Zhou, R., Sun, Y., Xu, J., Bai, H., & Wang, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3370762 · Cited by 20
“…datasets, and we deployed our proposed system to compare with competing state-of-the-art systems, including: 1) visual–inertial odometry: VINS-MONO [42]; 2) lidar-only odometry: LOAM [58]; 3) lidar–inertial odometry: LIO-SAM [59]; and 4) lidar– visual–inertial odometry: LVI-SAM [6] and R3LIVE [8],…”
BackgroundLiu, D., Wu, J., Du, Y., Zhang, R., & Cong, M. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3385825 · Cited by 26
“VINS-Mono [3] develops a low-computation-cost VIO framework that utilizes the DBoW2 bag-of-words (BoWs) library [9] and 4DoF graph optimization techniques.”
BackgroundMethodWang, Y., & Boyle, D. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3432405 · Cited by 28
“In our setup, we integrate a loop detection process into VID-Fusion [20], following the methodology outlined in [91], to enhance measurement accuracy.”
Point–Line Visual–Inertial Odometry With Optimized Line Feature Processing
Si, H., Yu, H., Chen, K., & Yang, W. T. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3436114 · Cited by 20
“For evaluation, we compare with several state-of-the-art methods, including typical VIO systems, such as OKVIS [43] and ROVIO [44]; 5-years-ago methods, such as VINS-Mono [37] and PL-VIO [24]; and more recent methods, such as PL-VINS [26] and EPLF-VINS [11].”
BackgroundMethodLanguage-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding
Kassab, C., Mattamala, M., Zhang, L., & Fallon, M. F. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610341 · Cited by 38
“3) Full System Evaluation: We conducted a comparison using LEXIS as a complete SLAM system, benchmarked against two state-of-the-art alternatives: ORB-SLAM3 [36] and VINS-Fusion [37].”
MethodCaltech Aerial RGB-Thermal Dataset in the Wild
Lee, C., Anderson, M., Ranganathan, N., Zuo, X., Do, K., Gkioxari, G., & Chung, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73036-8_14 · Cited by 33
MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Maps
Wu, H., Zhang, Z., Lin, S., Mu, X., Zhao, Q., Yang, M., & Qin, T. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802757 · Cited by 45
“By leveraging prior built maps, such as 3D point clouds and distinctive visual features, LiDAR-based [1] and visual-based [2, 3] SLAM methods can be used for localization.”
Self-citationVLIP: Tightly Coupled Visible-Light/Inertial Positioning System to Cope With Intermittent Outage
Qin, C., & Zhan, X. (2018) · IEEE Photonics Technology Letters · doi:10.1109/lpt.2018.2883345 · Cited by 21
“They are modeled as in [14]:”
MethodRobust Stereo Visual-Inertial Odometry Using Nonlinear Optimization
Ma, S., Bai, X., Wang, Y., & Fang, R. M. (2019) · Sensors · doi:10.3390/s19173747 · Cited by 22
Visual SLAM with RGB-D Cameras
Jin, Q., Liu, Y., Man, Y., & Li, F. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865270 · Cited by 22
“During the period when the camera data is invalid, we can realize a better motion estimation with IMU than pure visual RGB-D SLAM [55].”
MethodJoint Spatial-Temporal Optimization for Stereo 3D Object Tracking
Li, P., Shi, J., & Shen, S. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00691 · Cited by 26
Self-citationCollaborative Visual Inertial SLAM for Multiple Smart Phones
Liu, J., Liu, R., Chen, K., Zhang, J., & Guo, D. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561946 · Cited by 21
“Table IV also shows that the fusion accuracy of the proposed method has achieved similar results to VINS-Mono, and the benefits of sharing information obtained by multiple agents to improve accuracy during collaboration.”
