Double window optimisation for constant time visual SLAM
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
We present a novel and general optimisation framework for visual SLAM, which scales for both local, highly accurate reconstruction and large-scale motion with long loop closures. We take a two-level approach that combines accurate pose-point constraints in the primary region of interest with a stabilising periphery of pose-pose soft constraints. Our algorithm automatically builds a suitable connected graph of keyposes and constraints, dynamically selects inner and outer window membership and optimises both simultaneously. We demonstrate in extensive simulation experiments that our method approaches the accuracy of offline bundle adjustment while maintaining constant-time operation, even in the hard case of very loopy monocular camera motion. Furthermore, we present a set of real experiments for various types of visual sensor and motion, including large scale SLAM with both monocular and stereo cameras, loopy local browsing with either monocular or RGB-D cameras, and dense RGB-D object model building.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“inspired by [223], Strasdat et al. [235] take a two-stage approach and optimize first a local pose-features graph and then a pose-pose graph; Williams et al. [259] split factor graph optimization in a high-frequency filter and lowfrequency smoother, which are periodically synchronized.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [235]
Citations
Cites
Machine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555
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 · cited 3×
“For example, PTAM [6] runs full bundle adjustment in a background thread, which limits its scale to small workspaces.”
BackgroundClosed-form solution of absolute orientation using unit quaternions
Horn, B. K. P. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.000629 · Cited by 4,116 · cited 2×
“Given a set of three 3D-3D corresponences, a relative pose Ti,ref is uniquely defined [3].”
BRIEF: Binary Robust Independent Elementary Features
Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_56 · Cited by 3,597 · cited 1×
“Afterwards, we use guided BRIEF [1] matching between measurements and candidate points seeded at FAST [15] corners – followed by 3D to 3D robust pose refinement to produce an initial pose estimate.”
MethodScalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579 · cited 1×
“Candidates for large loop closures can be efficiently detected using appearance information only [2, 14].”
BackgroundPhoto tourism: exploring photo collections in 3D
Snavely, N., Seitz, S. M., & Szeliski, R. (2006) · ACM Transactions on Graphics · doi:10.1145/1141911.1141964 · Cited by 2,866
G2o: A general framework for graph optimization
Kummerle, R., Grisetti, G., Strasdat, H., Konolige, K., & Burgard, W. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5979949 · Cited by 1,982 · cited 2×
“Both methods are implemented using the efficient state-of-the-art sparse graph optimizer g(2)o [9] and executed on a single core of an Intel(R) Core(TM) i7 960 desktop computer.”
MethodSelf-citationPhoto tourism: exploring photo collections in 3D
Snavely, N., Seitz, S. M., & Szeliski, R. (2006) · ACM SIGGRAPH 2006 Papers on - SIGGRAPH '06 · doi:10.1145/1179352.1141964 · Cited by 696
FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping
Konolige, K., & Agrawal, M. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004832 · Cited by 532 · cited 3×
“Instead of estimating this uncertainty accurately using proper marginalisation [8], we suggest to approximate ΛTji coarsely:”
BackgroundMethodSelf-citationReal Time Localization and 3D Reconstruction
Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., & Sayd, P. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) · doi:10.1109/cvpr.2006.236 · Cited by 396 · cited 1×
“In general, keyframes are fixed at the boundary of the active window, and all those keyframes with co-visible points are typically included [13].”
Background
Research works printed but not linked: 1
- rosten, 2006, Machine learning for highspeed corner detection, Proceedings of the European Conference on Computer Vision (ECCV)
Cited by
Items 101–200 of 296
Semi-direct tracking and mapping with RGB-D camera for MAV
Bu, S., Zhao, Y., Wan, G., Li, K., Cheng, G., & Liu, Z. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3524-x · Cited by 21
Contour-SLAM: A Robust Object-Level SLAM Based on Contour Alignment
Lin, S., Wang, J., Xu, M., Zhao, H., & Chen, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3244223 · Cited by 23
“S(p, Zk(p)) is used to generate a virtual stereo coordinate [uL , vL , u R] introduced in [33], which is defined as follows:”
MethodHybrid sparse monocular visual odometry with online photometric calibration
Luo, D., Zhuang, Y., & Wang, S. (2022) · The International Journal of Robotics Research · doi:10.1177/02783649221107703 · Cited by 21
“When the number of features successfully tracked reaches Nth (Nth = 200 in this work), the feature tracking step is completed, and the covisibility graph (Strasdat et al., 2011) about the current frame is built which will be used in BA in Section 5.”
