FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
The DOI matches its Crossref record; 54 of the 57 references it cites were found in a registry or an index.
Abstract
This paper describes a probabilistic approach to the problem of recognizing places based on their appearance. The system we present is not limited to localization, but can determine that a new observation comes from a previously unseen place, and so augment its map. Effectively this is a SLAM system in the space of appearance. Our probabilistic approach allows us to explicitly account for perceptual aliasing in the environment—identical but indistinctive observations receive a low probability of having come from the same place. We achieve this by learning a generative model of place appearance. By partitioning the learning problem into two parts, new place models can be learned online from only a single observation of a place. The algorithm complexity is linear in the number of places in the map, and is particularly suitable for online loop closure detection in mobile robotics.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Adhi Harmoko, S., M.Komp, Jacquard, J. M., Zuse, K., & Eniac (2005) · Cited by 18,035
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,667
Rayward-Smith, V. J. (1991) · Journal of the Operational Research Society · doi:10.1057/jors.1991.155 · Cited by 16,821
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 2×
“Local feature schemes consist of a region-of-interest detector combined with a descriptor of the local region, SIFT (Lowe 1999) being a popular example.”
BackgroundSURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
(1999) · Cited by 12,854
Grossman, P. (2009) · Discrete Mathematics for Computing · doi:10.1007/978-0-230-37405-8_1 · Cited by 8,834
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 4×
“Finally, we map regions of descriptor space to visual words as suggested by Sivic and Zisserman (2003).”
MethodInfluentialGumbel, E. J. (1958) · Columbia University Press eBooks · doi:10.7312/gumb92958 · Cited by 5,567
Research works printed but not linked: 27
- Bay, H., 2006, Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, 13, 404
- Bowling, M., Twenty-First National Conference on Artificial Intelligence
- Bowling, M., Proceedings of the International Symposium of Robotics Research
- Dementiev, R., Proceedings 3rd International Conference on Theoretical Computer Science
- Ferreira, F., Proceedings IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
- Gutmann, J., Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA)
- Ho, K., Proceedings of the European Conference on Mobile Robotics
- Ho, K., Proceedings of the International Conference on Computational Intelligence
- Johnson, A., 1997, Spin-Images: a representation for 3-D surface matching
- Li, F., IEEE International Conference on Robotics and Automation
- Lowe, D.G., Proceedings of the 7th International Conference on Computer Vision
- Meila, M., ICML '99: Proceedings of the Sixteenth International Conference on Machine Learning
- Meila2-Predoviciu, M., 1999, Learning with mixtures of trees
- Mozos, O., Proceedings of the IEEE International Conference on Robotics and Automation
- Newman, P., Proceedings of the IEEE International Conference on Robotics and Automation
- Newman, P.M., Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
- Nister, D., 2006, Proceedings of the Conference on Computer Vision and Pattern Recognition, 2, 2161
- Ramos, F.T., Proceedings of the IJCAI Workshop on Reasoning with Uncertainty in Robotics
- Ranganathan, A., Proceedings of International Conference on Robotics and Automation
- Schindler, G., Proceedings IEEE Conference on Computer Vision and Pattern Recognition
- Silpa-Anan, C., Proceedings of the Australian Conference on Robotics and Automation
- Silpa-Anan, C., Proceedings of the Workshop on Omnidirectional Vision
- Sim, R., Proceedings of the IEEE International Conference on Intelligent Robots and Systems
- Sivic, J., Proceedings of the International Conference on Computer Vision
- Srebro, N., Proceedings of the 17th Annual Conference on Uncertainty in Artificial Intelligence (UAI-01)
- Torralba, A., ICCV '03: Proceedings of the Ninth IEEE International Conference on Computer Vision
- Wang, J., Proceedings of the IEEE International Conference on Robotics and Automation
Cited by
Items 301–400 of 1,002
Autonomous indoor helicopter flight using a single onboard camera
Soundararaj, S. P., Sujeeth, A. K., & Saxena, A. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354617 · Cited by 37
“SLAM (e.g., [27], [ 6 ], [22]), in which the map is built using images captured from a camera.”
BackgroundRobust incremental SLAM with consistency-checking
Graham, M. C., How, J. P., & Gustafson, D. E. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353363 · Cited by 44
“In practice however, the front-end systems used to identify landmarks and loop closures can generate incorrect measurements caused by self-similar structures in the environment (e.g. visual aliasing [4]).”
