The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Visual SLAM: Why filter?
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“MAP estimation has been proven to be more accurate and efficient than original approaches for SLAM based on nonlinear filtering.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [236]
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
Parallel 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
MonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959
Self-citationiSAM2: Incremental smoothing and mapping using the Bayes tree
Kaess, M., Johannsson, H., Roberts, R., Ila, V., Leonard, J. J., & Dellaert, F. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364911430419 · Cited by 1,362
Adaptive relative bundle adjustment
Sibley, G., Mei, C., Reid, I., & Newman, P. (2009) · Robotics: Science and Systems V · doi:10.15607/rss.2009.v.023 · Cited by 139
Research works printed but not linked: 15
- Azarbayejani, 1995, Recursive estimation of motion, structure, and focal length, IEEE Trans. Pattern Anal. Mach. Intell., 17, 562, 10.1109/34.387503 · DOI
- Bell, 1993, The iterated Kalman filter update as a Gauss–Newton method, IEEE Trans. Autom. Control., 38, 294, 10.1109/9.250476 · DOI
- Chiuso, 2002, Structure from motion causally integrated over time, IEEE Trans. Pattern Anal. Mach. Intell., 24, 523, 10.1109/34.993559 · DOI
- Chli, 2009, Active matching for visual tracking, Robot. Auton. Syst., 57, 1173, 10.1016/j.robot.2009.07.010 · DOI
- Civera, 2008, Inverse depth parametrization for monocular SLAM, IEEE Trans. Rob., 24, 932, 10.1109/TRO.2008.2003276 · DOI
- Civera, 2010, 1-point RANSAC for EKF filtering. Application to real-time structure from motion and visual odometry, J. Field Rob., 27, 609, 10.1002/rob.20345 · DOI
- Dyer, 1969, Extension of square-root filtering to include process noise, J. Optim. Theory Appl., 3, 444, 10.1007/BF00929358 · DOI
- E. Eade. Monocular Simultaneous Localisation and Mapping. PhD thesis, University of Cambridge, 2008.
- Kaess, 2008, iSAM: incremental smoothing and mapping, IEEE Trans. Rob., 24, 1365, 10.1109/TRO.2008.2006706 · DOI · Paper page
- Konolige, 2008, FrameSLAM: from bundle adjustment to real-time visual mapping, IEEE Trans. Rob., 24, 1066, 10.1109/TRO.2008.2004832 · DOI
- Mahony, 2002, The geometry of the Newton method on non-compact Lie groups, J. Glob. Optim., 23, 309, 10.1023/A:1016586831090 · DOI
- Mei, 2011, RSLAM: a system for large-scale mapping in constant-time using stereo, Int. J. Comput. Vision, 94, 198, 10.1007/s11263-010-0361-7 · DOI
- Neira, 2001, Data association in stochastic mapping using the joint compatibility test, IEEE Trans. Robot. Autom., 17, 890, 10.1109/70.976019 · DOI · Paper page
- Nistér, 2004, An efficient solution to the five-point relative pose problem, IEEE Trans. Pattern Anal. Mach. Intell., 26, 756, 10.1109/TPAMI.2004.17 · DOI · Paper page
- Pinies, 2008, Large scale SLAM building conditionally independent local maps: application to monocular vision, IEEE Trans. Rob., 24, 1094, 10.1109/TRO.2008.2004636 · DOI
Cited by
Sorted by citations
Items 301–400 of 426
NavigationNet: A Large-scale Interactive Indoor Navigation DatasetPreprint
Huang, H., Shen, Y., Sun, J., & Lu, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08374 · Cited by 4
Em-SLAM: a Fast and Robust Monocular SLAM Method for Embedded Systems
Wu, Y.-R., Li, Z.-K., Palaiahnakote, S., & Lu, T. (2018) · International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545173 · Cited by 3
“As defined in [11], the best way to estimate pose is to construct a probability model with the structure of a probabilistic Markov chain, where si and fj are variables, and li,j are represented by edges in the chain graph.”
BackgroundMethodAddressing Data Association in Maximum Likelihood SLAM with Random Finite Sets
Inostroza, F., & Adams, M. (2018) · Fusion · doi:10.23919/icif.2018.8455273 · Cited by 3
“cl obtain a Maximum Likelihood (ML) solution [8, 9].”
MethodRobust and fast mapping based on direct methods
Wang, P., Gao, C., Guo, W., Li, M.-T., Zha, F.-S., & Cong, Y. (2017) · International Conference on Advanced Robotics and Mechatronics · doi:10.1109/icarm.2017.8273229 · Cited by 3
“That keyframebased methods are more accurate compared to filtering is proved in [4].”
