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 901–1,000 of 1,002
Khaliq, A., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.08153 · Cited by 11
“Other approaches includes HOG, SURF, FAST [26], GIST [27], FABMAP [19] and SEQSLAM [20].”
MethodSequential Place Learning: Heuristic-Free High-Performance Long-Term Place RecognitionPreprint
Chancán, M., & Milford, M. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02074 · Cited by 6
“This allows us to compare our approach against five other methods such as FAB-MAP [10], VLAD-based [25], SMART [35], CNN+Seq [8], Robust Image-sequence-based framework (RISF) [44], in addition to SeqSLAM and the baseline network.”
Unsupervised mapping and semantic user localisation from first-person monocular video
Süveges, T., & McKenna, S. J. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110923 · Cited by 5
Hierarchical loop closure detection with weighted local patch features and global descriptors
Ren, M., Zhang, X., Liu, B., & Zhu, Y. (2025) · Applied Intelligence · doi:10.1007/s10489-024-06135-0 · Cited by 4
“For offline methods, the most influential LCD scheme is FAB-MAP, which was proposed by M. Cummins and P. Newman [21].”
Loop Closure Detection with a Holistic Image Feature
Campos, F. M., Correia, L. M. P., & Calado, J. M. F. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40669-0_22 · Cited by 5
Visual place recognition based on multilevel descriptors for the visually impaired people
Fang, Y., Wang, K., Cheng, R., Yang, K., & Bai, J. Y. (2019) · Target and Background Signatures · doi:10.1117/12.2532524 · Cited by 5
Day and Night Place Recognition Based on Low-quality Night-time Images
Liu, L., Cappelle, C., & Ruichek, Y. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294480 · Cited by 5
“ToDayGAN improves the performance by over 250% in recognizing places that underwent drastically different illumination conditions compared to other state-of-art approaches like ActiveSearch [11], CSL [12], FAB-MAP [4] and NetVLAD [2].”
BackgroundVisual Loop Closure Detection for a Future Mars Science Helicopter
Dietsche, A., Ott, L., Siegwart, R., & Brockers, R. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3207547 · Cited by 4
“FAB-MAP [12] casts the recognition problem in a probabilistic manner by learning a generative model of a place’s appearance.”
BackgroundZhang, X., Cui, Y., Ren, Y., Duan, G., & Zhang, H. (2024) · Remote Sensing · doi:10.3390/rs16163038 · Cited by 4
“The calculation method is shown in the following formula [44]: where ¯ I ( x , y ) is the mean grayscale value within the grid, the grid’s width is W, and the height is H.”
MethodMatched Filtering Based LiDAR Place Recognition for Urban and Natural Environments
Joseph, T., Fischer, T., & Milford, M. J. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3533966 · Cited by 7
Unified Depth-Guided Feature Fusion and Reranking for Hierarchical Place Recognition
Li, K., Ou, Y., Ning, J., Kong, F., Cai, H., & Li, H. (2025) · Sensors · doi:10.3390/s25134056 · Cited by 6
“…to verify that our method can be applied to the practical loop closure detection tasks of robots, we selected two commonly used datasets for loop closure detection, New College [68] and City Centre [69], for experimental testing and compared ours with several state-of-the-art two-stage methods.”
Mobile robot global localization with non-quantized SIFT features
Campos, F. M., Correia, L. M. P., & Calado, J. M. F. (2011) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2011.6088564 · Cited by 4
“Realizing that these effects can be lessened with more discriminating sensor models, researchers have proposed solutions that include complex sensor models [1] or features invariant to environmental factors such as lighting”
BackgroundExact Primitives for Time Series Data Mining
Mueen, S. A. (2012) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2339530.2378374 · Cited by 4
“In an effort to verify this utility, we use the “New College” dataset [25], where a set of 2,146 images have been collected by a moving robot.”
MethodLowry, S. M., & Milford, M. J. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353801 · Cited by 4
“On the other hand, if the environment has changed very little, highly permissive matching will cause false positive matches, and a stricter matching strategy which enforces high appearance similarity should be used [1].”