BackgroundSequence searching with CNN features for robust and fast visual place recognition
Bai, D., Wang, C., Zhang, B., Yi, X., & Yang, X. (2017) · Computers & Graphics · doi:10.1016/j.cag.2017.07.019 · Cited by 38
Seed: A Segmentation-Based Egocentric 3D Point Cloud Descriptor for Loop Closure Detection
Fan, Y., He, Y., & Tan, U.-X. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341517 · Cited by 37
“CVFH [14] follows the idea and improves the robustness by dividing points cloud into smooth regions before calculating descriptor.”
BackgroundMapping, planning and exploration with Pose SLAM
Carreño, R. V. (2013) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-94927 · Cited by 39
Addressing Challenging Place Recognition Tasks Using Generative Adversarial Networks
Latif, Y., Garg, R., Milford, M. J., & Reid, I. D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461081 · Cited by 36
Global localization of a mobile robot using lidar and visual features
Su, Z., Zhou, X., Cheng, T., Zhang, H., Xu, B., & Chen, W. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324775 · Cited by 37
“FAB-MAP is another work using bag of words image representation and explicitly models the dependencies between different visual words [7].”
MethodNetwork Uncertainty Informed Semantic Feature Selection for Visual SLAM
Ganti, P., & Waslander, S. L. (2019) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2019.00024 · Cited by 38
“Traditional feature detectors and descriptors, such as SIFT [2], SURF [3], FAST [4], or ORB [5] aim to satisfy the first 3 criteria, while appearance based methods such as FAB-MAP [6] or SeqSLAM [7] aim to fulfill criteria 4 and 5.”
MethodVision-only autonomous navigation using topometric maps
Dayoub, F., Morris, T., Upcroft, B., & Corke, P. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696611 · Cited by 36
“Vision has also become critical for ‘closing the loop’ — forming connections from the current view to other corresponding views elsewhere in the map that might not be co-located in the current map due to sensor error or odometry drift [5].”
BackgroundTopological simultaneous localization and mapping: a survey
Boal, J., Miralles, Á. S., & Arranz, Á. (2013) · Robotica · doi:10.1017/s0263574713001070 · Cited by 45
“Cummins and Newman 22 employ a Chow-Liu tree.”
BackgroundMethodHerrera-Granda, E. P., Torres, J. C., & Peluffo-Ordóñez, D. H. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e37356 · Cited by 49
Fleer, D., & Möller, R. (2016) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2016.12.001 · Cited by 37
“2The class of holistic methods is not equivalent to that of visual-appearance methods, as at least some appearance methods use local visual features such as SIFT or SURF [17, 64].”
MethodXu, Y., Huang, J., Wang, J., Wang, Y., Qin, H., & Nan, K. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3094228 · Cited by 41
“The left images of CC and NC are employed in evaluation and the authors in [16] provided corresponding ground truths.”
MethodFAB-MAP: Appearance-Based Place Recognition and Mapping using a Learned Visual Vocabulary Model
Cummins, M., & Newman, P. M. (2010) · International Conference on Machine Learning · Cited by 35
Self-citationAccurate localization by fusing images and GPS signals
Kumar, V., Jawahar, C. V., & Chari, V. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301390 · Cited by 35
“Most popular localization approaches are designed to represent object location in 3D coordinate systems either using the lat/long format like Global Position System ( GPS ) sensors, or by using metric distances like vision based localization methods.”
BackgroundTowards improving the efficiency of sequence-based SLAM
Liu, Y., & Zhang, H. (2013) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2013.6618095 · Cited by 34
“The state-of-the-art solution to SLAM in apperance used Bag-of-Word (BoW) image descriptor [1] which is a vector quantized representation of the local salient feature descrip tors such as SIFT [2] and SURF [3], with FAB-MAP [4] as one of the representatives.”
MethodVisual Place Recognition Using Landmark Distribution Descriptors
Panphattarasap, P., & Calway, A. D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54190-7_30 · Cited by 35
“To aid robustness, these techniques are often incorporated within some form of temporal integration, the probabilistic FAB-MAP method [5, 6] being the most well known.”
MethodOpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions
Talbot, B., Garg, S., & Milford, M. J. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593761 · Cited by 34
GSLAM: A General SLAM Framework and Benchmark
Zhao, Y., Xu, S., Bu, S., Jiang, H., & Han, P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00120 · Cited by 41
“FabMap [11] [30] propose a probabilistic approach to the problem of recognizing places based on their appearance, which is used by RSLAM [47], LSD-SLAM [16].”