MethodRobust visual-inertial SLAM: combination of EKF and optimization method
Quan, M.-X., & Piao, S.-H. (2017) · arXiv.org · doi:10.48550/arxiv.1706.03648 · Cited by 3
“In [1], it was shown that nonlinear optimization-based approaches provide better accuracy than filtering approaches by its capability to relinearize the state at each iteration, therefore avoiding integrated error from linearization, however it leads to higher computational demands.”
BackgroundMethodApplication of a Nonlinear Recursive Visual-Depth Observer Using UH60 Flight Data
Keshavan, J., Escobar-Alvarez, H., Dimble, K. D., Humbert, J., Goerzen, C., & Whalley, M. (2016) · doi:10.2514/1.g001450 · Cited by 3
Multiple Master-Slave FPGA Architecture of a Stereo Visual Odometry
Chien, C.-H., Hsu, C., & Chien, C.-J. (2021) · IEEE Access · doi:10.1109/access.2021.3098856 · Cited by 3
“Although a good performance was given, [12] used multi-state constraint Kalman filter (MSCKF) to estimates poses, which contributes inferior performances compared to non-filtering family, as stated in [13].”
MethodRobust 3D Visual Localization Based on RTABmaps
Florido, A. M., Montero, F. R., & Plaza, J. M. (2018) · Advances in computer and electrical engineering book series · doi:10.4018/978-1-5225-5628-2.ch001 · Cited by 3
Direct Pose Estimation and Refinement
Alismail, H. (2016) · doi:10.1184/r1/6715961.v1 · Cited by 3
“[349], where it was concluded that BA is more efficient per unit of computation.”
BackgroundInfluentialXiao, G., Li, P., Li, T., Zhang, B., Xiao, Z., Ma, H.-L., & Xiao, K. (2026) · Geodesy and Geodynamics · doi:10.1016/j.geog.2026.03.004 · Cited by 2
Camera Pose Refinement for Precise BIM Alignment in Mixed Reality Visualization
Einizinab, S., Khoshelham, K., Winter, S., & Christopher, P. (2025) · Journal of computing in civil engineering · doi:10.1061/jccee5.cpeng-6439 · Cited by 2
Combining the SLAM back and front ends with a joint vector-set distribution
Inostroza, F., & Adams, M. D. (2025) · Int. J. Robotics Res. · doi:10.1177/02783649241303770 · Cited by 2
“…tracking community, the robotics SLAM community has moved away from fi ltering-based solutions to the batch estimation approach, which uses nonlinear optimization methods to obtain either a Maximum Likelihood (ML) or a maximum a posteriori (MAP) solution (Kaess et al., 2012; Strasdat et al., 2012).”
Enhancing Real-Time Visual SLAM with Distant Landmarks in Large-Scale Environments
Dou, H., Zhao, X., Liu, B., Jia, Y.-H., Wang, G., & Wang, C. (2024) · Drones · doi:10.3390/drones8100586 · Cited by 2
Catadioptric omnidirectional thermal odometry in dynamic environment
Wu, Y., Wang, L., Zhang, L., Han, X., Zheng, D., Wang, S., Li, Y., & Cai, Y. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.07.021 · Cited by 3
GraSS: Graph Neural Networks for Loop Closure Detection with Semantic and Spatial Assistance
Lu, S., Peng, Z., Xiao, Z.-L., Yan, B., Lin, S.-S., Yu, S., & He, D. (2024) · International Symposium on Circuits and Systems · doi:10.1109/iscas58744.2024.10557928 · Cited by 2
“The pose estimation of Visual Odometry (VO) [4] is a recursive process, where errors can accumulate and result in trajectory drift.”
BackgroundAdaptive Outlier Thresholding for Bundle Adjustment in Visual SLAM
Fontan, A., Civera, J., & Milford, M. (2024) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra57147.2024.10610433 · Cited by 2
“BA-based V-SLAM, involving batch optimization over several spatially distributed keyframes, has shown a higher accuracy than filtering-based methods with equivalent computational budget [34].”
MethodEnhancing Autonomous Navigation: A Visual SLAM Approach
Paul, S., Kumar, C. H., & Bongale, C. A. (2024) · Journal of Physics, Conference Series · doi:10.1088/1742-6596/2748/1/012008 · Cited by 2
“According to Strasdat et al. [9] to diminish the computing overload filtering on basis of keyframes can be used.”
