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 201–300 of 1,002
PLISS: Detecting and Labeling Places Using Online Change-Point Detection
Ranganathan, A. (2010) · Robotics: Science and Systems · doi:10.15607/rss.2010.vi.024 · Cited by 73
“In our exposition, we closely follow the more general methods of [2], [10] which is applicable to conjugate-exponential models.”
MethodDV-LOAM: Direct Visual LiDAR Odometry and Mapping
Wang, W., Liu, J., Wang, C., Luo, B., & Zhang, C. (2021) · Remote Sensing · doi:10.3390/rs13163340 · Cited by 74
An Open-source Bio-inspired Solution to Underwater SLAM★
Silveira, L., Guth, F., Drews, P., Ballester, P. L., Machado, M. O., Codevilla, F., Filho, N. L. D., & Botelho, S. S. D. C. (2015) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2015.06.035 · Cited by 76
Mei, C., Sibley, G., & Newman, P. (2010) · 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2010.5652266 · Cited by 67
“Applying state-of-the-art pose-based loop closure solutions such as FABMAP [3] to these three images, the results will depend on the order.”
BackgroundMethodSelf-citationVisual-SLAM Classical Framework and Key Techniques: A Review
Jia, G., Li, X., Zhang, D., Xu, W., Lv, H., Shi, Y. C., & Cai, M. (2022) · Sensors · doi:10.3390/s22124582 · Cited by 69
How to learn an illumination robust image feature for place recognition
Lategahn, H., Beck, J., Kitt, B., & Stiller, C. (2013) · 2013 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2013.6629483 · Cited by 66
“The presented work is related to methods on place recognition and loop closure detection [9], [1], [2], [19], [15] and research on descriptor evaluation and learning [21], [6], [17], [8], [18], [5], [22], [10], [14].”
BackgroundMethodSemantic segmentation of street scenes by superpixel co-occurrence and 3D geometry
Mičušík, B., & Košecká, J. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457645 · Cited by 74
“This strategy watches whether: ”When a particular visual word is observed, is the most likely word from the learned tree observed too?” It has been shown in [4] in connection of location recognition that, if using a vocabulary tree and image signatures, such an approximation yields substantially better results than th…”
ResultLocalizing Discriminative Visual Landmarks for Place Recognition
Xin, Z., Cai, Y., Lu, T., Xing, X., Cai, S., Zhang, J., Yang, Y., & Wang, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794383 · Cited by 71
“[13] have been demonstrated to outperform traditional Bagof-Words (BoWs) models [2], [4] on visual place recognition.”
BackgroundGlobal Localization with Object-Level Semantics and Topology
Liu, Y., Pétillot, Y., Lane, D. M., & Wang, S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794475 · Cited by 79
“, Fast Appearance-Based MAPping (FAB-MAP) [5].”
BackgroundInfluentialGN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization
von Stumberg, L., Wenzel, P., Khan, Q., & Cremers, D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2965031 · Cited by 81
“Relocalization: An important task of relocalization is to approximate the pose of an image by simply querying the most similar image from a database [30], [31].”
BackgroundSemantic Reinforced Attention Learning for Visual Place Recognition
Peng, G., Yue, Y., Zhang, J., Wu, Z., Tang, X., & Wang, D. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561812 · Cited by 73
Relative Navigation Approach for Vision-Based Aerial GPS-Denied Navigation
Leishman, R. C., McLain, T. W., & Beard, R. W. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9914-7 · Cited by 76
“Place recognition is completed by comparing images to one another to find close matches [36], [37].”
BackgroundFast place recognition with plane-based maps
Fernández-Moral, E., Mayol-Cuevas, W. W., Arévalo, V., & González-Jiménez, J. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630951 · Cited by 62
High performance loop closure detection using bag of word pairs
Kejriwal, N., Kumar, S., & Shibata, T. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.12.003 · Cited by 70
DASGIL: Domain Adaptation for Semantic and Geometric-Aware Image-Based Localization
Hu, H., Qiao, Z., Cheng, M., Liu, Z., & Wang, H. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3043875 · Cited by 79
“Traditional local feature descriptors are aggregated for image retrieval [35], [36], and have successfully addressed most cases of loop closure detection in real-time Visual SLAM (VSLAM) [37], [38] without huge environmental changes.”
BackgroundSparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization
Germain, H., Bourmaud, G., & Lepetit, V. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00063 · Cited by 73
Fast and effective visual place recognition using binary codes and disparity information
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., Yebes, J. J., & Bronte, S. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942989 · Cited by 65
“Since the appearance of FAB-MAP [1], loop closure techniques based on visual information have experienced a significant growth and several works have contributed to this research line (see Section II).”
MethodReal-time 6-DOF monocular visual SLAM in a large-scale environment
Lim, H., Lim, J., & Kim, H. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907055 · Cited by 61
“The loop detection has been done by the appearance-based scene matching method [14] which shares the core idea with the vocabulary tree method [15] for fast large-scale image retrieval.”
MethodA generative framework for fast urban labeling using spatial and temporal context
Posner, I., Cummins, M., & Newman, P. M. (2009) · Autonomous Robots · doi:10.1007/s10514-009-9110-6 · Cited by 60
“Our patch-level classifier is inspired by the probabilistic appearance model described in [8] and the theory presented below is an extension of that work into a more general classification framework.”
BackgroundMethodInfluentialSelf-citationMonocular localization in urban environments using road markings
Lu, Y., Huang, J., Chen, Y.-T., & Heisele, B. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995762 · Cited by 72
“In [10] Cummins and Newman localize a camera by matching the current image against an image database using bag-of-words techniques [11].”
Saha, M., Fiannaca, A. J., Kneisel, M., Cutrell, E., & Morris, M. R. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353776 · Cited by 56
“computer vision techniques [14] for performing place recognition [24].”
BackgroundFast and incremental loop closure detection with deep features and proximity graphs
An, S., Zhu, H., Wei, D., Tsintotas, K. A., & Gasteratos, A. C. (2022) · Journal of Field Robotics · doi:10.1002/rob.22060 · Cited by 61
“Concerning the off-line approaches, Fast AppearanceBased MAPping (FAB-MAP) [5] introduced the visual vocabulary model aiming to mitigate the quantity of the extracted SURF points-of-interest [22], while a Chow Liu tree was adopted to learn the co-visibility between these words [55].”
BackgroundMethodInfluentialAttentional Pyramid Pooling of Salient Visual Residuals for Place Recognition
Peng, G., Zhang, J., Li, H., & Wang, D. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00092 · Cited by 70
“Visual place recognition (VPR) has become the core technique of many promising applications in the field of computer vision [1,2,5,39,41,45] and robotics [7,10,11,25], such as autonomous driving [6,24,28], geo-localization [22, 23, 40], 3D reconstruction [9] and virtual reality [26].”
BackgroundNID-SLAM: Robust Monocular SLAM Using Normalised Information Distance
Pascoe, G., Maddern, W., Tanner, M., Piniés, P., & Newman, P. M. (2017) · 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/cvpr.2017.158 · Cited by 68
Self-citationDeep Learning for Visual SLAM in Transportation Robotics: A review
Duan, C., Junginger, S., Huang, J., Jin, K., & Thurow, K. (2019) · Transportation Safety and Environment · doi:10.1093/tse/tdz019 · Cited by 63
“In other words, the robot can tell whether it has been to the place or not [53–55].”
BackgroundBag‐of‐words‐driven, single‐camera simultaneous localization and mapping
Botterill, T., Mills, S. J., & Green, R. (2010) · Journal of Field Robotics · doi:10.1002/rob.20368 · Cited by 69
“When used for robot localization, these schemes typically index images at around 1 Hz (Angeli et al., 2008b; Cummins & Newman, 2008b), as extracting SIFT or SURF features from every frame is too slow for real-time processing (Cummins & Newman, 2009; Rosten & Drummond, 2006).”
BackgroundMethodInfluentialKeep it brief: Scalable creation of compressed localization maps
Dymczyk, M., Lynen, S., Bosse, M. C., & Siegwart, R. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353722 · Cited by 57
“In order to match the features against the 3d landmarks, approaches from robotics can be used to first retrieve relevant database images [6, 7].”
MethodTextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts
Hong, Z., Pétillot, Y., Lane, D. M., Miao, Y., & Wang, S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00295 · Cited by 74
“Some of them have shown impressive place recognition performance for large-scale environments by using a single image matching [4, 5].”