InfluentialDistributed Visual-Inertial Cooperative Localization
Zhu, P., Geneva, P., Ren, W., & Huang, G. P. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636031 · Cited by 26
Unsupervised Learning of Monocular Depth and Ego-Motion in Outdoor/Indoor Environments
Gao, R., Xiao, X., Xing, W., Li, C., & Liu, L. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3151629 · Cited by 23
“There are many famous VIO algorithms which have fused vision and inertial data with either filters or optimization frameworks to improve the tracking accuracy, e.g., MSCKF [22], VINS [23], ROVIO [24], and OKVIS [25].”
MethodWu, D., Zhong, X., Peng, X., Hu, H., & Liu, Q. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3205687 · Cited by 22
“There are four types of factors in the factor graph: re-projection factor between two frames, the re-projection factor between the left and right camera, the pre-integration factor and the marginalization factor, and their detailed definition and construction can be found at [16], [33].”
BackgroundMethodZhao, S., & Fang, Z. (2018) · Sensors · doi:10.3390/s18103339 · Cited by 21
He, M., Chen, C., Liu, J., Li, C., Lyu, X., Huang, G. P., & Meng, Z. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3441491 · Cited by 26
“In order to illustrate the results of relative pose estimation on AerialVL, we implement widely used visual odometry and visual inertial odometry methods, including ORB-SLAM2 [43], ORB-SLAM3 [29] and VINS-Mono [28].”
MethodRUSSO: Robust Underwater SLAM With Sonar Optimization Against Visual Degradation
Pan, S., Hong, Z., Hu, Z., Xu, X., Lu, W., & Hu, L. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3550730 · Cited by 19
“In all experiments, the state-of-the-art underwater SLAM algorithm SVIn2 [18] and VIO algorithm VINS-Fusion [28] are used for comparison.”
De-Skewing LiDAR Scan for Refinement of Local Mapping
He, L., Jin, Z. H., & Gao, Z. (2020) · Sensors · doi:10.3390/s20071846 · Cited by 19
“Similar to [11,28], we combined LiDAR odometry and IMU motions to solve the external parameters first which were optimized in ceres solver later.”
MethodOnline Localization with Imprecise Floor Space Maps using Stochastic Gradient Descent
Li, Z., Ang, M. H., & Rus, D. L. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340793 · Cited by 27
“Mono vision with a feature detector [12] or Stereo vision generating a particle swarm [13] can be used for localization as well.”
BackgroundZhou, Z., & Wu, J. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3067659 · Cited by 19
“[55] T. Qin, P. Li, and S. Shen, “VINS-mono: A robust and versatile monocular visual-inertial state estimator,” IEEE Trans.”
BackgroundThe YTU dataset and recurrent neural network based visual-inertial odometry
Gürtürk, M., Yusefi, A., Aslan, M. F., Soycan, M., Durdu, A., & Masiero, A. (2021) · Measurement · doi:10.1016/j.measurement.2021.109878 · Cited by 22
Lyu, Y., Yuan, S., & Xie, L. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3142663 · Cited by 21
Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions
Bégin, M.-A., & Hunter, I. W. (2022) · Sensors · doi:10.3390/s22030835 · Cited by 19
“Feature-based algorithms, such as ORB-SLAM [27] and VINS-Fusion [28], for instance, are more strongly affected by motion blur and less affected by noise than methods such as DSO [29], which minimizes photometric error.”
MethodGu, Z., Gong, Z., Tao, B., Yin, Z., & Ding, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3205952 · Cited by 20
“There are two main forms, namely recursive filtering [19], [20], [21] and batch optimization [22], [23], [24].”
BackgroundMethodLee, J.-C., Chen, C.-C., Shen, C.-T., & Lai, Y. (2022) · Sensors · doi:10.3390/s22249654 · Cited by 19
“VINS-Mono is a robust and nonlinear visual–inertial state estimator that utilizes IMU preintegration, sliding window, and global optimization.”