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
“LC [14] and the pose graph optimization [18] are also utilized to solve the problem of localization drifting over time.”
MethodLoop Closing Detection in RGB-D SLAM Combining Appearance and Geometric Constraints
Zhang, H., Liu, Y., & Tan, J. (2015) · Sensors · doi:10.3390/s150614639 · Cited by 21
“Loop closing detection [1,2] consists of determining whether the robot is in the area that has been visited before according to current sensor information, or whether the current position of the robot has”
BackgroundEfficient keyframe-based real-time camera tracking
Dong, Z., Zhang, G., Jia, J., & Bao, H. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.08.005 · Cited by 20
“Recently, Hauke Strasdat and Konolige [25] proposed a double window optimization framework for scalable SLAM, which scales for both accurate local reconstruction and large-scale loopy camera motion.”
Large Scale Dense Visual Inertial SLAM
Ma, L., Falquez, J. M., McGuire, S., & Sibley, G. (2016) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-27702-8_10 · Cited by 19
“Perhaps the point based approaches [1–3] are the most popular ones for large scale SLAM.”
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
Layout aware visual tracking and mapping
Salas, M., Hussain, W., Concha, A., Montano, L., Civera, J., & Montiel, J. M. M. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353367 · Cited by 19
“, start a new map after X sec or Y features [23], [24].”
BackgroundSelf-citationLD-SLAM: A Robust and Accurate GNSS-Aided Multi-Map Method for Long-Distance Visual SLAM
Li, D., Zhang, F., Feng, J., Wang, Z., Fan, J., Li, Y., Li, J., & Yang, T. (2023) · Remote Sensing · doi:10.3390/rs15184442 · Cited by 20
DS-PTAM: Distributed Stereo Parallel Tracking and Mapping SLAM System
Croce, M. D., Pire, T., & Bergero, F. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0913-6 · Cited by 17
“All this makes cameras one of the most widely used sensors to solve the SLAM problem (PTAM [14], ORB-SLAM2 [17], LSD-SLAM [6], ScaViSLAM [22], SVO [9], S-LSD-SLAM [7] and S-PTAM [19]).”
MethodCross-platform AR annotation for assembly-design communication in pipe outfitting
Wang, J., Fan, X., Zhu, Y., Yang, X., & Yin, X. (2022) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-022-09637-8 · Cited by 17
“Based on the covisibility graph [48], an algorithm (Algorithm 1) is proposed to maintain a dense local map with expanded search scope.”
MethodOff the beaten track: Predicting localisation performance in visual teach and repeat
Dequaire, J., Tong, C. H., Churchill, W., & Posner, I. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487209 · Cited by 16
“In this framework, a robot is driven along a desired path in a teach phase, during which it builds a topometric map [8], [9] of the world by estimating its relative pose between consecutive keyframes.”
BackgroundZhao, Y., Smith, J. S., Karumanchi, S. H., & Vela, P. A. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197003 · Cited by 19
“The duration profile is defined with medium describing an interval of [2, 10] minutes.”
BackgroundDSOL: A Fast Direct Sparse Odometry Scheme
Qu, C., Shivakumar, S. S., Miller, I. D., & Taylor, C. J. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981491 · Cited by 19
“Early VO/V-SLAM systems were mostly sparse and indirect [9], [10], [11], [12].”
Backgroundσ-DVO: Sensor Noise Model Meets Dense Visual Odometry
Babu, B. P. W., Kim, S., Yan, Z., & Ren, L. (2016) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2016.11 · Cited by 18
“On generation of a new keyframe, the back-end graph is updated with the previous keyframe information and a double window graph structure similar to [22] is created as shown in Figure 8.”
MethodFMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAM
Tang, F., Li, H., & Wu, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793664 · Cited by 17
“A double window optimisation for constant time visual SLAM was proposed in [24].”
MethodCongestion-aware Evacuation Routing using Augmented Reality Devices
Zhang, Z., Liu, H., Jiao, Z., Zhu, Y., & Zhu, S. C. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197494 · Cited by 14
“The DBoW2 algorithm [37] further matches these key points to a keyframe of the environment by searching through the pre-built covisibility graph [38].”