BackgroundMethodInfluentialMilford, M. J., Lowry, S. M., Sünderhauf, N., Rowlands, S., Pepperell, E., Upcroft, B., Shen, C., Lin, G., Liu, F., Cadena, C., et al. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301395 · Cited by 60
“Experimental Setup Experiments were run using a new dataset consisting of two 1.1 km day and night car traverses along a multi-lane road (Figure 7).”
MethodInfluentialObject-aware bundle adjustment for correcting monocular scale drift
Frost, D., Kähler, O., & Murray, D. W. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487680 · Cited by 67
“All SLAM systems accumulate error in their estimates, which can be redistributed and reduced on loop-closure [12], [10], [13], [14].”
BackgroundTraining a Convolutional Neural Network for Appearance-Invariant Place RecognitionPreprint
Gomez-Ojeda, R., López-Antequera, M., Petkov, N., & González-Jiménez, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.07428 · Cited by 70
“One of the first SLAM techniques which introduced BoW in this context was FAB-MAP [5], where a probabilistic approach to place recognition based on the local appearance of each location was proposed.”
MethodAccurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
Shi, Y., Yu, X., Liu, L., Campbell, D., Koniusz, P., & Li, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3189702 · Cited by 101
Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
Garg, S., Harwood, B., Anand, G., & Milford, M. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3005627 · Cited by 63
“It is worth noting that a subsequent geometric verification step, commonly employed in hierarchical localization pipelines [39], [49], [50], can further improve the precision performance.”
BackgroundMethodLeveraging experience for large-scale LIDAR localisation in changing cities
Maddern, W., Pascoe, G., & Newman, P. M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139414 · Cited by 59
“Instead we make use of a stereo camera mounted on the vehicle, and perfom an offline multisession pose graph optimisation combining visual odometry and loop closures provided by FAB-MAP [30] to form a globally consistent ground-truth metric map.”
MethodSelf-citationCity scale geo-spatial trajectory estimation of a moving camera
Vaca-Castano, G., Zamir, A., & Shah, M. A. (2012) · 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/cvpr.2012.6247800 · Cited by 57
“The average frame-by-frame error of the first step of FAB-MAP algorithm was 441.01 meters.”
MethodInfluentialDirect Visual Localisation and Calibration for Road Vehicles in Changing City Environments
Pascoe, G., Maddern, W., & Newman, P. M. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.23 · Cited by 60
“Starting from an initial guess ĜCW provided by the previous vehicle position or a weak localiser such as GPS or image retrieval [7], we seek to solve (1) using an optimisation framework.”
MethodInfluentialSelf-citationA systematic literature review on long‐term localization and mapping for mobile robots
Sousa, R. B., Sobreira, H., & Moreira, A. P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22170 · Cited by 68
Parallel, real-time visual SLAM
Clipp, B., Lim, J., Frahm, J., & Pollefeys, M. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5653696 · Cited by 52
“Please note, any alternative approach like the Fab-Map [3] approach of Cummins and Newman could be used instead.”
MethodRobust place recognition with stereo cameras
Cadena, C., Gálvez-López, D., Ramos, F., Tardós, J. D., & Neira, J. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650234 · Cited by 54
“Some techniques derived from BoW have been successfully applied to loop closing-related problems ([2], [3]) but exhibit false positives.”
BackgroundMethodVisual Loop Closing using Gist Descriptors in Manhattan World
Singh, G. B. (2010) · Cited by 52
Point cloud descriptors for place recognition using sparse visual information
Cieslewski, T., Stumm, E. S., Gawel, A., Bosse, M., Lynen, S., & Siegwart, R. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487687 · Cited by 57
“Many visual place recognition techniques utilize bag-ofwords algorithms borrowed from the text and image retrieval communities [5] [6], along with adaptations to probabilistic frameworks which deal with perceptual aliasing [7].”
MethodGraph-Based Place Recognition in Image Sequences with CNN Features
Zhang, X., Wang, L., Zhao, Y. C., & Su, Y. L. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0917-2 · Cited by 56
“We compare our method with FAB-MAP [10], which has been widely used as a standard place recognition algorithm and has achieved state-of-the-art performance for visual place recognition.”