Deep Learning for Underwater Visual Odometry Estimation
Teixeira, B., Silva, H. M., Matos, A. C., & Silva, E. (2020) · IEEE Access · doi:10.1109/access.2020.2978406 · Cited by 41
“In addition, the system has embedded a Bag-of-Words (BoW) [86] place recognition module that is used for performing both loop-closing and relocalization, built with the open-source library DBoW2 [87], taking advantage of an offline computation of the discretization of the descriptor space, which is…”
MethodSemantic loop closure detection based on graph matching in multi-objects scenes
Qin, C., Zhang, Y., Liu, Y., & Lv, G. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103072 · Cited by 42
Global image signature for visual loop-closure detection
Carrasco, P. L. N., Font, F. B., & Oliver, G. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9522-4 · Cited by 39
“In this context, images are represented as vectors that account for the number of occurrences of local image features taken from a dictionary.”
BackgroundMethodInfluentialZhang, G., Lilly, M. J., & Vela, P. A. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487205 · Cited by 33
“Frame 356 is therefore retrieved as the final loop-closure index.”
BackgroundMethodInfluentialLarge-Scale Place Recognition Based on Camera-LiDAR Fused Descriptor
Xie, S., Pan, C., Peng, Y., Liu, K., & Ying, S. (2020) · Sensors · doi:10.3390/s20102870 · Cited by 35
Probabilistic Visual Place Recognition for Hierarchical Localization
Xu, M., Sünderhauf, N., & Milford, M. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3040134 · Cited by 49
“In comparison, our approach does not perform mapping, however unlike [14], [18], [37], it can successfully localize in a large-scale map across severe appearance change when used in conjunction with a condition invariant VPR method.”
BackgroundMethodInfluentialSLAM in with the Combined Kalman-Information Filter
Cadena, C., & Neira, J. (2010) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2010.08.003 · Cited by 40
“Both simulations and experiments with the Victoria Park dataset, the DLR dataset, and an experiment using visual stereo are used to illustrate the algorithms’ advantages, also with respect to non filtering alternatives such as iSAM, the Treemap and Tectonic SAM.”
MethodRobust visual localization in changing lighting conditions
Kim, P., Coltin, B., Alexandrov, O., & Kim, H. J. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989640 · Cited by 34
“FAB-MAP [4], one of the most famous image retrieval approaches, shows impressive performance through a probabilistic model of natural features in a bag-of-words [5].”
BackgroundHu, H., Wang, H., Liu, Z., & Chen, W. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1003907 · Cited by 35
“5m 2◦ / 5◦ 2◦ / 5◦ 2◦ / 5◦ FAB-MAP [28] 0.”
BackgroundMethodA framework for learning semantic maps from grounded natural language descriptions
Walter, M. R., Hemachandra, S. M., Homberg, B. S., Tellex, S., & Teller, S. J. (2014) · The International Journal of Robotics Research · doi:10.1177/0278364914537359 · Cited by 39
“More recent methods consider a region’s visual appearance as a more discriminative means of performing place recognition [40, 6, 38].”
BackgroundMethodInfluentialEfficient data association for view based SLAM using connected dominating sets
Booij, O., Živković, Z., & Kröse, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.06.006 · Cited by 34
Indelman, V., Nelson, E., Dong, J., Michael, N., & Dellaert, F. (2016) · IEEE Control Systems · doi:10.1109/mcs.2015.2512031 · Cited by 32
Learning Deep NBNN Representations for Robust Place Categorization
Mancini, M., Bulò, S. R., Ricci, E., & Barbara Caputo, B. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2705282 · Cited by 32
“In the last decade several works in the robotic community addressed the problem of developing robust place recognition [15], [16], [17], [8], [9] and semantic classification [4], [18], [7] approaches using visual data.”
BackgroundLM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization
von Stumberg, L., Wenzel, P., Yang, N., & Cremers, D. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00107 · Cited by 45
“and more important for robotics [6], autonomous driving [24, 4] and AR/VR [29].”
BackgroundRadar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
Yin, H., Xu, X., Wang, Y., & Xiong, R. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.661199 · Cited by 39
“Based on these front-end descriptors, some researchers proposed probabilistic approach to Cummins and Newman (2008), or searched the best candidates in the past sequences Milford and Wyeth (2012).”