BackgroundMethodInfluentialVision-Based Hybrid Map Building for Mobile Robot Navigation
Üzer, F., Korrapati, H., Royer, E., Mezouar, Y., & Lee, S. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_11 · Cited by 4
Zhang, K., & Zhang, W. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8244215 · Cited by 4
“City Center open dataset of FAB-MAP [16] is used to be the input of the model.”
MethodCondition and Viewpoint Invariant Omni-Directional Place Recognition Using CNN
Kumar, D., Neher, H., Das, A., Clausi, D. A., & Waslander, S. L. (2017) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2017.26 · Cited by 4
“In the past, numerous place recognition methods have been proposed for large scale environment localization, including FAB MAP [11], [23], MonoSLAM [24] and SeqSLAM [20], but, there are very few long term localization place recognition systems [5], [25].”
BackgroundOnline 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
“To address the problems above, we propose a method which is not only utilize an appearance-based method [3] but also bridges disconnected feature-tolandmark relations inspired by image-based localization.”
MethodUsing 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
“While loop-closure can redistribute and reduce accumulated error [14] [7], [28], [6], the error in location can be so severe, as evident in Fig.”
BackgroundAn improved bag of words method for appearance based visual loop closure detection
Zhu, H., Xie, L., Yu, H., & Liujun, W. (2018) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2018.8408123 · Cited by 5
Autonomous Urban Localization and Navigation with Limited Information
Chipka, J. B., & Campbell, M. (2018) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2018.8500693 · Cited by 5
“For example, FAB-MAP, a topological SLAM technique, has been shown to allow for appearance-based navigation [7].”
MethodSimilarity criteria: evaluating perceptual change for visual localization
Lowry, S. M. (2019) · European Conference on Mobile Robots · doi:10.1109/ecmr.2019.8870962 · Cited by 5
“Confidence metrics have typically been provided by frameworks such as probabilistic localization systems [7], [8], [9].”
BackgroundAn efficient edge-feature constraint visual SLAM
Liu, W., Mo, Y., & Jiao, J. (2019) · International Conference on Artificial Intelligence, Information Processing and Cloud Computing (AIIPCC) · doi:10.1145/3371425.3371455 · Cited by 4
Lost in the Woods? Place Recognition for Navigation in Difficult Forest Environments
Garforth, J., & Webb, B. H. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.541770 · Cited by 5
“Three state of the art loop closure algorithms are compared in Lowry and Andreasson (2018): a binary Bag of Words (BoW) model similar to that used in ORBSLAM2 (GálvezLópez and Tardós, 2012; Mur-Artal and Tardós, 2017), FABMAP (Cummins and Newman, 2008), and a Vectors of Locally Aggregated Descriptors (VLAD, Jégou et a…”
MethodSequence-based visual place recognition: a scale-space approach for boundary detection
Bampis, L., & Gasteratos, A. C. (2021) · Autonomous Robots · doi:10.1007/s10514-021-09984-7 · Cited by 4
“In the later work of FAB-MAP 2.0 (Cummins and Newman 2011), a sparse approximation of the above method was implemented scaling the system by more than two orders of magnitude.”
MethodInfluentialSV-Loop:Semantic-Visual Loop Closure Detection with Panoptic Segmentation
Yuan, Z., Xu, K., Deng, B., Zhou, X., Chen, P., & Ma, Y. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688756 · Cited by 4
“FAB-MAP [11] is one of the classic loop closure methods in monocular SLAM and achieved brilliant experimental results.”
Kasebi, S. S., Seyedarabi, H., & Niya, J. M. (2021) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke54056.2021.9721522 · Cited by 4
Loop Closure Detection for Visual SLAM Systems Based on Convolutional Netural Network
Shi, X., & Li, L. (2021) · IEEE International Conference on Computational Science and Engineering (CSE) · doi:10.1109/cse53436.2021.00027 · Cited by 4
Loop-Closure Detection with 3D LiDAR Data for Extreme Viewpoint Changes
Alexiou, D., Tsiakas, K., Kostavelis, I., Giakoumis, D., Gasteratos, A. C., & Tzovaras, D. K. (2022) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar55195.2022.9874344 · Cited by 4
“For this reason, local descriptors, being more robust in geometrical transformations, have been widely used in visual localization methods [24].”