Deep Pose Graph-Matching-Based Loop Closure Detection for Semantic Visual SLAM
Duan, R., Feng, Y., & Wen, C. (2022) · Sustainability · doi:10.3390/su141911864 · Cited by 13
Gyro-aided camera-odometer online calibration and localization
Li, D., Eckenhoff, K., Wu, K., Wang, Y., Xiong, R., & Huang, G. P. (2017) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2017.7963501 · Cited by 14
“al [14] presented Double-Window Optimization, which performs optimization in a local map.”
A general framework for modeling and dynamic simulation of multibody systems using factor graphs
Blanco, J., Leanza, A., & Reina, G. (2021) · Nonlinear Dynamics · doi:10.1007/s11071-021-06731-6 · Cited by 13
“[33]) approaches exist as well, enabling the efficient estimation of problems with thousands to millions of variables [34, 35, 36].”
BackgroundHybrid Monocular SLAM Using Double Window Optimization
Luo, H., Pape, C., & Reithmeier, E. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3070298 · Cited by 15
“Note that in our formulation the pose-pose constraint is used for the inner window, which is opposite to the work in [13].”
MethodBundledSLAM: An Accurate Visual SLAM System Using Multiple Cameras
Han, S., Liu, C., & Dai, H. (2024) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac59436.2024.10503743 · Cited by 20
“Covisibility is represented as an undirected weighted graph as in [12].”
BackgroundVisual SLAM using multiple RGB-D cameras
Yang, S., Yi, X., Wang, Z., Wang, Y., & Yang, X. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7418965 · Cited by 14
“The SLAM system in [28] uses a twolevel approach for efficient optimisation of the map.”
MethodMonocular Visual Odometry using Learned Repeatability and Description
Huang, H., Ye, H., Sun, Y., & Liu, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197406 · Cited by 13
Visual recovery of saliency maps from human attention in 3D environments
Santner, K., Fritz, G., Paletta, L., & Mayer, H. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631185 · Cited by 12
Real-time Omnidirectional Visual SLAM with Semi-Dense Mapping
Wang, S., Yue, J., Dong, Y., Shen, R., & Zhang, X. (2018) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2018.8500460 · Cited by 12
“The covisibility map which can give a brief description of a keyframe’s surroundings can thus be built by fusing map points in one specified keyframes and other nearby keyframes [19].”
BackgroundZhang, C., Liu, Y., Wang, F., Xia, Y., & Zhang, W. (2018) · Sensors · doi:10.3390/s18114036 · Cited by 13
“Improved Double Window Structure An improved double window structure [24,35] was built in our VINS-MKF, which was retrieved from a local visible map, to organize variables to be optimized and related observations, as Figure 11b shows.”
MethodSimultaneous Localization and Mapping
Stachniss, C. (2017) · Springer eBooks · doi:10.1007/978-3-662-47094-7_49 · Cited by 13
SlamDunk: Affordable Real-Time RGB-D SLAM
Fioraio, N., & Stefano, L. D. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_28 · Cited by 11
“On the other hand, proposals conceived to deal with long mapping paths, such as [24,22], find the active region following the existing connections between keyframes along the camera path; instead, by relying on the current camera position only, we foster the creation of links and, possibly, close…”
BackgroundMethodInfluentialIndirect Visual Simultaneous Localization and Mapping Based on Linear Models
Chien, C.-H., Hsu, C.-C. J., Wang, W., & Chiang, H. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2952722 · Cited by 11
“Similar to [8], another approach [12] inheriting the front-end of PTAM revealed a double-window optimization for the back-end.”
ResultLIV-LAM: LiDAR and Visual Localization and Mapping
Radmanesh, R., Wang, Z., Chipade, V. S., Tsechpenakis, G., & Panagou, D. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9148037 · Cited by 12
“In SLAM methods, the most dominant approach for motion estimation using cameras are the so-called indirect methods (feature-based methods) [9], [19], [12].”
MethodLiODOM: Adaptive local mapping for robust LiDAR-only odometry
Garcia‐Fidalgo, E., Bonnin‐Pascual, F., & Ortiz, A. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104226 · Cited by 14
Robust Onboard Visual SLAM for Autonomous MAVs
Yang, S., Scherer, S., & Zell, A. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_27 · Cited by 11
“The work in [9] proposed a double-window graph structure for optimizing its global map.”