MethodFast relocalization for visual odometry using binary features
Straub, J., Hilsenbeck, S., Schroth, G., Huitl, R., Möller, A., & Steinbach, E. G. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738525 · Cited by 32
“In the middle part, the hallway opens up for a large staircase.”
BackgroundVision-based global localization for mobile robots with hybrid maps of objects and spatial layouts
Park, S., Kim, S., Park, M., & Park, S.-K. (2009) · Information Sciences · doi:10.1016/j.ins.2009.06.030 · Cited by 32
“Most place-recognitionbased systems [8,18,21,29,31,39] represent the environment as representative views captured from the environment, or as a set of specific types of visual features, such as local invariant features [24] extracted from the environmental images.”
BackgroundMethodIndexing visual features: Real-time loop closure detection using a tree structure
Liu, Y., & Zhang, H. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224741 · Cited by 34
“This model was modified in FAB-MAP 2.0 [6] in conjunction with a randomized KD-forest used in the clustering process for generating visual words for the system to deal with large outdoor environment.”
BackgroundMethodInfluentialSemantic Mapping with Mobile Robots
Pronobis, A. (2011) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 50
Generative Methods for Long-Term Place Recognition in Dynamic Scenes
Johns, E., & Yang, G. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0648-6 · Cited by 39
“Linear interpolation was used in learning visual word likelihoods for place recognition in (Cummins and Newman, 2008) by combining the explicitly-learned likelihood with a prior likelihood on the visual word (Cummins and Newman, 2009).”
MethodAccelerating FAB-MAP With Concentration Inequalities
Cummins, M., & Newman, P. M. (2010) · IEEE Transactions on Robotics · doi:10.1109/tro.2010.2080390 · Cited by 31
“HE MOTIVATION of this paper is to improve the speed of our fast-appearance-based mapping system (FAB-MAP), which is an appearance-based navigation system for mobile robots [5], [7].”
MethodSelf-citationPepperell, E., Corke, P., & Milford, M. J. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915618766 · Cited by 32
“…100% precision, and the longest continuous regions of location uncertainty, all of which are standard benchmarks in the community (Churchill and Newman, 2012; Cummins and Newman, 2008; Johns and Yang, 2013b; Liu and Zhang, 2013; Lowry et al., 2014a; McManus et al., 2014b; Milford and Wyeth, 2012).”
BackgroundMethodMemorable Maps: A Framework for Re-Defining Places in Visual Place Recognition
Zaffar, M., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3001228 · Cited by 40
Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization
Li, X., Ylioinas, J., Verbeek, J. J., & Kannala, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11015-4_19 · Cited by 35
Piniés, P., Paz, L. M., Gálvez‐López, D., & Tardós, J. D. (2010) · Journal of Field Robotics · doi:10.1002/rob.20355 · Cited by 43
“We can also see that BoW outperforms FAB-MAP in these data sets when using the Oxford vocabulary.”
BackgroundMethodResultInfluentialLocation graphs for visual place recognition
Stumm, E. S., Christopher Mei, A., Lacroix, S., & Chli, M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139964 · Cited by 33
“In the FAB-MAP framework, the probability normalization model differs compared to that in Equation (2), reducing recall significantly in the presence of multiple instances of the same location in the map (see [3] and [6] for more details).”
BackgroundMethodInfluentialMartín, F., Triebel, R., Moreno, L. E., & Siegwart, R. (2013) · Robotica · doi:10.1017/s026357471300060x · Cited by 32
Benchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map
Ragot, N., Khemmar, R., Pokala, A., Rossi, R., & Ertaud, J.-Y. (2019) · International Conference on Emerging Security Technologies · doi:10.1109/est.2019.8806213 · Cited by 32
Chen, H., ZHANG, G., & Ye, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3010580 · Cited by 32
“The FAB-MAP dataset [26] and the proposed Dynamic Scenes dataset include the ground truth for evaluating the loop detection performance.”
MethodSTA-VPR: Spatio-Temporal Alignment for Visual Place Recognition
Lu, F. H., Chen, B., Zhou, X., & Song, D. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3067623 · Cited by 30
“Traditional VPR methods, such as FAB-MAP [5], typically follow computer vision approaches to encode handcrafted features like SURF [16] into the bag-of-words models.”