MethodTLCD: A Transformer based Loop Closure Detection for Robotic Visual SLAM
Li, C., Ren, H., Bi, M., Ding, C., Li, W., Zhang, R., Liu, X., & Yu, H. (2022) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm54641.2022.9959319 · Cited by 4
“The FAB-Map [12] algorithm proposed by Cummins et al. used SURF features and has achieved good results.”
MethodLi, Y., Wu, W., & Zhu, H. (2023) · Applied Sciences · doi:10.3390/app13116481 · Cited by 4
Gutiérrez-Gómez, D., Mayol-Cuevas, W. W., & Guerrero, J. J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139963 · Cited by 4
A robust semi-semantic approach for visual localization in urban environment
Cascianelli, S., Costante, G., Bellocchio, E., Valigi, P., Fravolini, M. L., & Ciarfuglia, T. A. (2016) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc2.2016.7580799 · Cited by 4
“The selected algorithm is the well-known FABMAP [23] • A technique that is based on the high level features extracted by Edge Boxes and AlexNet conv3, that were also used in our work, but does not use any graph-based representation of the environment, namely the approach proposed by Sunderhauf et al. in [11].”
MethodResultInfluentialQuickSketch: Building 3D Representations in Unknown Environments Using Crowdsourcing
Ahmad, F., Qiu, H., Liu, X., Bai, F., & Govindan, R. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455437 · Cited by 4
“Third, the BoW model depends only on the frequency of visual features and so, images containing common features e.g., stop signs, windows, street lights etc. , have a high similarity score [7], resulting in the large errors shown in Figure 11 for image matching.”
ResultConvolutional Autoencoder aided loop closure detection for monocular SLAM
Leonardi, M., & Stahl, A. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.09.486 · Cited by 5
BTEL: A Binary Tree Encoding Approach for Visual Localization
Le, H., Hoang, T., & Milford, M. J. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2932580 · Cited by 5
“In addition to the traditional methods for visual place recognition such as SeqSLAM [3] or FAB-MAP [5], the main contributing factors to the recent success of visual similarity search are arguably the advances in learning image representations [6], the strong developments in state-of-theart quantization techniques and…”
MethodImproved Deep Distance Learning for Visual Loop Closure Detection in Smart City
Jin, S., Gao, Y. H., & Chen, L. (2020) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-019-00861-w · Cited by 4
Regional Relation Modeling for Visual Place Recognition
Zhu, Y., Li, B., Wang, J., & Zhao, Z. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401176 · Cited by 5
“In this paper, we tackle the Visual Place Recognition (VPR) task which has consistently attracted considerable attention in computer vision [2, 4, 8, 56] and robotics communities [9, 10, 35, 60].”
MethodSPRINT: Subgraph Place Recognition for INtelligent Transportation
Latif, Y., Doan, A.-D., Chin, T.-J., & Reid, I. D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196522 · Cited by 4
“In contrast to loop closure detection which aims to recover the robot’s (mostly 6-DoF) pose with respect to a previously built map [6, 9, 17], place recognition is topological in nature, that is, it matches the current query image to one of the previously seen images (or the indices thereof) that…”
BackgroundInterval Inspired Approach Based on Temporal Sequence Constraints to Place Recognition
Neuland, R., Rodrigues, F., Pittol, D., Jaulin, L., Maffei, R. D. Q., Kolberg, M., & Prestes, E. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-021-01375-5 · Cited by 4
“Considering an interval [x] = [7; 10], as an example, it is associated with four images, thus, to four descriptors:”
BackgroundMethodInfluentialDeep Next-Best-View Planner for Cross-Season Visual Route Classification
Kurauchi, K., & Kanji, T. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412043 · Cited by 5
“They are largely divided into global [15] and local feature approaches [16].”