MethodInfluentialSemantic Mapping for View-Invariant Relocalization
Li, J., Meger, D., & Dudek, G. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793624 · Cited by 59
“Earlier work such as FAB-MAP [12], [13] that is based purely on matching local appearance-based features have been shown to be susceptible to changes in condition (e.g. changes in illumination, weather, season, time of day) [14].”
MethodA Neurologically Inspired Sequence Processing Model for Mobile Robot Place Recognition
Neubert, P., Schubert, S., & Protzel, P. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2927096 · Cited by 54
“Beyond simple pairwise comparison and using statistics of feature appearances (e.g. FAB-MAP [13]), the benefit of exploiting sequence information is well accepted in the literature: For SeqSLAM, Milford et al. [2] proposed to search for linear segments of high similarity in the pairwise similarity matrix after a local…”
Modest-vocabulary loop-closure detection with incremental bag of tracked words
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103782 · Cited by 53
Real-time monocular image-based 6-DoF localization
Lim, H., Sinha, S. N., Cohen, M. F., Uyttendaele, M., & Kim, H. J. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364914561101 · Cited by 58
“…in autonomous robot navigation (Royer et al., 2007; Achtelik et al., 2011; Meier et al., 2012), place recognition (Robertson and Cipolla, 2004; Schindler et al., 2007; Cummins and Newman, 2008; Milford, 2013) and augmented reality (Klein and Murray, 2007; Dong et al., 2009; Wagner et al., 2010).”
BackgroundChen, Y., Yang, J., Wang, C., & Liu, N. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.07.009 · Cited by 56
Convolutional networks for real-time 6-DOF camera relocalization.Preprint
Kendall, A., Grimes, M. K., & Cipolla, R. (2015) · arXiv (Cornell University) · Cited by 50
Keyframe detection for appearance-based visual SLAM
Zhang, H., Li, B. H., & Yang, D. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650625 · Cited by 56
“To address these challenges, more recently, appearancebased visual SLAM (aSLAM) has been introduced [7], [3].”
BackgroundRobust visual semi-semantic loop closure detection by a covisibility graph and CNN features
Cascianelli, S., Costante, G., Bellocchio, E., Valigi, P., Fravolini, M. L., & Ciarfuglia, T. A. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.004 · Cited by 54
Graph-Based Thermal–Inertial SLAM With Probabilistic Neural Networks
Saputra, M. R. U., Lu, C. X., de Gusmão, P. P. B., Wang, B., Markham, A., & Trigoni, N. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3120036 · Cited by 62
A realistic benchmark for visual indoor place recognition
Pronobis, A., Caputo, B., Jensfelt, P., & Christensen, H. I. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.025 · Cited by 55
“As a result, this research line is attracting more and more attention, and several methods have been proposed using vision alone [56,48,51,17], or combined with more traditional range sensors [28,53,50].”
BackgroundMethodInfluentialTopological local-metric framework for mobile robots navigation: a long term perspective
Tang, L., Wang, Y., Ding, X., Yin, H., Xiong, R., & Huang, S. (2018) · Autonomous Robots · doi:10.1007/s10514-018-9724-7 · Cited by 53
“The other is to find the topological localization through place recognition (Lowry et al. 2016; Churchill and Newman 2013; Milford and Wyeth 2012; Cummins and Newman 2008).”
BackgroundMethodInfluentialVisual Localization by Learning Objects-Of-Interest Dense Match Regression
Weinzaepfel, P., Csurka, G., Cabon, Y., & Humenberger, M. (2019) · 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/cvpr.2019.00578 · Cited by 51
“Interesting applications include robot navigation [8], self-driving cars and augmented reality (AR) [6, 22].”
BackgroundCondition-Invariant Multi-View Place RecognitionPreprint
Fácil, J. M., Olid, D., Montesano, L., & Civera, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09516 · Cited by 54
“Feature-based approaches ( e.g. , FAB-MAP [18] and DBoW [6]), relying on local information around salient points, are more robust to those changes.”
BackgroundSpatio-temporal feature-based keyframe detection from video shots using spectral clustering
Vázquez-Martín, R., & Bandera, A. J. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.009 · Cited by 47
Sky segmentation with ultraviolet images can be used for navigation
Stone, T., Mangan, M., Ardin, P., & Webb, B. H. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.047 · Cited by 49
“The ant’s compound eye provides very coarse resolution (on the order of 4° per pixel), and thus is unlikely to be capable of extracting and matching many distinct features, a capacity which is fundamental to many current visual Simultaneous localisation and mapping (SLAM) methods (e.g. [5]).”