MethodImmediate Pose Recovery Method for Untracked Frames in Feature-Based SLAM
Dou, H., Wang, Z.-H., Wang, C., & Zhao, X. (2024) · Italian National Conference on Sensors · doi:10.3390/s24030835 · Cited by 2
Hardware Acceleration for SLAM in Mobile Systems
Fan, Z., Hao, Y.-F., Zhi, T., Guo, Q., & Du, Z. (2023) · Journal of Computer Science and Technology · doi:10.1007/s11390-021-1523-5 · Cited by 3
LL-SLAM: Lightweight Loosely-Coupled Visual-Inertial SLAM
Wang, A., Zhong, R., Zheng, K., & Fang, H. (2023) · Cybersecurity and Cyberforensics Conference · doi:10.23919/ccc58697.2023.10239955 · Cited by 2
A Comprehensive Introduction of Visual-Inertial Navigation
Ning, Y. (2023) · arXiv.org · doi:10.48550/arxiv.2307.11758 · Cited by 2
“Strasdat et al.[141][142] indicate that the computational cost of filter-based methods scales poorly with the number of landmarks.”
BackgroundPRISM: Probabilistic Real-Time Inference in Spatial World Models
Mirchev, A., Kayalibay, B., Agha, A., van der Smagt, P., Cremers, D., & Bayer, J. (2022) · Conference on Robot Learning · doi:10.48550/arxiv.2212.02988 · Cited by 2
“[3, 4, 5, 70, 71, 72, 73]), primarily due to scalability concerns [6, 74].”
BackgroundVision-based Velocimetry over Unknown Terrain with a Low-Noise IMU
Conway, D., Trawny, N., & Martin, A. M. S. (2022) · AIAA SCITECH 2022 Forum · doi:10.2514/6.2022-1710 · Cited by 2
Stereo visual odometry with velocity constraint for ground vehicle applications
Liu, F., Sarvrood, Y. B., Liu, Y., & Gao, Y. (2021) · Journal of navigation · doi:10.1017/s037346332100028x · Cited by 2
“Key-frame-based bundle adjustment optimisation (Strasdat et al., 2012; Campos et al., 2020) and loop detection and relocalisation (Gálvez-López and Tardos, 2012; Campos et al.”
MethodVisual SLAM Location Methods Based on Complex Scenes: A Review
Zhang, H.-X., & Peng, J.-S. (2020) · International Conference on Adaptive and Intelligent Systems · doi:10.1007/978-3-030-57881-7_43 · Cited by 2
A Dataset for Evaluating Multi-spectral Motion Estimation Methods
Dai, W.-C., Zhang, Y., Chen, S., Sun, D., & Kong, D. (2020) · arXiv.org · doi:10.48550/arxiv.2007.00622 · Cited by 2
“These motion estimation methods can be categorized into filter-based [11] and factor-graphoptimization-based methods [12].”
MethodMOZARD: Multi-Modal Localization for Autonomous Vehicles in Urban Outdoor Environments
Schaupp, L., Pfreundschuh, P., Bürki, M., Cadena, C., Siegwart, R., & Nieto, J. I. (2020) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros45743.2020.9341400 · Cited by 2
High-Precision Visual Localization and Dense Mapping Based on Visual SLAM for Indoor Environment
Yu, Z., Zhou, T., & Su, Y. (2019) · 2019 IEEE 5th International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc47050.2019.9064221 · Cited by 2
“It is widely accepted that nonlinear optimization can achieve better results under the same amount of calculation [11].”
BackgroundMarangi, A., Olia, K., Daneshgaran, F., Bruno, N., Lizzio, F., & Mondin, M. (2019) · International Symposium Advanced Electrical and Communication Technologies · doi:10.1109/isaect47714.2019.9069727 · Cited by 2
“As literature survey suggests [12, 13], nowadays SLAM techniques are focused towards keyframe based algorithms and bundle adjustment (BA) local optimization.”
BackgroundRobust Linear-Complexity Approach to Full SLAM Problems: Stochastic Variational Bayes Inference
Jiang, X.-Y., Yu, H., Hoy, M., & Dauwels, J. (2019) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2019.8891361 · Cited by 2
“Unfortunately, such remedies might jeopardize the accuracy of the estimation [11].”
BackgroundNguyen, D. (2018) · doi:10.70675/8ac770b2zd919z4d04z85f0z4e610646fa46 · Cited by 2
“[107] compared filter and keyframe based VSLAM demonstrating that the latter achieves a better balance between computational cost and precision.”
BackgroundORB-SLAM based humanoid robot location and navigation system
He, Z.-C., Leng, X.-K., & Zha, F.-S. (2018) · doi:10.21595/vp.2018.19690 · Cited by 2
“The history of the research on SLAM has been over 30 years, and the models for solving SLAM problems can be divided into two categories: filtering based methods and graph optimization based methods [3].”