BackgroundVG-SSL: Benchmarking Self-Supervised Representation Learning Approaches for Visual Geo-Localization
Xiao, J., Zhu, G., & Loianno, G. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00649 · Cited by 9
“Traditional VG approaches [17, 18, 24, 33] rely on handcrafted templates, which are generally less resilient to noise and appearance changes (e.g., illumination).”
Appearance and map-based global localization using laser reflectivity
Zhang, D., Kurazume, R., Iwashita, Y., & Hasegawa, T. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181420 · Cited by 5
“In [3], the authors didn’t evaluate the experimental results explicitly under large changes of illumination.”
BackgroundTopological Mapping with Image Sequence Partitioning
Korrapati, H., Courbon, J., & Mezouar, Y. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-35485-4_3 · Cited by 4
Probabilistic qualitative mapping for robots
Padgett, J., & Campbell, M. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487750 · Cited by 4
Computing Egomotion with Local Loop Closures for Egocentric Videos
Patra, S., Aggarwal, H., Arora, H., Banerjee, S., & Arora, C. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.57 · Cited by 4
“Newman [24] use visual features for image-to-image loop-closures.”
Ran, L., Zhang, Y., Yang, T., & Chen, T. (2016) · International Conference on Advances in Mobile Computing and Multimedia (MoMM) · doi:10.1145/3007120.3011073 · Cited by 4
“Various systems have been proposed, for example, MonoSLAM [5], PTAM [13], FAB-MAP [4], DTAM [20], KinectFusion [19], etc. Recently, Caruso et al. [1] successfully accomplish a SLAM system for direct use of omnidirectional cameras.”
MethodRojas-Castro, D. M., Revel, A., & Ménard, M. (2020) · International Journal of Social Robotics · doi:10.1007/s12369-019-00602-2 · Cited by 5
Bio-inspired Multi-scale Visual Place Recognition for the Aerial Vehicle Navigation
Fan, C., Jacobson, A., Chen, Z., He, X., Zhang, L., Hu, X., & Milford, M. J. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8155-7_87 · Cited by 4
Adaptation and Learning for Image Based Navigation
Achar, S., & Jawahar, C. V. (2008) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1109/icvgip.2008.72 · Cited by 4
“In [1] a Bayesian approach to Bag-of-Words localization is presented.”
MethodPlace Recognition for Indoor Blind Navigation
Brett Browning, A., & Dias, M. B. (2011) · Cited by 4
Towards CNN Map Compression for camera relocalisationPreprint
Contreras, L., & Mayol-Cuevas, W. W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00845 · Cited by 4
“From a human observer point of view, it is common to think of metric or topological relationships among elements in space to build maps; for this reason, metric and topological are two well known map representations (such as [24], [25], and [26]).”
BackgroundEfficient Condition-based Representations for Long-Term Visual Localization.Preprint
Germain, H., Bourmaud, G., & Lepetit, V. (2018) · arXiv (Cornell University) · Cited by 4
Feature Matching via Graph Clustering with Local Affine Consensus
Lu, Y., & Ma, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02291-5 · Cited by 5
MDAG-Net: Multidomain Association-Guided Network for Image-Based Long-Term Visual Localization
Ge, F., Zhang, Y., Wang, L., Tan, Y., Coleman, S., & Kerr, D. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2024.3525180 · Cited by 3
“FAB-MAP [56], DIFL-FCL [22], NetVLAD [30], DenseVLAD [31] and DISAM [23] are chosen for performance comparison as these are considered state-of-the-art image-based localization methods.”
Robot localization: a comprehensive survey from classical methods to intelligent autonomy
Alipourvarmazabadi, M., & Ebner, M. (2026) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-026-00528-9 · Cited by 5
“The resulting maps are well suited for incremental SLAM and revisiting previously seen places via appearance-based loop closure (Cummins and Newman 2008; Galvez-López and Tardós 2012).”