BackgroundBidirectional loop closure detection on panoramas for visual navigation
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., Yebes, J. J., & Gamez, S. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856457 · Cited by 52
“A set of experiments considering several binary descriptors (ORB, BRISK, FREAK, LDB) is provided, where LDB excels as the most suitable.”
MethodCNN Feature Boosted SeqSLAM for Real‐Time Loop Closure Detection
Bai, D., Wang, C., Zhang, B., Yi, X., & Yang, X. (2018) · Chinese Journal of Electronics · doi:10.1049/cje.2018.03.010 · Cited by 49
Fast and Incremental Loop Closure Detection Using Proximity Graphs
An, S., Che, G., Zhou, F., Liu, X., Ma, X., & Chen, Y. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968043 · Cited by 51
“With the increase in computing power, the mobile robots not only use range and bearing sensors such as laser scanners [3], radars and sonars [4], but also use single cameras [5] or stereo-camera rigs [6].”
BackgroundMethodActive SLAM using 3D Submap Saliency for Underwater Volumetric Exploration
Suresh, S., Sodhi, P., Mangelson, J. G., Wettergreen, D. S., & Kaess, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196939 · Cited by 56
“A bag-of-words (BoW) representation [26] creates a scene dictionary, which can be used for online loop closure detection [27].”
BackgroundIndoor Localization Algorithms for an Ambulatory Human Operated 3D Mobile Mapping System
Corso, N., & Zakhor, A. (2013) · Remote Sensing · doi:10.3390/rs5126611 · Cited by 53
Let the Light Guide Us: VLC-Based Localization
Qiu, K., Zhang, F., & Liu, M. (2016) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2016.2591833 · Cited by 47
A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation
Sepulveda, G., Niebles, J. C., & Soto, Á. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460646 · Cited by 50
Augmenting Visual Place Recognition With Structural Cues
Oertel, A., Cieslewski, T., & Scaramuzza, D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3009077 · Cited by 51
“Related research has focused on various ways to efficiently match such local features and to meaningfully aggregate them for generating matches between full images [2], [7]–[12].”
BackgroundMagnenat, S., Philippsen, R., & Mondada, F. (2012) · Autonomous Robots · doi:10.1007/s10514-012-9296-x · Cited by 50
“Recent studies have explored the use of vision (Cummins and Newman 2008) and range data (Beeson et al. 2010), and some have shown how to take the odometry readings into account (Sabatta et al. 2010).”
Correcting Scale Drift by Object Recognition in Single-Camera SLAM
Botterill, T., Mills, S. J., & Green, R. (2012) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2230164 · Cited by 49
Transforming morning to afternoon using linear regression techniques
Lowry, S. M., Milford, M. J., & Wyeth, G. F. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907432 · Cited by 46
“Visual localization can perform strongly on outdoor environments in situations where the enviro undergo drastic perceptual change [1-3].”
BackgroundSRAL: Shared Representative Appearance Learning for Long-Term Visual Place Recognition
Han, F., Yang, X., Deng, Y., Rentschler, M. E., Yang, D., & Zhang, H. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2662061 · Cited by 45
“Notation: In this paper, matrices are written as boldface, capital letters, and vectors are written as boldface lowercase letters.”
BackgroundSemantically guided location recognition for outdoors scenes
Mousavian, A., Košecká, J., & Lien, J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139877 · Cited by 44
“Various improvements of BoW methods include learning better vocabularies, developing better quantization and spatial verification methods [15], [25], [26], employing more sophisticated models of dependence of local features [4] or improving the scalability [20].”
BackgroundMethodAutoPlace: Robust Place Recognition with Single-chip Automotive Radar
Cai, K., Wang, B., & Lu, C. X. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811869 · Cited by 56
3D Point Cloud Reduction Using Mixed-Integer Quadratic Programming
Park, H. S., Wang, Y., Nurvitadhi, E., Hoe, J. C., Sheikh, Y. A., & Chen, M. (2013) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2013.41 · Cited by 44
“Using this reduced database, we present a novel criterion for finding 2D-3D correspondences in Section 3.2.”