BackgroundMethodRelative Topometric Localization in Globally Inconsistent Maps
Mazuran, M., Boniardi, F., Burgard, W., & Tipaldi, G. D. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-60916-4_25 · Cited by 11
“[29], to consider a second optimization window and to enforce a metric consistency within this optimization window.”
BackgroundAccurate Collaborative Globally-Referenced Digital Mapping with Standard GNSS
Narula, L., Wooten, J., Murrian, M. J., LaChapelle, D. M., & Humphreys, T. E. (2018) · Sensors · doi:10.3390/s18082452 · Cited by 10
“To this end, a pose-graph optimization [64] is performed over a large Nm-level covisibility window for Ki, where the relative translations and rotations between covisible keyframes, as estimated in the current session, are provided as delta-pose measurements, while the 6-DoF poses for the terminal nodes in the covisib…”
MethodBio-inspired visual self-localization in real world scenarios using Slow Feature Analysis
Metka, B., Franzius, M., & Bauer-Wersing, U. (2018) · PLoS ONE · doi:10.1371/journal.pone.0203994 · Cited by 11
Optimization-Based, Simplified Stereo Visual-Inertial Odometry With High-Accuracy Initialization
Yang, G., Zhao, L., Mao, J., & Liu, X. (2019) · IEEE Access · doi:10.1109/access.2019.2902295 · Cited by 12
“This model was first proposed in [2] and we utilize it to reduce the dimension of stereo visual measurements in traditional VIO.”
MethodEfficient on-board Stereo SLAM through constrained-covisibility strategies
Castro, G., Nitsche, M., Pire, T., Fischer, T., & Cristóforis, P. D. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.03.015 · Cited by 12
CDSFusion: Dense Semantic SLAM for Indoor Environment Using CPU Computing
Wang, S., Gou, G., Sui, H., Zhou, Y., Zhang, H., & Li, J. (2022) · Remote Sensing · doi:10.3390/rs14040979 · Cited by 11
Li, A., Liu, H., Wang, J., & Zhang, N. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981275 · Cited by 15
“Prior work suggests the use of metrics such as entropy [7], covisibility [8], [9], and covariance [10], [11] to select a subset of available keyframes to provide to BA.”
MethodA back-end L1 norm based solution for factor graph SLAM
Casafranca, J. J., Paz, L. M., & Piniés, P. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696326 · Cited by 10
Accurate Map-Based RGB-D SLAM for Mobile Robots
Belter, D., Nowicki, M., & Skrzypczyński, P. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-27149-1_41 · Cited by 10
Detection and Resolution of Motion Conflict in Visual Inertial Odometry
Babu, B. P. W., Cyganski, D., Duckworth, J., & Kim, S. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460870 · Cited by 11
“A sliding window based optimization [27] approach was used for the state estimation.”
MethodBundle adjustment using aerial images with two-stage geometric verification
Kume, H., Sato, T., & Yokoya, N. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.05.003 · Cited by 10
“To reduce accumulative errors in SfM, loop closing techniques [22, 23, 24] are sometimes employed.”
MethodTutor-Guided Interior Navigation With Deep Reinforcement Learning
Zeng, F., Wang, C., & Ge, S. S. (2020) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.3039859 · Cited by 11
ORB-LINE-SLAM: An Open-Source Stereo Visual SLAM System with Point and Line FeaturesPreprint
Alamanos, I., & Tzafestas, C. S. (2022) · doi:10.36227/techrxiv.21691949 · Cited by 11
SDVL: Efficient and Accurate Semi-Direct Visual Localization
Perdices, E., & Cañas, J. (2019) · Italian National Conference on Sensors · doi:10.3390/s19020302 · Cited by 9
“Following the main PTAM architecture, [7] proposed an algorithm that detects loop closures and can successfully handle large maps.”
MethodDynaNav-SVO: Dynamic Stereo Visual Odometry With Semantic-Aware Perception for Autonomous Navigation
Contreras, M., Bhatt, N. P., & Hashemi, E. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3414653 · Cited by 14
“Covisibility graph: We denote a graph, which has nodes in the map points connected to nodes that encode the camera poses all with respect to the world frame w [27], by C .”