InfluentialLong-term Visual Place Recognition
Alijani, F., Peltomäki, J., Puura, J., Huttunen, H. J., Kämäräinen, J., & Rahtu, E. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956392 · Cited by 4
“To highlight a few, New College and City Centre [5], KITTI Odometry benchmark [19], Ford campus [20], extended CMU seasons [21], [22], Mapillary Street-level [23], M´alaga Urban [24], Alderley [4], Aachen Day-Night [25] and Nordland [26] are the outdoor and InLoc [27], ETH-Microsoft [28], and NAVER…”
Efficiently closing loops in LiDAR-based SLAM using point cloud density maps
Gupta, S., Guadagnino, T., Mersch, B., Trekel, N., Malladi, M. V. R., & Stachniss, C. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261449269 · Cited by 7
“Place recognition has been widely studied in the context of camera images [8], [14], [40], [59], [60].”
Localization independent of location based on place recognition and GPS observations
Saito, T., & KURODA, Y. (2012) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2012.6426958 · Cited by 3
An image-to-image loop-closure detection method based on unsupervised landmark extraction
Sarıyanidi, E., Şencan, O., & Temeltaş, H. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232174 · Cited by 3
“The importance of loop closure detection for Simultaneous Localization and Mapping (SLAM) algorithms has been established by several authors [10], [4], [16].”
BackgroundMethodA localization based on a space observation model in a crowded environment
Muramatsu, S., Tomizawa, T., Kudoh, S., & Suehiro, T. (2012) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2012.6265964 · Cited by 3
“Various localization techniques by landmark matching have been studied, for example, localization by using a camera sensor [3] and a magnetic sensor [4].”
MethodDevelopment of the robust delivery robot system with the unknown object in indoor environment
Muramatsu, S., Takahashi, K., Tomizawa, T., Kudoh, S., & Suehiro, T. (2013) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2013.6700518 · Cited by 3
“As the method of position presumption, techniques using markers[1], RFID[2], a landmark[3], and an environmental installation type camera[4][5] were proposed.”
MethodDivergence-based Dynamic Sensor Fusion for Robust Localization Using Particle Filter
Suyama, K., Funabora, Y., Doki, S., & Doki, K. (2017) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.53.169 · Cited by 3
c-M2DP: A Fast Point Cloud Descriptor with Color Information to Perform Loop Closure Detection
Perdomo, L., Pittol, D., Mantelli, M., Maffei, R. D. Q., Kolberg, M., & Prestes, E. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8842896 · Cited by 3
“While there is a significant amount of visual based methods exploiting 2D camera features to accomplish loop closure detection [2]–[4], few approaches employ 3D sensor readings such as LIDAR or stereo cameras.”
MethodMishra, R., Vineel, C., & Javed, A. (2020) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar49639.2020.9108074 · Cited by 3
Moreira, L. A. S., Justel, C. M., Oliveira, J. C. D., & Rosa, P. F. F. (2020) · Robotica · doi:10.1017/s0263574720000570 · Cited by 3
“We considered the New College dataset, 19 a benchmark widely used by researchers in recognition and visual mapping, as an example of application of our method.”
MethodScene-Unified Image Translation For Visual Localization
Han, S., Gao, W., Wan, Y., & Wu, Y. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190885 · Cited by 4
“…2D-3D matches between features in a query image and the 3D scene model, while image-based methods such as Den-seVLAD [5], NetVLAD [6], and FAB-MAP [7] utilize the extracted global descriptors for retrieval, and then the pose of the nearest image retrieved is regarded as the pose of the query…”
BackgroundMethodPL‐VSCN: Patch‐level vision similarity compares network for image matching
You, X., Li, Q., Li, K., Yu, A., & Bu, S. (2021) · IET Computer Vision · doi:10.1049/cvi2.12018 · Cited by 3
“The CNN feature and spatial relation are effectively integrated in the similarity measurement model, and the method can effectively complete the loop closure detection task in SLAM.”
BackgroundSLAM Loop Detection Algorithm Based on Improved Bag-of-Words Model
Xi, K., He, J., Hao, S., & Luo, L. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904167 · Cited by 3
SO-PFH: Semantic Object-based Point Feature Histogram for Global Localization in Parking Lot
Lv, J., Meng, C., Wang, Y., Sun, J., Xiong, R., & Pu, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981094 · Cited by 4
“Among these methods, the appearance-based method has been deeply investigated and successfully applied in various mapping and localization tasks [2][3].”