MethodVisual Loop Closure Detection with Scene Mutual Information for Mobile Robot
Liu, N., & Wu, J.-J. (2014) · Journal of Computers · doi:10.4304/jcp.9.11.2642-2647 · Cited by 2
Optimization-Based Monocular 3D Object Tracking via Combined Ellipsoid-Cuboid Representation
Kim, G. C., Jang, Y., & Kim, H. J. (2024) · IEEE Access · doi:10.1109/access.2024.3438162 · Cited by 2
“Studies in SLAM literature [34], [35] have consistently shown that nonlinear optimization methods outperform filtering methods in terms of estimation accuracy.”
MethodGriguletskii, M., Shipitko, O., Abramov, M., Pristanskiy, E., Kibalov, V., & Grigoryev, A. (2023) · IEEE Access · doi:10.1109/access.2023.3247503 · Cited by 2
“However, filter-based localization algorithms are still widely used in industry and researches [17], [18] due to fast computations and comparable (to Graph-based algorithms) level of accuracy [19], [20].”
Train unmanned driving algorithm based on reasoning and learning strategy
Liu, H. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-822830-2.00003-9 · Cited by 2
Nakamura, H., Sonobe, T., Toda, H., Fujisawa, N., Taketomi, T., Plopski, A., Sandor, C., & Kato, H. (2019) · Journal of the Institute of Positioning Navigation and Timing of Japan · doi:10.5266/ipntj.10.1 · Cited by 2
“3 次元構造の推定精 度向上には特徴点の数を増加させることが重要であり,そのた めには EKF のようなフィルタリングによる手法よりもキーフレー ムを用いた BA の方が優位であることが先行研究[12]によって 示されている.”
Fast Automatic Differentiation for Large Scale Bundle Adjustment
Shen, Y., & Dai, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2812173 · Cited by 2
“BA can be superior to KF and PF in terms of accuracy [6], [7], but with much more computation.”
BackgroundVariation Based Dense 3D Reconstruction
Painer, S. (2016) · BestMasters · doi:10.1007/978-3-658-12698-8 · Cited by 2
“There is also the approach of Simultaneous Localization and Mapping (SLAM) which is better suited for real-time applications [1, 2, 23].”
BackgroundFast and Robust $ell_1$-averaging-based Pose Estimation for Driving Scenarios
Ros, G., Sappa, A., Ponsa, D., López, A., & Guerrero, J. (2013) · British Machine Vision Conference · doi:10.5244/c.27.86 · Cited by 2
Why does Deep Learning Improve Visual SLAM?Preprint
Cioffi, G., & Scaramuzza, D. (2026) · arXiv.org · doi:10.48550/arxiv.2607.06023 · Cited by 1
“Optimization-based systems, such as OKVIS [39] and VINS-Mono [40], allow for the re-processing of past states through bundle adjustment, offering superior consistency and accuracy [41].”
Kamath, P. A., Reddy, K. L. R., Thunhaal, S. T., Arjunan, B., & Singh, P. (2025) · International Conference on Robotics and Mechatronics · doi:10.1109/icrm66809.2025.11349014 · Cited by 1
Is Iteration Worth It? Revisit its Impact in Sliding-Window VIO
Chen, C., Peng, Y., & Huang, G.-Q. P. (2025) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra55743.2025.11127352 · Cited by 1
“Strasdat et al. [29] analyzed the trade-offs between filtering and BA but focused solely on visual SLAM.”
Novel Orb Slam System for Robot Navigation in Real-Time
Chakraborty, S., Verma, A., Hartman, A., & Ho, N. T. (2025) · International Conference on Multimodal Interaction · doi:10.1109/icmi65310.2025.11141249 · Cited by 1
“Methodologies based on keyframes offer superior accuracy compared to filtering at equivalent computational expense [8].”
FLAF: Focal Line and Feature-Constrained Active View Planning for Visual Teach and Repeat
Fu, C., Chen, W., Xu, W.-J., & Zhang, H. (2024) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra55743.2025.11128785 · Cited by 1
A monocular inertial UAV SLAM algorithm leveraging feature clustering
Xia, Y., Li, H., Pan, G., Xue, W., Fan, Z.-C., Qi, N.-M., & Huo, M.-Y. (2024) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc62065.2024.00020 · Cited by 1
“Finally, the Jacobian matrix is used for optimization: The significance of each partial derivative in the Jacobian matrix is elaborated in reference [3].”