Image based optimisation without global consistency for constant time monocular visual SLAM
Lui, V., & Drummond, T. W. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7140011 · Cited by 9
“For example, Strasdat et al. proposed a double window optimisation (DWO) [1] framework which attempts to keep the mapping time constant.”
BackgroundMethodEGO-SLAM: A Robust Monocular SLAM for Egocentric Videos
Patra, S., Gupta, K., Ahmad, F., Arora, C., & Banerjee, S. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00011 · Cited by 16
“While a variety of strategies including incremental [19, 9, 32, 7, 8, 26, 31, 47, 49, 51], hierarchical [50] and global [55] approaches have been proposed, the incremental ones remain popular because of their efficiency and 12000 frames”
BackgroundReal-time CPU-based large-scale 3D mesh reconstructionPreprint
Piazza, E., Romanoni, A., & Matteucci, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05230 · Cited by 9
“The most preeminent paradigms shown in the literature can be classified in featurebased [4], [5], direct [6], [7], and dense algorithms [8], [9].”
BackgroundStereo Visual Inertial Pose Estimation Based on Feedforward-Feedback LoopsPreprint
Chen, S., Wen, C., Zou, Y., & Chen, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02250 · Cited by 9
“Compared to its ancestors, ORB-SLAM includes many welldeveloped components: ORB features [8], dictionary-based loop detection [9], scale-aware loop closing [10], covisibilitybased optimization [11] and keyframe management strategy.”
BackgroundDepth data fusion for simultaneous localization and mapping — RGB-DD SLAM
Walas, K., Nowicki, M., Ferstl, D., & Skrzypczyński, P. (2016) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2016.7849459 · Cited by 8
A unified visual graph-based approach to navigation for wheeled mobile robots
Hartmann, J., Klüssendorff, J. H., & Maehle, E. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696610 · Cited by 8
“Assuming that the robot initially has no knowledge of the environment and its own position, the robot position has to be estimated while building the map, which is therefore called simultaneous localization and mapping (SLAM).”
BackgroundGraph-based visual SLAM and visual odometry using an RGB-D camera
Klüssendorff, J. H., Hartmann, J., Forouher, D., & Maehle, E. (2013) · International Workshop on Robot Motion and Control · doi:10.1109/romoco.2013.6614623 · Cited by 8
“developed a double window optimization for visual SLAM [14], which utilizes a graph-based approach, however, using two levels.”
MethodReduced dimensionality extended Kalman Filter for SLAM in a relative formulation
Gamage, D., & Drummond, T. W. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353545 · Cited by 9
“Newer methods like PTAM [9], ISAM [7], DWO [14], coalesced observations SLAM [4] solve this problem by retaining old views and performing bundle adjustment each time a key-frame is added to the view set.”
MethodSimultaneous Localization and Mapping
Stachniss, C. (2016) · Springer eBooks · doi:10.1007/978-3-662-46900-2_49-2 · Cited by 16
Towards Globally Consistent Visual-Inertial Collaborative SLAM
Karrer, M., & Chli, M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461213 · Cited by 8
“Since a full BA quickly becomes computationally infeasible for real-time or close to real-time applications, local optimization is performed frequently as in most KF-based SLAM systems today [16], [20].”
BackgroundLine Primitives and Their Applications in Geometric Computer Vision
Zhang, L. (2013) · MACAU: Open Access Repository of Kiel University (University Library Kiel) · Cited by 8
Monocular Visual-Inertial-Pressure fusion for Underwater localization and 3D mapping.
Ferrera, M. (2019) · theses.fr (ABES) · doi:10.70675/0a530b06ze9c8z4a9dzabccz9acc11efeb31 · Cited by 13
“The method follows the approach of (Klein et al., 2007a; Mur-Artal et al., 2015; Strasdat et al., 2011a).”
BackgroundMap Point Selection for Visual SLAM
Müller, C. J., & van Daalen, C. V. (2023) · Robotics Auton. Syst. · doi:10.1016/j.robot.2023.104485 · Cited by 4
“[17] proposed performing bundle adjustment in a local window while using approximate pose-graph optimisation in a larger outer window.”
BackgroundLVIF: a lightweight tightly coupled stereo-inertial SLAM with fisheye camera
Zhu, H., Zhang, G., Ye, Z., & Zhou, H. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01190-5 · Cited by 10
“Reference [23] presents a double-window optimization with a co-visibility graph.”