MethodLoop Closure Detection With Bidirectional Manifold Representation Consensus
Zhang, K., Li, Z., & Ma, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3229364 · Cited by 3
“For example, the gold standard approach regarding LCD, i.e. , FAB-MAP [27], [28], performs keypoint detection and associated description of an image with SURF.”
MethodBinary Image Fingerprint: Stable Structure Identifier for 3D LiDAR Place Recognition
Zhang, G., Zhang, T., zhao, S., & Hou, L. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3297063 · Cited by 5
“FAB-MAP [1], SeqSLAM [2] and ABLE-M [3] techniques also show excellent performance in long-term visual localization.”
BackgroundMATC-Net: Learning compact sequence representation for hierarchical loop closure detection
Fu, F., Yang, J., Zhang, J., & Ma, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106734 · Cited by 3
Adaptive Soft Encoding: A General Unsupervised Feature Aggregation Method for Place Recognition
Gong, Y., Yuan, J., Sun, F., Sun, Q., Zhu, W., & Zhang, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3307752 · Cited by 3
“FAB-MAP is limited by the distinguishability of vectors aggregated by BoW, making the recognition results worse than those of the proposed framework in all sequences.”
MethodInfluentialMozzarelli, L., Corno, M., & Savaresi, S. M. (2023) · IEEE Conference on Control Technology and Applications (CCTA) · doi:10.1109/ccta54093.2023.10253172 · Cited by 3
“ORB-SLAM 2 [9] and FAB-MAP [10] are two of the most popular examples.”
BackgroundMethodLocalization Exploiting Semantic and Metric Information in Non-static Indoor Environments
Gómez, C., Hernandez, A. C., Barber, R., & Stachniss, C. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02021-y · Cited by 4
ALCDNet: Loop Closure Detection Based on Acoustic Echoes
Liu, G., Cui, W., Jia, N., Xi, Y., Li, S., & Wang, Z. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3519906 · Cited by 3
“Loop closure detection: Loop closure detection techniques are primarily categorized into visual-based [4], [5], [6], [7], [8] and LiDAR-based [9], [10], [11] methods.”
Conditional Variational Autoencoders for Probabilistic Pose Regression
Zangeneh, F., Bruns, L., Dekel, A., Pieropan, A., & Jensfelt, P. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802091 · Cited by 5
“Estimation of camera pose given an image is a long-standing problem in computer vision [15]–[17].”
A vision-based system supports mapping services for visually impaired people in indoor environments
Nguyen, Q.-H., Vu, H., Tran, T.-H., & Nguyen, Q.-H. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064541 · Cited by 3
“To adapt with these issues, we involve the FAB-MAP algorithms [3] which are recently successful for matching places in routes over long period time.”
BackgroundMethodInfluentialQuality visual landmark selection based on distinctiveness and repeatability
Shimoda, M., & Yamazaki, K. (2015) · ROBOMECH Journal · doi:10.1186/s40648-015-0036-9 · Cited by 3
“For mobile robot navigation, hundreds of features detected from a single image have been used as landmarks [5–8].”
MethodProbabilistic qualitative mapping for robots
Padgett, J., & Campbell, M. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.09.013 · Cited by 3
“Some approaches, such as FABMap [6], make hard decisions about locations in the topological map and map connectivity at run time.”
MethodDynamic Environments Localization via Dimensions Reduction of Deep Learning Features
Zhang, H., Wang, X., Du, X., Liu, M., & Chen, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68345-4_22 · Cited by 5
“FAB-MAP [7] described a probabilistic approach to the problem of matching images and map augment.”
BackgroundMethodInfluentialUsing collaborative sharing on cloud for fast relocalization in keyframe-based SLAM
Zhang, P., Wang, H., & Ding, B. (2017) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar.2017.8311876 · Cited by 3
“The loop detection applied in RTAB-Map [10] and ORB-SLAM is the appearance-based place recognition, which proposed in [11] and [8].”