MethodInfluentialStereo Visual Odometry With Automatic Brightness Adjustment and Feature Tracking Prediction
Yin, H., Liu, P. X., & Zheng, M. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3223070 · Cited by 19
“In order to constrain the computational complexity, we apply a sliding window optimization [2], [3], [31] and marginalize the oldest states, which are converted into a prior by Schur complement [32], [33].”
MethodA Unified Initial Alignment Method of SINS Based on FGO
Zhou, H., & Ye, X. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3229335 · Cited by 22
“Recently, batch estimator FGO has been widely used in SLAM and integration navigation [10], [11], [12], [13], [14].”
MethodA Lightweight Real-Time 3D LiDAR SLAM for Autonomous Vehicles in Large-Scale Urban Environment
Lu, G., Yang, H. B., Li, J., Kuang, Z., & Yang, R. (2023) · IEEE Access · doi:10.1109/access.2023.3241800 · Cited by 20
“It generally can be classified by visual SLAM [5], [6], [7] and LiDAR SLAM [8], [9], [10], [11], [12] according to sensors (camera, LiDAR) employed.”
MethodChiang, K., Huang, C.-H., Chang, H.-W., Lin, C.-X., Tsai, M.-L., Zeng, J.-C., & Hung, M.-C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3265267 · Cited by 20
“In [39], VINS-Mono is a very accurate and robust”
BackgroundMethodInfluentialS-VIO: Exploiting Structural Constraints for RGB-D Visual Inertial Odometry
Gu, P., & Meng, Z. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3270033 · Cited by 22
“DigitalObjectIdentifier 10.1109/LRA.2023.3270033 Nowadays, many excellent VIO/SLAM algorithms have been proposed and are shown to achieve high localization accuracy [1], [2], [3], [4].”
BackgroundMethodInfluentialGao, Y., Bai, C., & Quan, Q. (2023) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.6858 · Cited by 19
“The finishing line approaching term u1,i in (25) has a invariable norm ‖‖u1,i‖‖ = vm.”
BackgroundDAMS-LIO: A Degeneration-Aware and Modular Sensor-Fusion LiDAR-inertial Odometry
Han, F., Zheng, H., Huang, W., Xiong, R., Wang, Y., & Jiao, Y. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160971 · Cited by 30
“We compare our method with other vision-based methods (VINS-MONO [31]), LiDAR-based method (LIO-SAM [32], Fast-LIO2), and sensor-fusion methods (LVI-SAM [8], LOCUS [11]).”
MethodLog-GPIS-MOP: A Unified Representation for Mapping, Odometry, and Planning
Wu, L., Lee, K. M. B., Gentil, C. L., & Vidal‐Calleja, T. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3296982 · Cited by 30
Monocular depth estimation using self-supervised learning with more effective geometric constraints
Xiong, M., Zhang, Z., Liu, J., Zhang, T., & Xiong, H. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107489 · Cited by 19
YDD-SLAM: Indoor Dynamic Visual SLAM Fusing YOLOv5 with Depth Information
Cong, P., Liu, J., Li, J., Xiao, Y., Chen, X., Feng, X., & Zhang, X. (2023) · Sensors · doi:10.3390/s23239592 · Cited by 23
“The related algorithms include the monocular visual–inertial system and GNSS–visual–inertial system algorithms proposed by Shen et al. [7,8] and the ORB-SLAM [9–11] series of algorithms based on ORB [12] feature points proposed by the University of Zaragoza in Spain.”
MethodHu, X., Zheng, L., Wu, J., Geng, R., Yu, Y., Wei, H., Tang, X., Wang, L., Jiao, J., & Liu, M. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3362902 · Cited by 36
“Inspired by previous gravity and ZUPT work [26], [31], [33], [34], we implement the gravity factor and no motion factor to handle these frequently occurred static scenes.”
Wang, Z., Li, X., Zhang, Y., & Huang, P. (2024) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2024.3366695 · Cited by 21
“Moreover, visual-aided inertial navigation systems [3], [4], [5] usually degenerate in large-scale environments due to a lack of optical par-allaxes and inertial incentives [6].”