MethodAppearance-invariant Visual Localization for Long-term Navigation
Su, Z.-R., Lin, X., He, L., Xu, Z.-H., & Zhou, X.-F. (2024) · 2024 10th International Conference on Electrical Engineering, Control and Robotics (EECR) · doi:10.1109/eecr60807.2024.10607284 · Cited by 1
“…Localization and Mapping (SLAM) is the paradigm of mapping an unseen environment and has achieved significant advancement in the past decades [1]–[3]; however, most existing works pay more attention to fusing varied visual features (e.g. point [4]–[6], line segment [7], plane [8], etc) or…”
BackgroundA TEST ON COLLABORATIVE VISION AND UWB-BASED POSITIONING
Gurturk, M., Masiero, A., Toth, C., Dabove, P., Pietra, V. D., Vettore, A., Guarnieri, A., Cortesi, I., Pellis, E., & Soycan, M. (2023) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlviii-1-w2-2023-1185-2023 · Cited by 1
Monocular Vision for 3D Distance Computation in Augmented Reality Applications
Martínez-Díaz, S. (2023) · IEEE Symposium Series on Computational Intelligence · doi:10.1109/ssci52147.2023.10371849 · Cited by 1
“In the paper of Strasdat et al [10] is showed that keyframe-based techniques can be more accurate than filtering methods, with a similar computational cost.”
MethodEfficient 6-DoF camera pose tracking with circular edges
Tang, F.-L., Wu, S., Qian, Z., & Wu, Y. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103767 · Cited by 1
Roil, M. K., & Prakash, A. (2023) · 2023 IEEE 8th International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct57861.2023.10126239 · Cited by 1
Distributed Block Coordinate Moving Horizon Estimation for 2D Visual-Inertial-Odometry SLAM
Flayac, É., & Shames, I. (2023) · IEEE Conference on Decision and Control · doi:10.1109/cdc49753.2023.10384137 · Cited by 1
“EKFs are cheap and simple to implement but suffer from consistency issues due to successive lineari-sations and from bad scalability with respect to the number of landmarks considered in the environment [23], [7], [13].”
BackgroundMethodA Compensation Method for Lost Trajectories of ORB-SLAM3 with DROID-VO
Liu, K.-R., Fan, Y., Su, J., Wu, L., & Zhang, K.-X. (2023) · 2023 3rd International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr56747.2023.10194078 · Cited by 1
“In addition, the filtering method was prone to accumulated drift when it ran for a long time, so it was quickly replaced by BA(Bundle Adjustment) based on keyframes[12].”
MethodResearch on Extraction of RGB feature points for visual SLAM
Wang, Y., Liang, W., & Zhao, Y. (2021) · International Conference on Control and Intelligent Robotics · doi:10.1145/3473714.3473761 · Cited by 1
He, Y.-Q., Dai, B., Xu, W.-L., Yang, L.-Y., & Gu, F. (2020) · Scientia Sinica Informationis · doi:10.1360/ssi-2019-0237 · Cited by 1
Whole scene reconstruction of medical service robots fused with key frame focus stack images
Hu, Y.-Z., Wang, Y.-J., & Wang, S. (2020) · International Symposium on Artificial Intelligence in Medical Sciences · doi:10.1145/3429889.3430077 · Cited by 1
Algorithm for the Design of a Three-Dimensional Map of the Environment with a Depth Camera
Ortiz-Gonzalez, A., Kober, V., Karnaukhov, V., & Mozerov, M. (2020) · Journal of communications technology & electronics · doi:10.1134/s1064226920060224 · Cited by 1
New Methods of Eye-to-Eye Calibration and its Application to Cooperative Localization
Li, Z.-J. (2020) · doi:10.25534/tuprints-00011465 · Cited by 1
“With the drastic improvement in computation power nowadays, the localization algorithms have shown the tendency of developing from the filter-based framework to the non-linear optimization-based fashion [60], which is computationally more expensive but exhibits better performance compared to the former.”
BackgroundAfifi, A., & Woo, B. (2019) · Positioning · doi:10.4236/pos.2019.104004 · Cited by 1
“demonstrated that keyframe-based techniques are more accurate than filtering for the same computational efficiency [32].”
BackgroundEfficient Visual Localization for Ground Vehicles in Outdoor Environments
Bürki, M. (2019) · doi:10.3929/ethz-b-000372042 · Cited by 1
“1 State Estimator At the core of our localization system we employ a state estimation framework in information form, the dual representation of the (Extended) Kalman-Filter [11, 84].”
MethodA Hierarchical Searching Approach for Laser SLAM Re-localization on Mobile Robot Platform
Zhang, S.-M., & Lu, Q. (2019) · International Conference on Real-time Computing and Robotics · doi:10.1109/rcar47638.2019.9044132 · Cited by 1
MAV based SLAM and autonomous navigation: A view towards efficient on-board systems
Murray, P., & Schukat, M. (2017) · Irish Signals and Systems Conference · doi:10.1109/issc.2017.7983597 · Cited by 1
“There are works that have investigated various limitations that a robot may face, such as limited and distorted images in a camera system [19], algorithm effectiveness and efficiency [20] or running an EKF on a platform with real-time limitations [21].”