MethodVisual Loop Closure Detection Based on Stacked Convolutional and Autoencoder Neural Networks
Wang, F., Ruan, X., & Huang, J. (2019) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/563/5/052082 · Cited by 3
“Comparison of different features from SCANN model Experiments were performed on the New College and City Center datasets [15] to verify the feasibility and effectiveness of the proposed method.”
MethodThree level sequence-based Loop Closure Detection
Rodrigues, F., Neuland, R., Mantelli, M., Pittol, D., Maffei, R. D. Q., Prestes, E., & Kolberg, M. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103620 · Cited by 3
Traffic Intersection Re-Identification Using Monocular Camera Sensors
Xiong, L., Deng, Z., Huang, Y., Du, W., Zhao, X., Lu, C., & Tian, W. (2020) · Sensors · doi:10.3390/s20226515 · Cited by 3
Dynamic Time Warping of Deep Features for Place Recognition in Visually Varying Conditions
Alqaraleh, S., Hafez, A. H. A., & Tello, A. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-020-05146-6 · Cited by 3
Egomap: Hierarchical First-Person Semantic Mapping
Süveges, T., & McKenna, S. J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68796-0_25 · Cited by 3
Learning-based Camera Relocalization with Domain Adaptation via Image-to-Image Translation
Yang, C., Liu, Y., & Zell, A. (2021) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas51884.2021.9476673 · Cited by 4
VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-Based Convolutional Autoencoder
Xu, Z., Zhang, Q., Hao, F., Ren, Z., Kang, Y., & Cheng, J. S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88007-1_8 · Cited by 4
Experimental Analysis of Appearance Maps as Descriptor Manifolds Approximations
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89131-2_10 · Cited by 3
Explicit feature disentanglement for visual place recognition across appearance changes
Tang, L., Wang, Y., Tan, Q., & Xiong, R. (2021) · International Journal of Advanced Robotic Systems · doi:10.1177/17298814211037497 · Cited by 3
“Typical pipeline for visual place recognition includes (1) feature extraction and (2) matching, 5,6,16–21 optionally followed by (3) temporal fusion.”
BackgroundA UAV Visual Relocalization Method Using Semantic Object Features Based on Internet of Things
Wang, M., Wang, H., Wang, Z., & Li, Y. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7299309 · Cited by 3
“At this time, the relocalization effect of these two methods will be greatly deteriorated, and if we want to keep the performance of them, we have to pay expensive map maintenance costs [15].”
BackgroundVisual Place Recognition via Semantic and Geometric Descriptor for Automated Valet Parking
Yu, J., & Su, J. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739413 · Cited by 3
“The classical approach [3] constructs descriptors based on the point feature [4].”
BackgroundMethodChen, Y., Yang, Z. X., Wang, W., & Peng, H. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.6.061816 · Cited by 4
“Table 1 records the time and memory overheads required for loop-closure detection on the City Center dataset 9 by the methods proposed in Refs.”
BackgroundMethodUnifying Deep ConvNet and Semantic Edge Features for Loop Closure Detection
Jin, J., Bai, J., Xu, Y., & Huang, J. (2022) · Remote Sensing · doi:10.3390/rs14194885 · Cited by 3
Sequential visual place recognition using semantically-enhanced features
Paturkar, V., Yadav, R., & Kala, R. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17404-4 · Cited by 3
“We have compared our approach with the following state-of-the-art place recognition approaches: Fast Appearance Based Mapping (FABMAP) [8], Network Vector of Locally Aggregated Descriptors (NetVLAD) [2], and Convolutional Autoencoder for Loop Closure (CALC) [17].”
AWLC: Adaptive Weighted Loop Closure for SLAM with Multi-Modal Sensor Fusion
Zhou, G., Fei, H., Liu, W., Zhang, Y., Wei, H., & Hou, X. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126624502335 · Cited by 3
Topological Mapping with Image Sequence Partitioning
Korrapati, H., Courbon, J., & Mezouar, Y. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-33926-4_13 · Cited by 3
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.