BackgroundPR-SLAM: Parallel Real-Time Dynamic SLAM Method Based on Semantic Segmentation
Zhang, H., Peng, J., & Yang, Q. F. (2024) · IEEE Access · doi:10.1109/access.2024.3373308 · Cited by 23
“Many visual SLAM algorithms based on this framework primarily operate in static environments, such as ORB-SLAM3 [2], DSO [3], VINS-Mono [4], SVSF-SLAM [6], and LSD-SLAM [5].”
BackgroundRadarize: Enhancing Radar SLAM with Generalizable Doppler-Based Odometry
Sie, E., Wu, X., Guo, H., & Vasisht, D. (2024) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3643832.3661871 · Cited by 24
“The scans of the environment can come from different sensor types such as LIDARs [46, 47], cameras [2, 38, 39, 44], acoustic sensors [6, 7].”
BackgroundRobust Indoor Localization with Ranging-IMU Fusion
Jiang, F., Caruso, D., Dhekne, A., Qu, Q., Engel, J. J., & Dong, J. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611274 · Cited by 24
“Traditionally, accurate indoor 6 Degrees-of-Freedom (DoF) localization is performed using Visual-Inertial Odometry (VIO) [1], and visual Simultaneous Localization and Mapping (SLAM) [2], [3], [4], in which camera images are the main source of information.”
MethodDetection-first tightly-coupled LiDAR-Visual-Inertial SLAM in dynamic environments
Xu, X., Hu, J., Zhang, L., Cao, C., Yang, J. J., Ran, Y., Tan, Z., Xu, L., & Luo, M. (2024) · Measurement · doi:10.1016/j.measurement.2024.115506 · Cited by 20
Robust Collaborative Visual-Inertial SLAM for Mobile Augmented Reality
Pan, X., Huang, G., Zhang, Z., Li, J., Bao, H., & Zhang, G. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456152 · Cited by 28
“Recent VI-SLAM systems, including VINS-Mono [31] and VINS-Fusion, adopting keyframe-based bundle adjustment and sliding window techniques in the frontend, as well as pose graph optimization (PGO) based loop closure in the backend to mitigate drift accumulation, thereby achieving better accuracy.”
InfluentialD3FlowSLAM: Self-supervised dynamic SLAM with flow motion decomposition and DINO guidance
Yu, X., Ye, W., Guo, X., Ming, Y., Li, J., Bao, H., Cui, Z., & Zhang, G. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133023 · Cited by 37
SE(2)-Constrained Visual Inertial Fusion for Ground Vehicles
Fan, Z., & Liu, Y. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2873055 · Cited by 21
“[13] also proposed an open-source versatile visual inertial estimator similar to [12].”
BackgroundNguyen, T. Q., Mann, G. K. I., Vardy, A., & Gosine, R. G. (2019) · Journal of Dynamic Systems Measurement and Control · doi:10.1115/1.4042951 · Cited by 23
Zhang, Z., Zhao, R., Liu, E., Yan, K., Ma, Y., & Xu, Y. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.03.010 · Cited by 19
Hu, J., Yang, M. Z., Xu, H., He, Y., & Wang, C. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917529 · Cited by 19
Multi-sensor Fusion Towards VINS: A Concise Tutorial, Survey, Framework and Challenges
Dinh, N. V., & Kim, G.-W. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-26 · Cited by 25
Indoor Localization Based on VIO System and Three-Dimensional Map Matching
Zhang, J., Ren, M., Wang, P., Meng, J., & Mu, Y. (2020) · Sensors · doi:10.3390/s20102790 · Cited by 19
Real-Time Multi-SLAM System for Agent Localization and 3D Mapping in Dynamic Scenarios
Alliez, P., Bonardi, F., Bouchafa, S., Didier, J.-Y., Hadj-Abdelkader, H., Muñoz, F. I. I., Kachurka, V., Rault, B., Robin, M., & Roussel, D. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340646 · Cited by 25
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.