MethodElhashash, M., & Qin, R. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.03.018 · Cited by 30
A Demonstration of ‘Broken’ Visual Space
Svarverud, E., Gilson, S. J., & Glennerster, A. (2012) · PLoS ONE · doi:10.1371/journal.pone.0033782 · Cited by 30
“One distinct alternative to 3D reconstruction is view-based representation, particularly in the contexts of object recognition [32] or navigation [33,34,35,36].”
Application of Locality Sensitive Hashing to realtime loop closure detection
Shahbazi, H., & Zhang, H. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6095099 · Cited by 30
“To solve the image matching problem in the context of visual SLAM, several frameworks have been developed [1], [3] and at the heart of each of these frameworks, there is a method for computing image similarities.”
MethodEnvironment selection and hierarchical place recognition
Mohan, M., Gálvez‐López, D., Monteleoni, C., & Sibley, G. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139966 · Cited by 30
“Consequently, a large number of techniques for describing and comparing images and for retrieving the best matches have been proposed in the literature [3], [15].”
BackgroundLocal region detector + CNN based landmarks for practical place recognition in changing environments
Neubert, P., & Protzel, P. (2015) · European Conference on Mobile Robots · doi:10.1109/ecmr.2015.7324051 · Cited by 31
“the keypoint based FAB-MAP [7] system has severe problems with seasonal changes.”
BackgroundInfluentialBuilding Location Models for Visual Place Recognition
Stumm, E. S., Christopher Mei, A., & Lacroix, S. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915570140 · Cited by 29
“Note that the model could be further extended to remove the conditional independence assumption between words, for instance by using a Chow–Liu tree as done in Cummins and Newman (2008).”
BackgroundMethodResultInfluentialAn Online Sparsity-Cognizant Loop-Closure Algorithm for Visual Navigation
Latif, Y., Huang, G. P., Leonard, J. J., & Neira, J. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.036 · Cited by 29
“In particular, Cummins and Newman [12] proposed FAB-MAP, a probabilistic appearancebased approach using visual BoW for place recognition, and showed it to work robustly over trajectories up to 1000 km. Similarly, Galvez-Lopez and Tardos [18] introduced a BinaryBoW (BBoW)-based method, which detects FAST [27] keypoints…”
MethodLoop-Closure Detection Using Local Relative Orientation Matching
Ma, J., Ye, X., Zhou, H., Mei, X., & Fan, F. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3074520 · Cited by 29
Large Scale Monocular Vision-Only Mapping from a Fixed-Wing sUAS
Warren, M., McKinnon, D. H., He, H., Glover, A., Shiel, M., & Upcroft, B. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-40686-7_33 · Cited by 29
“In comparison to the SURF detector used in the original FABMAP [6], our algorithm uses the STAR detector (based on CenSu rE [1]).”
MethodInfluentialRelative geometry-aware siamese neural network for 6DOF camera relocalization
Li, Q., Zhu, J., Cao, R., Sun, K., Garibaldi, J. M., Li, Q., Liu, B., & Qiu, G. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.09.071 · Cited by 30
An Opportunistic Linear–Convex Algorithm for Localization in Mobile Robot Networks
Safavi, S., & Khan, U. A. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2686441 · Cited by 29
“Robot localization approaches include but are not limited to dead-reckoning [7], [8], simultaneous localization and mapping (SLAM), [9]–[12], Monte Carlo techniques [3], [5], [6], [13], [14], and Kalman filtering methods [15]–[20]; other related works include [21]–[29].”
BackgroundMethodEvaluation of Object Proposals and ConvNet Features for Landmark-based Visual Place Recognition
Hou, Y., Zhang, H., & Zhou, S. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0735-y · Cited by 28
“For example, visual Bag-of-Words (BoW) [11] used in FAB-MAP [3] is one of the most popular local feature-based techniques.”
MethodScene Recognition for Indoor Localization of Mobile Robots Using Deep CNN
Woźniak, P., Afrisal, H., Esparza, R. G., & Kwolek, B. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00692-1_13 · Cited by 31
“FAB-MAP [6] is a probabilistic approach to recognize places on the basis of appearance information.”
BackgroundVision-based UAVs Aerial Image Localization: A Survey
Xu, Y., Pan, L., Du, C., Li, J., Jing, N., & Wu, J. (2018) · ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI) · doi:10.1145/3281548.3281556 · Cited by 38
“The localization performance of probabilistic systems with relative location information such as FAB-MAP[12], FAB-MAP 2.0[13] is also improved by introducing relative position information through Bayesian filtering technology.”