Fast and robust mapping with low-cost Kinect V2 for photovoltaic panel cleaning robot
Li, M., Zhang, M., Fu, Y., Guo, W. P., Zhong, X., Wang, X., & Chen, F. (2016) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2016.7606901 · Cited by 8
Tightly Coupled Semantic RGB-D Inertial Odometry for Accurate Long-Term Localization and Mapping
Patel, N., Khorrami, F., Krishnamurthy, P., & Tzes, A. P. (2019) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar46387.2019.8981658 · Cited by 8
“During loop closure, the current keyframe Ki is compared in terms of similarity of its bag of word vectors with other keyframes in the covisibility graph [28] and similarly matched based on semantic feature matching.”
MethodORB-SLAM2S: A Fast ORB-SLAM2 System with Sparse Optical Flow Tracking
Diao, Y., Cen, R., Xue, F., & Su, X. (2021) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci52617.2021.9435915 · Cited by 7
“…of robust descriptors of keypoints, the feature-based method can establish the common view relationship for a longer time and add more constraint relations, such as covisibility graph [14], relocalization, and loop detection, so that this method can obtain better robustness and trajectory accuracy.”
MethodSimultaneous Localization and Mapping
Stachniss, C. (2015) · Springer eBooks · doi:10.1007/978-3-662-46900-2_49-1 · Cited by 8
Stereovision-Based Ego-Motion Estimation for Combine Harvesters
Chen, H., Chen, J., Guan, Z.-H., Li, Y.-M., Cheng, K., & Cui, Z.-H. (2022) · Italian National Conference on Sensors · doi:10.3390/s22176394 · Cited by 8
“A plethora of excellent batch nonlinear optimization methods have emerged [20,21].”
BackgroundCross-Agent Relocalization for Decentralized Collaborative SLAM
Bänninger, P., Alzugaray, I., Karrer, M., & Chli, M. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160941 · Cited by 8
“The tracking of each new frame only considers the map points observed from the subset of local keyframes Tlocal(Tref) [17], [34].”
BackgroundOriginal Loop-Closure Detection Algorithm for Monocular vSLAM
Bokovoy, A., & Yakovlev, K. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-73013-4_19 · Cited by 7
“There exist also standalone loop-closure detectors [9,10] that may be plugged in to some of the vSLAM methods.”
ATG-PVD: Ticketing Parking Violations on A DronePreprint
Wang, H., Liu, Y., Huang, H., Pan, Y., Yu, W., Jiang, J., Lyu, D., Bocus, M. J., Liu, M., Pitas, I., et al. (2020) · doi:10.36227/techrxiv.12839156 · Cited by 7
“iews of a 3D scene (typically known as multi-view geometry) to estimate camera poses and construct/update a map of the 3D scene. The state-of-the-art VSLAM approaches are classied as either indirect [24,25,26] or direct [27,28,29]. Both types extract visual features from images and associate them with descriptors. How…”
BackgroundBlintsov, V., & Kucenko, P. (2019) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2019.179486 · Cited by 6
A Stereo Visual Odometry Framework with Augmented Perception for Dynamic Urban Environments
Contreras, M., Bhatt, N. P., & Hashemi, E. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421981 · Cited by 7
“Covisibility graph: Let C be a graph which contains a window of frames and the map points seen in more than one frame [17].”
BackgroundConstrained-covisibility marginalization for efficient on-board stereo SLAM
Nitsche, M., Castro, G., Pire, T., Fischer, T., & Cristóforis, P. D. (2017) · European Conference on Mobile Robots · doi:10.1109/ecmr.2017.8098655 · Cited by 6
“[14] introduces an optimization framework that distinguishes two different keyframe windows.”
BackgroundLow-latency Visual SLAM with Appearance-Enhanced Local Map Building
Zhao, Y., Ye, W., & Vela, P. A. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794046 · Cited by 6
“later extended to pose tracking [1], [8]–[10].”
Camera Motion Agnostic Method for Estimating 3D Human Poses
Kim, S. H., Jeong, S., Park, S., & Chang, J. Y. (2022) · Sensors · doi:10.3390/s22207975 · Cited by 7
“We believe that this error accumulation problem can be alleviated through the use of constraints, such as loop closure in methods for simultaneous localization and mapping [48].”
