The DOI matches its Crossref record; 54 of the 57 references it cites were found in a registry or an index.
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
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 801–900 of 1,002
MRStudio: A mixed reality display system for aircraft cockpit
Wan, H., Zou, S., Dong, Z., Lin, H. B., & Bao, H. (2011) · IEEE International Symposium on VR Innovation (ISVRI) · doi:10.1109/isvri.2011.5759615 · Cited by 7
“IEEE International Symposium on Virtual Reality Innovation 2011 19-20 March, Singapore 978-1-4577-0054-5/11/$26.00 ©2011 IEEE methods can be classified into keyframe-based methods which involve keyframe selection to reduce the data redundancy [21,24,26] and feature-based location recognition approaches which employ th…”
MethodInfluentialFast vision-based object segmentation for natural landmark detection on Indoor Mobile Robot
Chai, X., Wen, F., & Yuan, K. (2011) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2011.5986286 · Cited by 7
“A fast line segmentation and fitting method is proposed to improve the line detection efficiency and half edge structure is added to simplify the polygon generation process.”
BackgroundMethodSpeedup Robust Features based unsupervised place recognition for assistive mobile robot
Karasfi, B., Hong, T. S., Jalalian, A., & Nakhaeinia, D. (2011) · International Conference on Pattern Analysis and Intelligence Robotics (ICPAIR) · doi:10.1109/icpair.2011.5976919 · Cited by 7
“Cummins and Newman [15] introduced FAB-MAP algorithm that is a probabilistic framework inspired from bag-of-word (BOW) for place recognition tasks [16].”
Method石塚, 大., Yamashita, A., Kawanishi, R., Kaneko, T., & Asama, H. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130253 · Cited by 7
“As related works, self-localization methods using GPS [1], landmarks (RFID tags [2], etc.), normal camera [3], or are proposed.”
MethodSequential appearance-based Global Localization using an ensemble of kNN-DTW classifiers
Forechi, A., Souza, A. F. D., Badue, C. S., & Oliveira-Santos, T. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727550 · Cited by 7
“Cummins and Newman, in their seminal paper [8], employed a probabilistic approach to the topological SLAM problem in the space of appearance, named FAB-MAP.”
BackgroundOriginal Loop-Closure Detection Algorithm for Monocular vSLAM
Bokovoy, A., & Yakovlev, K. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-73013-4_19 · Cited by 7
“– image-to-image founds a correspondences between images, usually based on vocabulary of image features [22].”
BackgroundCompact Environment-Invariant Codes for Robust Visual Place Recognition
Jain, U., Namboodiri, V. P., & Pandey, G. (2017) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2017.22 · Cited by 7
“Traditional visual place recognition approaches like [3], [4] focused on situations where robot has to recognize places that it has recently visited, where the difference between query and database images was mainly due to different view-point of sensors.”
BackgroundMethodA Cloud-Based Visual SLAM Framework for Low-Cost Agents
Jiao, J., Peng, Y., & Liu, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68345-4_42 · Cited by 7
“Within appearance based approaches, a typical one is the FAB-MAP system [13].”
MethodLOGOS: Local Geometric Support for High-Outlier Spatial Verification
Lowry, S. M., & Andreasson, H. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460988 · Cited by 7
“For each false match, LOGOS incorrectly matches small, similar-looking regions; the City Centre dataset is particularly challenging for it as it contains many frequentlyrepeated features such as window panes [16].”
BackgroundMethodFaster Visual-Based Localization with Mobile-PoseNet
Cimarelli, C., Cazzato, D., Olivares-Méndez, M. A., & Voos, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29891-3_20 · Cited by 7
Taking Me to the Correct Place: Vision-Based Localization for Autonomous Vehicles
Lu, G., & Wong, X.-I. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803241 · Cited by 7
“Simultaneous Localization and Mapping (SLAM) algorithms [14, 15, 16] are proposed to address the drifting error by detecting the loop closure and conducting global bundle adjustment.”
MethodTowards Robust Loop Closure Detection in Weakly Textured Environments using Points and Lines
Joan P. Company-Corcoles, Garcia‐Fidalgo, E., & Ortiz, A. (2020) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa46521.2020.9212133 · Cited by 7
“The datasets considered for the evaluation are: CityCentre [21] (CC), KITTI 00 [22] (K00), KITTI 06 [22] (K06) and Lip6Outdoor [1] (L6O).”
MethodQualitative relational mapping and navigation for planetary rovers
McClelland, M., Campbell, M., & Estlin, T. A. (2016) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2016.05.017 · Cited by 7
“[10], and the place-base mapping discussed by Cummins and Newman [11].”
BackgroundReal time visual SLAM using cloud computing
Ayush, K., & Agarwal, N. K. (2013) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt.2013.6726744 · Cited by 7
“Please note, any alternative approach like the Fab-Map [15] approach of Cummins and Newman could be used instead.”
MethodLoop closure detection using depth images
Scherer, S., Kloss, A., & Zell, A. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698827 · Cited by 7
“There are, however, a plethora of attempts to visually detect closed loops based on regular (intensity) camera images [2], [3], [4].”
BackgroundVLAD-based loop closure detection for monocular SLAM
Huang, Y., Sun, F., & Guo, Y. (2016) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2016.7831876 · Cited by 7
“After that, many various improvements and advancements has been made on the original FAB-MAP algorithm.”