MethodInfluentialMap Recovery and Fusion for Collaborative Augment Reality of Multiple Mobile Devices
Zhang, J., Liu, J., Chen, K., Pan, Z., Liu, R., Wang, Y., Yang, T. T., & Chen, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2999924 · Cited by 28
“The most common technique is the bag-of-word (BoW) model [12], which uses visual words to describe keyframes, and to compute the similarity among them [13], [14].”
MethodHow Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
Chelani, K., Kahl, F., & Sattler, T. (2021) · 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/cvpr46437.2021.01541 · Cited by 45
“This idea of lifting points to lines was later adapted for privacy-perserving SLAM [67].”
BackgroundTracking‐DOSeqSLAM: A dynamic sequence‐based visual place recognition paradigm
Tsintotas, K. A., Bampis, L., Gasteratos, A. C., & FIET (2021) · IET Computer Vision · doi:10.1049/cvi2.12041 · Cited by 29
“Sum of absolute differences (SAD), local feature vote density [18], bag of words (BoW) histograms [19] or feature vectors derived from convolutional neural networks (CNNs) [20] are the most common techniques.”
BackgroundMethodInfluentialVision-based precision vehicle localization in urban environments
Li, C., Dai, B., & Wu, T. (2013) · Chinese Automation Congress · doi:10.1109/cac.2013.6775806 · Cited by 31
“The works of [12]-[17] fall into the first category.”
BackgroundMethodContinuous appearance-based trajectory SLAM
Maddern, W., Milford, M. J., & Wyeth, G. F. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979963 · Cited by 27
“…two successive discrete observations: ( ) ( ) ( ) ( ) ( ) ( ) t i t i i e P t t e P t t t e P Z Z x | 1 | 1 | 1 = − + = − = = (20) The set of objects e i that form the appearance representation must be derived from training data in a similar environment to the test environment [3].”
BackgroundMethodInfluentialDetecting the Expectancy of a Place Using Nearby Context for Appearance-Based Mapping
Kazmi, S. M. A. M., & Mertsching, B. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2926475 · Cited by 29
“Instead of preparing a specialized vocabulary, a pretrained vocabulary is downloaded [47].”
BackgroundMethodInfluentialWang, Y., Qiu, Y., Cheng, P., & Duan, X. (2020) · Remote Sensing · doi:10.3390/rs12233890 · Cited by 29
The role of homing in visual topological navigation
Liu, M., Pradalier, C., Pomerleau, F., & Siegwart, R. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385640 · Cited by 27
Self-supervised Geometric Perception
Yang, H., Dong, W., Carlone, L., & Koltun, V. (2021) · 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/cvpr46437.2021.01412 · Cited by 41
“Future research includes (i) increasing the training recall towards 100%; (ii) differentiating the robust estimation layer [35]; (iii) designing an optimality-based [79] and learnable verifier based on cycle consistency [39, 33, 53]; (iv) speeding up the teacher-student loop; (iv) forming image and point cloud pairs u…”
MethodSpiking Neural Networks for Visual Place Recognition Via Weighted Neuronal Assignments
Hussaini, S., Milford, M. J., & Fischer, T. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3149030 · Cited by 28
“Early works for the VPR problem implemented hand-crafted feature representations – either from local points or by aggregating features over the whole image [17], [39], [40].”
Robust Onboard Localization in Changing Environments Exploiting Text Spotting
Zimmerman, N., Wiesmann, L., Guadagnino, T., Läbe, T., Behley, J., & Stachniss, C. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981049 · Cited by 29
“For cameras, the global localization task is framed under the visual place recognition framework, for which multiple algorithms have been proposed [3][10].”
MethodRobust online map merging system using laser scan matching and omnidirectional vision
Tungadi, F., Lui, W. L. D., Kleeman, L., & Jarvis, R. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5654446 · Cited by 27
“This paper shares the same idea with the work by Ho and Newman [ 12 ] , in the sense that both visual and laser range information is required for a robust place recognition system which can be used to solve both the loop closing and map merging problems .”
BackgroundMethodInfluentialPlace recognition based on deep feature and adaptive weighting of similarity matrix
Li, Q., Li, K., You, X., Bu, S., & Liu, Z. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.03.029 · Cited by 27
“In Fast Appearance Based Mapping (FAB-MAP) [14, 15, 16], a recent technology used to solve the loop closure detection in SLAM, the BoW model is adopted to build the descriptor of each video frame.”