Gyroscope assisted scalable visual simultaneous localization and mapping
Babu, B. P. W., Cyganski, D., & Duckworth, J. (2014) · Ubiquitous Positioning, Indoor Navigation, and Location Based Service · doi:10.1109/upinlbs.2014.7033731 · Cited by 7
“Ga-ScaViSLAM uses a similar threading architecture as proposed in ScaViSLAM[1] (Fig.”
BackgroundMethodResultInfluentialReal-time camera tracking using hybrid features in mobile augmented reality
Wang, W., & Wan, H. (2015) · Science China Information Sciences · doi:10.1007/s11432-015-5360-4 · Cited by 6
Global Motion Estimation from Relative Measurements in the Presence of Outliers
Bourmaud, G., Mégret, R., Giremus, A., & Berthoumieu, Y. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16814-2_24 · Cited by 7
“Indeed, a 3D rotation matrix evolves on the Lie group SO (3) [7], the rigid body motion matrices correspond to the Special Euclidean Lie group SE (3) [8], the homography matrices can be identified with the Special Linear Lie group SL (3) [9], and the 3D similarity transformation matrices form the Lie group Sim (3) [10…”
Incremental Pose Map Optimization for Monocular Vision SLAM Based on Similarity Transformation
Liu, W., Wu, S., Zhong-bo, W., & Wu, X. (2019) · Sensors · doi:10.3390/s19224945 · Cited by 7
“Strasdat et al. [14] proposed a two-level optimization method, which combines the precise point constraints of the main regions of interest with the stable edges of the position-attitude soft constraints, dynamically choosing the inner and outer window members and optimizing them simultaneously.”
MethodA general approach to time-varying parameters in pose-graph optimization
Cucci, D. A., Clausen, P., Škaloud, J., & Matteucci, M. (2017) · European Navigation Conference (ENC) · doi:10.1109/euronav.2017.7954217 · Cited by 8
“These approaches are well known in photogrammetry under the name of bundle-adjustment (BA) [5], and are now also popular in the robotic community, mainly because of their application to the Simultaneous Localization and Mapping (SLAM) problem [6], [7], [8].”
BackgroundHybrid Metric-topological Mapping for Large Scale Monocular SLAM
Fernández-Moral, E., Arévalo, V., & González-Jiménez, J. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-10891-9_12 · Cited by 6
“The work of [23] is also related to RBA, they propose a double window optimization: a first window as in PTAM and a second one including the periphery of the first to improve consistency by optimizing a pose-graph.”
MethodGood Graph to Optimize: Cost-Effective, Budget-Aware Bundle Adjustment in Visual SLAMPreprint
Zhao, Y., Smith, J. S., & Vela, P. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.10123 · Cited by 12
“Other systems [23]–[26] use the covisibility graph to organize historical states and query the covisible subgraph for local BA construction.”
BackgroundRobust Relocalization Based on Active Loop Closure for Real-Time Monocular SLAM
Chen, X., Lu, H., Xiao, J., Zhang, H., & Wang, P. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68345-4_12 · Cited by 5
Self-adaptation for Mobile Robot Algorithms Using Organic Computing Principles
Hartmann, J., Stechele, W., & Maehle, E. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36424-2_20 · Cited by 5
Creating Metric-topological Maps for Large-scale Monocular SLAM
Fernández-Moral, E., González-Jiménez, J., & Arévalo, V. (2013) · International Conference on Informatics in Control, Automation and Robotics (ICINCO) · doi:10.5220/0004438900390047 · Cited by 5
“The work of (Strasdat et al., 2011) is also related to RBA, they propose a double window optimization: a first window as in PTAM and a second one including the periphery of the first to improve consistency by optimizing a pose-graph.”
MethodLinear-complexity stochastic variational Bayes inference for SLAM
Jiang, X., Hoy, M., Yu, H., & Dauwels, J. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317844 · Cited by 5
“• Graph-Based Optimisation These methods iteratively perform batch optimization, exploiting the sparse graph structure of the SLAM problem (see e.g. [7], [8], [9], [10], [11]) 1 .”
BackgroundMethodZeng, F.-Y., Zeng, W., & Gan, Y. (2018) · International Conference on Image, Vision and Computing · doi:10.1109/icivc.2018.8492909 · Cited by 8
“The system maintains a covisibiliy graph [15] that links any two keyframes observing common points and a minimum spanning tree connecting all keyframes.”