MethodInfluentialLoop closure detection for visual SLAM using PCANet features
Xia, Y., Li, J., Qi, L., & Fan, H. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727481 · Cited by 44
“Bag-of-Words (BoW) is widely used in loop closure detection for visual SLAM [22] [23] [24].”
BackgroundMethodInfluentialWide-angle Visual Feature Matching for Outdoor Localization
Hansen, P., Corke, P., & Boles, W. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909356484 · Cited by 55
“However most of these works, with some exceptions such as Daniilidis et al. (2002) and Hansen et al. (2007a), use SIFT and other standard image processing algorithms such as KLT (Lucas and Kanade 1981 Tomasi and Kanade 1991).”
BackgroundMethodInfluentialNguyen, Q.-H., Vu, H., Tran, T.-H., & Nguyen, Q.-H. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-015-3204-2 · Cited by 46
“As clarified in the original work [5], to capture the co-occurrence of visual words in the scene, a Chow Liu tree is utilized to approximate the probability distribution over these visual words and the correlations among them [4].”
BackgroundMethodInfluentialEncoding the description of image sequences: A two-layered pipeline for loop closure detection
Bampis, L., Amanatiadis, A. A., & Gasteratos, A. C. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759667 · Cited by 42
“A well known method adopting a technique based on the first category –also known as appearance-based place recognition– is the FAB-MAP [7], according to which, a Bag of Visual Words (BVW) is created and used to measure the similarity between the acquired images.”
MethodExploiting artificial intelligence for digitally enriched museum visits
Ioannakis, G., Bampis, L., & Koutsoudis, A. (2019) · Journal of Cultural Heritage · doi:10.1016/j.culher.2019.07.019 · Cited by 46
Robot Teams for Intervention in Confined and Structured Environments
Tardioli, D., Sicignano, D., Riazuelo, L., Romeo, A., Villarroel, J. L., & Montano, L. (2015) · Journal of Field Robotics · doi:10.1002/rob.21577 · Cited by 41
“Concerning appearance methods, some of them have been applied for place recognition (Mozos, Rottmann, Triebel, Jensfelt, & Burgard, 2007), for SLAM at a topological level (Cummins & Newman, 2008; Newman, Cole, & Ho, 2006), and for navigation purposes (Booij, Terwijn, Zivkovic, & Krose, 2007).”
MethodLighting‐invariant Visual Teach and Repeat Using Appearance‐based Lidar
McManus, C., Furgale, P., Stenning, B. E., & Barfoot, T. D. (2012) · Journal of Field Robotics · doi:10.1002/rob.21444 · Cited by 44
“In addition, we also wish to explore place recognition systems such as FABMAP (Cummins and Newman, 2008) in order to exploit loop closures and add connections to our pose graph network.”
BackgroundProbabilistic place recognition with covisibility maps
Stumm, E., Mei, C., & Lacroix, S. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696952 · Cited by 42
“This approach is different from that used in other place recognition frameworks such as FAB-MAP [4].”
BackgroundMethodInfluentialPlace recognition using straight lines for vision-based SLAM
Lee, J. H., Zhang, G., Lim, J., & Suh, I. H. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631111 · Cited by 41
Large-Scale Volumetric Scene Reconstruction using LiDAR
Kühner, T., & Kümmerle, J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197388 · Cited by 43
“We then run the OpenFABMAP place recognition algorithm [28], which is an open source implementation of [29], to determine pose associations L = { ( T s , T d ) 1 . . . ( T s , T d ) l } .”
MethodCore Challenges in Embodied Vision-Language Planning
Francis, J., Kitamura, N., Labelle, F., Lu, X., Navarro, I., & Oh, J. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13646 · Cited by 62
Lai, T. (2022) · Sensors · doi:10.3390/s22197265 · Cited by 55
“Loop-closing can detect if a given keyframe had been seen previously [34], [35].”
BackgroundASL-SLAM: A LiDAR SLAM With Activity Semantics-Based Loop Closure
Zhou, B., Li, C., Chen, S., Xie, D., Yu, M., & Li, Q. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3270871 · Cited by 43
“Among image-based methods, bag-of-words (BOW) [29], [30] is the most famous.”