MethodMultimodal localization: Stereo over LiDAR map
Zuo, X., Ye, W., Yang, Y., Zheng, R., Vidal‐Calleja, T., Huang, G. P., & Liu, Y. (2020) · Journal of Field Robotics · doi:10.1002/rob.21936 · Cited by 27
“Cummins and Newman (2008) propose FAB ‐ Map, a probabilistic localization method in the space of appearance, which aims to address the problem of visual aliasing for large ‐ scale navigation.”
BackgroundRobust outdoor visual localization using a three‐dimensional‐edge map
Nuske, S. T., Roberts, J. M., & Wyeth, G. F. (2009) · Journal of Field Robotics · doi:10.1002/rob.20306 · Cited by 28
“The work of Cummins and Newman (2008) and Valgren and Lilienthal (2008) both present recent results that improve operations even when lighting changes cause disruptions in the image-point feature descriptions. However, these authors are solving a problem different from ours—that of appearance-based localization (recog…”
BackgroundMethodInfluentialA Survey on Monocular Re-Localization: From the Perspective of Scene Map Representation
Miao, J., Jiang, K., Wen, T., Wang, Y., Jia, P., Wijaya, B., Zhao, X., Qian, C., Xiao, Z., Huang, J. H., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3378716 · Cited by 54
“In addition to those LF-VPR solutions aggregating local features and localizing like GF-VPR methods, some other methods adopt probabilistic schemes to find matched reference frames in P ( A, B ) .”
Video-based localization without 3D mapping for the visually impaired
Liu, J. J., Phillips, C. J., & Daniilidis, K. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543581 · Cited by 26
“FAB-MAP uses bag of words to model locations using a generative appearance approach.”
InfluentialRetrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments
Hu, H., Wang, H., Liu, Z., Yang, C., Chen, W., & Xie, L. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968047 · Cited by 30
“We chose a structure-based localization method CSL [23] as well as two image-based localization methods FAB-MAP [17] and NetVLAD [10] as baselines.”
MethodSVG-Loop: Semantic–Visual–Geometric Information-Based Loop Closure Detection
Yuan, Z., Xu, K., Zhou, X., Deng, B., & Ma, Y. (2021) · Remote Sensing · doi:10.3390/rs13173520 · Cited by 27
A fast LiDAR place recognition and localization method by fusing local and global search
Shi, P., Li, J., & Zhang, Y. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.07.008 · Cited by 27
Ground robot navigation using uncalibrated cameras
Koch, O., Walter, M. R., Huang, A. S., & Teller, S. J. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509325 · Cited by 30
“Recent bag-of-words approaches, which quantize features into visual “words” and use a set of observed words to represent a place, have improved the speed and robustness of visual loop closing [12], [13].”
BackgroundScene structure registration for localization and mapping
Fernández-Moral, E., Rives, P., Arévalo, V., & González-Jiménez, J. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.09.009 · Cited by 26
“In robotics, the most common approach to solve this problem is the bag-of-words (BoW) method [5,6], which creates a dictionary of features and employs a voting method to retrieve the location, is traditionally used for relocalization, loop closure or topological localization and mapping.”
MethodPlace Recognition: An Overview of Vision Perspective
Zeng, Z., Zhang, J., Wang, X., Chen, Y., & Zhu, C. (2018) · Applied Sciences · doi:10.3390/app8112257 · Cited by 30
“State-of-the-art visual simultaneous localization and mapping (SLAM) systems such as FAB-MAP Cummins and Newman (2008; 2011) used bag-of-visual-words to construct the final image representation.”
MethodSequence-based sparse optimization methods for long-term loop closure detection in visual SLAM
Han, F., Wang, H., Huang, G. P., & Zhang, H. (2018) · Autonomous Robots · doi:10.1007/s10514-018-9736-3 · Cited by 26
“In most existing approaches, a new query scene is matched with a scene template in the database using scene matching methods, i.e. maximum similarity score or nearest neighbor search (Arroyo et al. 2015; Cummins and Newman 2008).”