BackgroundMonocular Camera Path Estimation Cross-linking Images in a Graph Structure
Wefelscheid, C. (2013) · doi:10.14279/depositonce-1140 · Cited by 1
“[84], a high number of features in contrast to a high framerate results in better accuracy.”
BackgroundSingle camera based location estimation with dissimilarity measurement
Adrjanowicz, L., Kubanek, M., & Bobulski, J. (2013) · International Conference on Human System Interaction · doi:10.1109/hsi.2013.6577830 · Cited by 1
Vision SLAM-based UAV obstacle avoidance system
Li, R., Shang, H., Shen, M.-H., & Xiao, Y.-Y. (2024) · 2023 INTERNATIONAL CONFERENCE ON MECHATRONIC AUTOMATION AND ELECTRICAL ENGINEERING (ICMAEE2023) · doi:10.1063/5.0214207 · Cited by 1
Localization in Unprecedentedly Crowded Airspace for UAVs and SUAVs
Khelifi, M., & Butun, I. (2022) · IEEE Access · doi:10.1109/access.2022.3181377 · Cited by 1
“While others opt for the Simultaneous Lo-37 calization and Mapping (SLAM) approach [51].”
BackgroundSLAM and deep learning for 3D indoor scene understanding
McCormac, B. J. (2018) · doi:10.25560/68466 · Cited by 1
Urban, S. (2016) · doi:10.5445/ir/1000063488 · Cited by 1
“Outstanding work of [41] and [178] give a detailed analysis of both methods and close the gap between SLAM, SfM and classical bundle adjustment by generalization of the entire reconstruction problem using graphical models.”
BackgroundMethodKumari, U., & Rana, S. (2025) · arXiv.org · doi:10.48550/arxiv.2503.17668
“Hauke Strasdat et al.[8] compare filtering and sparse bundle adjustment for visual SLAM using Monte Carlo experiments, emphasizing accuracy and cost.”
Diao, H., Wang, X., Lu, S., Gao, Y., Chen, Z., Wang, S., & Wei, Z. (2026) · Tribology International · doi:10.1016/j.triboint.2026.112813
Review of Visual SLAM: From Geometry to Learning with Challenges and Future Directions
Kamble, M., Watvisave, D., Watvisave, O., & Kamble, D. (2026) · International Journal of Mechanical Engineering · doi:10.14445/23488360/ijme-v13i7p118
“The pivotal insight, famously framed as "Why filter?" by Strasdat et al. [61], was that the SLAM problem is inherently sparse and is better solved as a large-scale batch optimization over a history of states.”
UAV-Assisted Collaborative Positioning in GNSS-Denied Environments
Masiero, A., Toth, C., Morelli, L., Trybała, P., & Remondino, F. (2026) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlix-b1-2026-41-2026
“SLAM-based methods can be visual (Strasdat et al., 2012, Macario Barros et al., 2022), using cameras (e.g., ORB-SLAM3 (Mur-Artal et al., 2015, Campos et al., 2021) and COLMAP-SLAM (Morelli et al., 2023)), or LiDAR-based.”
SLAM in Low-Light Environments: Project Report
Basystyi, O., Stasyshyn, A., Kosovan, O., & Prytula, Y. (2026) · arXiv.org · doi:10.48550/arxiv.2607.17699
“The optimization-based methods (Strasdat et al., 2012) are considered the current de facto standard; these systems solve the "complete graph" of constraints over a subset of frames known as keyframes (Mur-Artal et al., 2015; Mur-Artal and Tardós, 2017; Campos et al., 2021).”
Probabilistic Association of Sonar Contacts Using Factor Graphs
Bakken, E., Midtgaard, Ø., & Haavardsholm, T. (2026) · Fusion · doi:10.23919/fusion67272.2026.11726429
“In robotics, this is typically formulated as a MAP inference problem and solved using non-linear least squares optimisation [10], [4], [11].”