BackgroundVID-SLAM: Robust Pose Estimation with RGBD-Inertial Input for Indoor Robotic Localization
Shan, D., Su, J., Wang, X., Liu, Y., Zhou, T., & Wu, Z. (2024) · Electronics · doi:10.3390/electronics13020318 · Cited by 5
Enhanced Visual Loop Closing for Laser-Based SLAM
Zhu, Z., Yang, S., & Dai, H. (2018) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2018.8445128 · Cited by 5
“[12] create a loop closure detection mechanism using bags of words [13] with SURF [14] features.”
MethodAccurate Visual-Inertial SLAM by Feature Re-identification
Peng, X., Liu, Z., Wang, Q., Kim, Y.-T., Jeon, M. J., & Lee, H. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636186 · Cited by 5
YOWO: You Only Walk Once to Jointly Map an Indoor Scene and Register Ceiling-Mounted Cameras
Yang, F., Yamao, S., Kusajima, I., Moteki, A., Masui, S., & Jiang, S. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3453277 · Cited by 5
“However, due to the physical barriers posed by indoor walls, CMCs may be divided into separate spaces, and therefore, we cluster them into groups based on their co-observations [15], [66], [97].”
A Multi-Robot Collaborative Monocular SLAM Based on Semi-Direct Method
Yun, Z., Ma, X., & Ye, Y. (2022) · Prognostics and Health Management Conference (PHM) · doi:10.1109/phm2022-london52454.2022.00089 · Cited by 4
“The sliding window method [10] which is used to optimize the pose in the direct module could lose its flexibility and efficiency eventually because the keyframe insertion adopts a loose strategy that will cause the size of the sliding window to increase rapidly.”
MethodAn Effective LiDAR-Inertial SLAM-Based Map Construction Method for Outdoor Environments
Liu, Y., Wang, C., Wu, H., & Wei, Y. (2024) · Remote Sensing · doi:10.3390/rs16163099 · Cited by 7
“Back-end techniques commonly utilized include pose graph optimization algorithms such as GTSAM [9], Ceres Solver [10], and so on, while loop closure detection algorithms typically use radius nearest neighbor (RNN) [11].”
A sensor-centric EKF for inertial-aided visual odometry
Kleinert, M., & Stilla, U. (2013) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2013.6817915 · Cited by 4
“This hampers the application of key-frame selection methods as proposed in [5].”
MethodOnline 3D Reconstruction and 6-DoF Pose Estimation for RGB-D Sensors
Lim, H., Lim, J., & Kim, H. J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_16 · Cited by 4
“Other approaches such as [10, 22] search metric loop closures by assuming some motion prior to be available.”
BackgroundMethodInfluentialFDMO: Feature Assisted Direct Monocular Odometry
Younes, G., Asmar, D., & Zelek, J. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007524800002108 · Cited by 14
Using Learning of Speed to Stabilize Scale in Monocular Localization and Mapping
Frost, D., Murray, D. W., & Prisacariu, V. A. (2017) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00066 · Cited by 4
“[33].”
2D Grid map for navigation based on LCSD-SLAM
Zhou, Y., Li, B., Wang, D., & Mu, J. (2021) · International Conference on Information Science and Technology · doi:10.1109/icist52614.2021.9440650 · Cited by 4
“Relative to the last key frame, direct image alignment is used to track the new frame and create its depth map by projecting the active points in the window [13].”
BackgroundPal, S., Gupta, S., Das, N., & Ghosh, K. (2022) · Journal of Autonomous Vehicles and Systems · doi:10.1115/1.4055161 · Cited by 4
Metadata
- Authors
- Strasdat, H., Davison, A. J., Montiel, J. M. M., & Konolige, K.
- Affiliations
- Imperial College London (GB)
- Universidad de Zaragoza (ES)
- Venue
- 2011 International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2011-11
- Pages
- 2352-2359
- OpenAlex
- W2154280780
- Cited by
- 296
- References
- 21
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 9 · 2023: 13 · 2022: 25 · 2021: 20 · 2020: 30 · 2019: 33 · 2018: 31 · 2017: 30 · 2016: 23 · 2015: 34 · 2014: 15 · 2013: 21 · 2012: 5
- FWCI
- 25.35
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- visual SLAM, loop closure, monocular camera, stereo camera, RGB-D, dense 3D reconstruction, bundle adjustment
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.