Neubert, P., & Protzel, P. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2517824 · Cited by 41
Viewpoint-Tolerant Place Recognition Combining 2D and 3D Information for UAV Navigation
Maffra, F., Chen, Z., & Chli, M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460786 · Cited by 40
“To this end, the BoBW descriptor of Q is scored based on its L1-distance to Database entries, using a ‘term frequency–inverse document frequency’ (tfidf) weighting scheme [27] to suppress commonly occurring words to form the set S of matching keyframe candidates.”
MethodBenchmarking 6-DOF Outdoor Visual Localization in Changing ConditionsPreprint
Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Šivic, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.09092 · Cited by 51
“We use three 2D image-based methods for experimental evaluation, namely DenseVLAD [77], NetVLAD [2], and FAB-MAP [18].”
MethodMeilland, M., Comport, A. I., & Rives, P. (2014) · Journal of Field Robotics · doi:10.1002/rob.21531 · Cited by 49
“A dedicated technique such as that in Chapoulie et al. (2011) and Cummins & Newman (2008) will be investigated in future work.”
MethodRobust Multimodal Sequence-Based Loop Closure Detection via Structured Sparsity
Zhang, H., Han, F., & Wang, H. (2016) · Robotics: Science and Systems · doi:10.15607/rss.2016.xii.043 · Cited by 39
“FAB-MAP [6, 7] utilized the Speeded Up Robust Features (SURF) for visual loop closure detection.”
BackgroundMethodInfluentialDeepLocalization: Landmark-based Self-Localization with Deep Neural Networks
Engel, N., Hoermann, S., Horn, M., Belagiannis, V., & Dietmayer, K. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917005 · Cited by 45
“GPS, with a high-precision map to estimate the vehicle’s pose [6], [7], [8].”
Full-Frame Scene Coordinate Regression for Image-Based Localization
Li, X., Ylioinas, J., & Kannala, J. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.015 · Cited by 49
Robust Loop Closure Detection based on Bag of SuperPoints and Graph Verification
Yue, H., Miao, J., Yu, Y., Chen, W., & Wen, C. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967726 · Cited by 43
“One of the most influential BoW-based LCD algorithms is FAB-MAP [19].”
MethodInfluentialWen, S., Zhao, Y., Liu, X., Sun, F., Lu, H., & Wang, Z. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3041852 · Cited by 41
“Some common loop closure detection methods (e.g. BoW) are based on indexed image features [14], [34], [35].”
MethodRGB-D based cognitive map building and navigation
Tian, B., Shim, V. A., Miaolong, Y., Srinivasan, C., Tang, H., & Li, H. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696557 · Cited by 49
“FAB-MAP does not rely on a filter, but depends on the accurate comparison derived from speeded up robust features(SURF) descriptors.”
BackgroundImproved Visual Relocalization by Discovering Anchor PointsPreprint
Saha, S., Varma, G., & Jawahar, C. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.04370 · Cited by 54
“The visual place recognition task has been traditionally solved by modeling it as an image retrieval problem [1], [5], [27], [21].”
Model-Based Global Localization for Aerial Robots Using Edge Alignment
Qiu, K., Liu, T., & Shen, S. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2660063 · Cited by 38
“Global localization solutions based on place recognition [1], [2] can only obtain topological localization which is not accurate enough for closed-loop flight control.”
BackgroundAn Evaluation of Deep Learning in Loop Closure Detection for Visual SLAM
Xia, Y., Li, J., Qi, L., Yu, H. L., & Dong, J. (2017) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata.2017.18 · Cited by 42
“[16] M. Cummins and P. Newman, “FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance,” The International Journal of Robotics Research, vol. 27, pp. 647–665, June 2008.”
MethodInfluentialVisual Place Recognition by spatial matching of high-level CNN features
Camara, L. G., & Přeučil, L. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103625 · Cited by 47
“Visual place recognition has been traditionally approached in the literature as an image retrieval task, using Bag of (visual) Words (BoW) models [10, 19, 20, 21] or the closely related VLAD [22, 23, 24] and Fisher vec-3 tors [25, 26].”
MethodLi, Z., Shang, T., Xu, P., & Deng, Z. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11367-8 · Cited by 50
“19, the sequence-based visual place recognition methods—SeqSLAM, FAB-MAP, DBoW, MRS-VPR, and OpenSeqSLAM 2.0—exhibit varying performance across datasets characterized by different environmental complexities.”
Influential
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.