Towards Ubiquitous Mapping and Localization for Dynamic Indoor Environments
Djerroud, H., Steyn, N., Rabreau, O., Bonnin, P., & Benali, A. (2026) · International Conference on Agents and Artificial Intelligence · doi:10.5220/0013245400003890
“Estimation algorithms (Strasdat et al., 2012), such as the Extended Kalman Filter (EKF-SLAM), particle filters (Fast-SLAM) (Montemerlo, 2002), and graph-based optimization methods (Graph-SLAM) (Thrun and Mon-temerlo, 2006), are used to solve nonlinear state equations and optimize both the robot’s…”
A Comprehensive Evaluation of ORB and SuperPoint Frontends for Visual SLAM
Eltaher, A., Mohammed, A. M., Abozied, M., & Elrewainy, A. (2026) · International Symposium on Information Engineering and Electronic Commerce · doi:10.1109/ieec69628.2026.11583983
Synthetic and real data for training and testing ground camera-based UAV tracking
Masiero, A., Dabove, P., Pietra, V. D., Piragnolo, M., Guarnieri, A., Vettore, A., & Toth, C. (2026) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlviii-4-w18-2025-249-2026
“This capability is exploited in Simultaneous Localization and Mapping (SLAM, (Leonard and Durrant-Whyte, 1991, Strasdat et al., 2012)) approaches (Macario Barros et al., 2022, Kazerouni et al., 2022), which may be further enhanced with supplementary sensor data to improve localization accuracy…”
Givens, M. W., & McMahon, J. W. (2026) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g008783
Nocerino, A., Fasano, G., Grassi, M., & Opromolla, R. (2026) · AIAA SCITECH 2026 Forum · doi:10.2514/6.2026-2260
Okawara, T., Nishibe, R., Kasano, M., Uno, K., & Yoshida, K. (2025) · 2025 International Conference on Space Robotics (iSpaRo) · doi:10.1109/isparo66239.2025.11436177
“The smoothing approaches contrast with typical filtering methods (e.g., Kalman filter)[22], which rely solely on the most recent data.”
Range-Based 6-DoF Monte Carlo SLAM with Gradient-Guided Particle Filter on GPU
Nakao, T., Koide, K., Takanose, A., Oishi, S., Yokozuka, M., & Date, H. (2025) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra55743.2025.11128385
“Since the Kalman filter only holds and estimates the current state and marginalizes out past states every time new observations arrive, it tends to accumulate linearization errors quickly [11].”
A Keyframe Optimization Method Based on Information Entropy
Zhang, X., & Tan, N. (2025) · 计算机科学辑要 · doi:10.63313/cs.8004
“…环境，可能导致系统关键帧插入的冗余度增加或重要关键帧漏选，从而限制了全局定位性能的进一步提 升。 信息熵 [7] 作为信息论中度量随机变量不确定性的重要指标（ Shannon, 1948 ），近年来在机器人导航 与 SLAM 领域的研究中得到了广泛关注 [8] 。 Strasdat 等首次提出了基于信息熵的关键帧选择策略 [9] ，通过 量化地图点信息量减少冗余关键帧插入，显著提升了单目 SLAM 系统的性能。 Das 与 Waslander 将信息 熵关键帧策略推广到多摄像头视觉 SLAM 系统（ MCPTAM ） [10]”
PIDNet-SLAM: A Multi-Resolution Semantic SLAM Algorithm for Dynamic Scenes
Rajan, S., Gu, J., & Liu, W. (2025) · IEEE Systems Conference · doi:10.1109/syscon64521.2025.11014652
Adaptive Approach to Simultaneous Localization and 3D Mapping Using an RGB-D Camera
González-Sarabia, A., González-Fraga, J. A., Kober, V., Karnaukhov, V., & Mozerov, M. (2025) · Journal of communications technology & electronics · doi:10.1134/s1064226925700214
Trisovic, J., Didier, A., Muntwiler, S., & Zeilinger, M. (2024) · European Control Conference · doi:10.23919/ecc65951.2025.11187277
“While EKFs are computationally efficient, they struggle with scalability and consistency, particularly with an increasing number of landmarks [3], [4].”
A GGCM-E Based Semantic Filter and Its Application in VSLAM Systems
Li, Y., Shao, C., & Wang, J. (2024) · Electronics · doi:10.3390/electronics13224487
Comparative Performance Analysis of LiDAR-Based SLAM Algorithms: A Case Study
Ramesh, K., Friesen, M., Facchinetti, T., & Wisniewski, L. (2024) · IEEE International Conference on Emerging Technologies and Factory Automation · doi:10.1109/etfa61755.2024.10710946
“Despite significant advancements in image processing and AI enhancing its functionality [8], LiDAR SLAM is preferred for its reliability in diverse environments, particularly in low-light or no-light conditions where Visual SLAM struggles [9].”
BackgroundA Comparative Study on Feature Descriptors in the Visual Odometry Stack for State Estimation
Gbreel, M., & Arslan, E. (2023) · 2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit58785.2023.10304924
“Unlike wheel odometry, VO does not suffer from wheel slip during turning or variations in terrain, making it more reliable in such scenarios [7].”