BackgroundMethodInfluentialDetection of loop closure in SLAM: A DeconvNet based approach
Mukherjee, A., Chakraborty, S., & Saha, S. K. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.04.041 · Cited by 25
High-level visual features for underwater place recognition
Li, J., Eustice, R. M., & Johnson‐Roberson, M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139706 · Cited by 31
Outdoor Localization Using Stereo Vision Under Various Illumination Conditions
Kiyoshi, I. R. I. E., Yoshida, T., & Tomono, M. (2012) · Advanced Robotics · doi:10.1163/156855311x614608 · Cited by 25
“Recently, appearance-based localization methods which are robust to changes in lighting have been proposed [17][18].”
BackgroundIndoor Place Recognition System for Localization of Mobile Robots
Sahdev, R., & Tsotsos, J. K. (2016) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2016.38 · Cited by 25
“Some other probabilistic appearance based methods include [20], [21] and [22].”
MethodVisual Place Recognition for Autonomous Mobile Robots
Horst, M., & Möller, R. (2017) · Robotics · doi:10.3390/robotics6020009 · Cited by 25
“FabMap [29] and its extensions [30,31] provide a full appearance-based SLAM system.”
BackgroundBansal, A., Badino, H., & Huber, D. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856605 · Cited by 25
“test data is gathered all at one time [7] or over a period of a few days [8] without controlling for such factors as illumination.”
BackgroundImage-Based Localization Aided Indoor Pedestrian Trajectory Estimation Using Smartphones
Zhou, Y., Zheng, X., Chen, R., Xiong, H., & Guo, S. (2018) · Sensors · doi:10.3390/s18010258 · Cited by 27
Visual Localization Using Sparse Semantic 3D Map
Shi, T., Shen, S., Gao, X., & Zhu, L. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8802957 · Cited by 32
Sparse Pose Graph Optimization in Cycle Space
Bai, F., Vidal‐Calleja, T., & Grisetti, G. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3050328 · Cited by 28
“An edge is created if there exists a relative geometric relation between two poses, i.e. relative poses , which can be produced by a wheel-encoder, scan-matching [21], [65], [66], epipolar geometry [67], [68], or visual loop-closing techniques etc. [69], [70].”
BackgroundMulti-Classes and Motion Properties for Concurrent Visual SLAM in Dynamic Environments
Yang, B., Ran, W., Wang, L., Lu, H., & Chen, Y. P. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3110667 · Cited by 25
SeqMatchNet: Contrastive Learning with Sequence Matching for Place Recognition & Relocalization
Garg, S., Vankadari, M. B., & Milford, M. J. (2021) · Conference on Robot Learning · Cited by 43
BioSLAM: A Bioinspired Lifelong Memory System for General Place Recognition
Yin, P., Abuduweili, A., Zhao, S., Xu, L., Liu, C., & Scherer, S. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3306615 · Cited by 38
“Based on these handcrafted features, FAB-MAP [23] build a bag-of-visual-words (BoW) architecture to achieve large-scale visual relocalization [8], [24]. iBoW-LCD [25] uses an incremental BoW scheme based on binary descriptors to retrieve matched images more efficiently.”
MethodDifferential dynamic programming for optimal estimation
Kobilarov, M., Ta, D.-N., & Dellaert, F. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139279 · Cited by 25
“Recent estimation methods based on related ideas have focused on fast performance for real-time navigation [10], [25], [24], [23], [31], large-scale problems with massive amount of sensor data [1], [6], [33], [34], [22], [11], and long-term navigation [35], [36], [8], [9], [32].”
Background
Metadata
- Authors
- Cummins, M., & Newman, P.
- Affiliations
- University of Oxford (GB)
- Corresponding author
- Cummins, Mark
- Newman, Paul
- ORCID
- Newman, Paul
- Venue
- The International Journal of Robotics Research
- Publisher
- SAGE Publications
- Published
- 2008-06
- Volume
- 27
- Issue
- 6
- Pages
- 647-665
- ISSN
- 0278-3649 (ISSN-L)
- 1741-3176
- OpenAlex
- W2144824356
- Cited by
- 1,472
- References
- 57
- Citations by year
- 2026: 28 · 2025: 43 · 2024: 60 · 2023: 59 · 2022: 119 · 2021: 122 · 2020: 103 · 2019: 117 · 2018: 105 · 2017: 127 · 2016: 90 · 2015: 103 · 2014: 72 · 2013: 83 · 2012: 71
- FWCI
- 116.69
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- The International Journal of Robotics Research (publishedVersion)
- Funders
- Engineering and Physical Sciences Research Council
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- place recognition, perceptual aliasing, loop closure detection, mobile robots
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.