BackgroundVision-based pose estimation for robot navigation in an uncontrolled environment
Zheng, J., Juarez-Salazar, R., & Díaz-Ramírez, V. (2023) · Optical Engineering + Applications · doi:10.1117/12.2677909
Robust LiDAR-Visual-Inertial Fusion Odometry for Autonomous Vehicles
Zheng, S.-K., Li, Z.-T., Zheng, P.-C., Zhang, H.-F., Liu, Y.-F., & Zou, X.-D. (2023) · Youth Academic Annual Conference of Chinese Association of Automation · doi:10.1109/yac59482.2023.10401326
“…methods, feature-based methods are robust to geometric distortion and inconsistent brightness [4], and can use bundle adjustment [5] to jointly optimize feature points projection in multiple frames and the pose states of these frames, achieving better performance than filter-based methods [6].”
MethodOffline GNSS/Camera Extrinsic Calibration Using RTK and Fiducials
Jordan, A. D., Johnson, J. C., McLain, T., & Beard, R. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3268014
“With the understanding that discrete batch-optimization approaches outperform the EKF in terms of accuracy per unit of computing time [11], the work in [6] and [7] present an optimization-based GNSS VIO system that includes GNSS to VIO extrinsics as an online calibration parameter.”
BackgroundDATASET FOR POSITIONING AND TRACKING CARS AND PEDESTRIANS FROM UAV IMAGERY AND STATIC LIDAR
Gurturk, M., Masiero, A., Toth, C., Dabove, P., Pietra, V. D., Vettore, A., Guarnieri, A., Mugnai, F., & Soycan, M. (2023) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlviii-1-w1-2023-161-2023
“Vision-based positioning and tracking techniques are quite popular, in particular for what concerns visual simultaneous localization and mapping (SLAM) techniques (Mur-Artal et al., 2015, Leonard and Durrant-Whyte, 1991, Strasdat et al., 2012, Whelan et al., 2016).”
MethodMohamed, M., Khalil, M., & Salama, C. R. (2022) · Novel Intelligent and Leading Emerging Sciences Conference · doi:10.1109/niles56402.2022.9942422
“Today, the mainstream of visual SLAM uses state-of-the-art optimization techniques which represented by graph optimization [2].”
BackgroundMonocular Cloud Map Generation for Intelligent Navigation
Vaibhav, K., Rc, V., R., S., Mm, H., Murthy, D. S., S, L., Ravikanth, M., & Tyagi, T. (2022) · IEEE International Conference on Electronics, Computing and Communication Technologies · doi:10.1109/conecct55679.2022.9865765
“Bags of binary words were obtained for the first time, from the BRIEF descriptors [30] by the Dorian Bag of words, DBoW2[31], and fused with the FAST feature detector [32].”
MethodVisual Navigation Based on Nonlinear Optimization Method for Asteroid Landing
Hu, R.-H., Huang, X.-Y., & Xu, C. (2021) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-15-8155-7_334
Yue, Y., & Wang, D. (2020) · Springer tracts in autonomous systems · doi:10.1007/978-981-15-8860-0_2
A Monocular Visual-Inertial Odometry Based on Hybrid Residuals
Lai, Z., Gui, J.-J., Xu, D., Dong, H., & Deng, B.-S. (2020) · IEEE International Conference on Systems, Man and Cybernetics · doi:10.1109/smc42975.2020.9283418
“It was shown in [17] that optimization-based approaches provide better accuracy for the same computational work when compared to filter-based approaches.”
MethodGonzalez, H. (2019) · doi:10.70675/e6e67bd9z1eaez4517zb42dze3f97a5be056
“Bayesian methods like Kalman filter or Particle filter are implemented to predict the robot location [10, 12, 11].”
Method
Metadata
- Authors
- Strasdat, H., Montiel, J. M. M., & Davison, A. J.
- Affiliations
- Imperial College London (GB)
- Universidad de Zaragoza (ES)
- Corresponding author
- Strasdat, Hauke
- Venue
- Image and Vision Computing
- Publisher
- Elsevier BV
- Published
- 2012-02
- Volume
- 30
- Issue
- 2
- Pages
- 65-77
- ISSN
- 0262-8856 (ISSN-L)
- OpenAlex
- W49679257
- Cited by
- 439
- References
- 0
- Citations by year
- 2026: 9 · 2025: 25 · 2024: 28 · 2023: 37 · 2022: 44 · 2021: 47 · 2020: 47 · 2019: 50 · 2018: 33 · 2017: 41 · 2016: 15 · 2015: 24 · 2014: 19 · 2013: 17 · 2012: 2
- FWCI
- 33.37
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Image and Vision Computing (publishedVersion)
- Funders
- Imperial College London
- Ministerio de Economía y Competitividad
- Universidad de Zaragoza
- FP7 Information and Communication Technologies
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- visual SLAM, structure from motion, filtering algorithms, sparse bundle adjustment, real-time SLAM, stereo SLAM, monocular SLAM, entropy reduction, computational cost, Monte Carlo simulation
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