MethodInfluentialPronobis, A., & Barbara Caputo, B. (2010) · The Kluwer international series on information retrieval · doi:10.1007/978-3-642-15181-1_10 · Cited by 7
“The topic has been vastly researched, resulting in a broad range of approaches spanning from the purely metric (Jogan and Leonardis, 2003; Dissanayake et al, 2001; Wolf et al, 2005), to topological (Ulrich and Nourbakhsh, 2000; Ullah et al, 2008; Cummins and Newman, 2008 ), and hybrid (Thrun, 1998; Brunskill et al, 20…”
BackgroundMethodInfluentialRelative Navigation in GPS‐Degraded Environments
Wheeler, D. O., Nyholm, P. W., Koch, D. P., Ellingson, G. J., McLain, T. W., & Beard, R. W. (2016) · Wiley eBooks · doi:10.1002/9780470686652.eae1154 · Cited by 7
“Further work has improved place recognition performance in the presence of aliasing, where high correlation is found on non-correlated images, like pictures of brick walls [28].”
BackgroundFeature Map Filtering: Improving Visual Place Recognition with Convolutional CalibrationPreprint
Hausler, S., Jacobson, A., & Milford, M. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12465 · Cited by 7
“, 2008] and HOG [Dalal and Triggs, 2005], and deep learnt networks have been used to attempt to solve the VPR challenge [Naseer et al., 2018; Cummins and Newman, 2008; Sunderhauf et al., 2015a; Arandjelovi et al., 2018].”
MethodDeep UAV Localization with Reference View RenderingPreprint
Hinzmann, T., & Siegwart, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04619 · Cited by 8
“Traditional image retrieval methods can be categorized in Bag-of-Words (BOW) and image voting approaches: FAB-MAP [9] is one of the most famous representant of the BOW approach.”
MethodDouble-Domain Adaptation Semantics for Retrieval-Based Long-Term Visual Localization
Ge, F., Zhang, Y., Wang, L., Coleman, S., & Kerr, D. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3345138 · Cited by 9
“…Total Loss Function: In order to simultaneously train the content encoder, decoder, semantic segmentation decoder and metric learning part for the double-domain adaptive model, the total loss function is integrated as follows: where, λ C , λ D , λ SAM , λ T , λ Seg and λ SegT are weight parameters.”
Arshad, S., & Park, T.-H. (2024) · Sensors · doi:10.3390/s24030906 · Cited by 6
“Notably, FAB-MAP [6] represents scenes using visual words and incorporates SURF [15] for detecting interest points.”
MethodModel-aided monocular visual-inertial state estimation and dense mapping
Qiu, K., & Shen, S. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205992 · Cited by 6
“And global localization solutions based on place recognition [1], [2] can only obtain topological localization which is not accurate enough for closed-loop control.”
BackgroundAn adaptive localization system for image storage and localization latency requirements
Mao, J., Hu, X., & Milford, M. J. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.06.007 · Cited by 6
“In the third group of experiments, we replaced the front-end SAD visual component shown in (12) with FAB-MAP [16], which is a benchmark visual place recognition method, to investigate the algorithm performance by using different visual components.”
BackgroundMethodInfluentialHM$^4$: Hidden Markov Model With Memory Management for Visual Place Recognition
Doan, A.-D., Latif, Y., Chin, T.-J., & Reid, I. D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3036615 · Cited by 6
“A popular approach in VPR is image retrieval from a geotagged database [12].”
Two-Stage vSLAM Loop Closure Detection Based on Sequence Node Matching and Semi-Semantic Autoencoder
Wang, Z., Peng, Z., Guan, Y. L., & Wu, L. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01302-0 · Cited by 7
Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation
Guan, P., Cao, Z., Yu, J., Tan, M. H., & Wang, S. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3206500 · Cited by 6
“An impressive case is fast appearance-based mapping (FAB-MAP) [28], which extracts the SURF features from an image and converts them into a BoW representation for effective place recognition.”
Liao, M., Zhang, Y., Zhang, J., Liang, L., Coleman, S., & Kerr, D. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981965 · Cited by 6
“Vision-based loop closure detection has been investigated for a long time, [1]–[3], using the Bag-of-Words method for encoding image features.”
Augmenting appearance-based localization and navigation using belief update
Chrysanthakopoulos, G., & Shani, G. (2010) · doi:10.5555/1838178.1838180 · Cited by 6
Lu, H., Li, X., Zhang, H., & Zheng, Z. (2013) · Advanced Robotics · doi:10.1080/01691864.2013.839090 · Cited by 6
“© 2013 Taylor & Francis and The Robotics Society of Japan”
BackgroundSequence-based multimodal apprenticeship learning for robot perception and decision making
Han, F., Yang, X., Zhang, Y., & Zhang, H. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989301 · Cited by 6
A Scalable Sampling-Based Optimal Path Planning Approach via Search Space Reduction
Lu, W., & Liu, D. (2019) · IEEE Access · doi:10.1109/access.2019.2948976 · Cited by 6
“Such obstacle representation can be built from Bayesian SLAM algorithms [39].”
MethodRobust Outdoor Self-localization In Changing Environments
Haris, M., Franzius, M., & Bauer-Wersing, U. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967549 · Cited by 7
“Although recent advances in the field have shown impressive results in the mapping of large-scale environments [2], [3], the long-term outdoor operation in unconstrained environments is still an active research area [4], [5].”
BackgroundLocalising PMDs through CNN Based Perception of Urban Streets
Jayasuriya, M., Arukgoda, J., Ranasinghe, R., & Dissanayake, G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196639 · Cited by 6
“However, these low level image features do not persist over long time frames, due to appearance, illumination, weather changes and occlusions, making building a pre-defined map of such features difficult [11][12][13].”
BackgroundSelf-Supervised Map-Segmentation by Mining Minimal-Map-Segments
Kanji, T. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304724 · Cited by 6
“Many other effective alternatives have been proposed, including places defined as individual mapped images [20] or sequence matching [44], query results close in time (e.g., “islands” of places) [21], images with similar covisibility [22], [25], place topics [26], spatial CENTRIST descriptors [23],…”
BackgroundA Multi-Channel Descriptor for LiDAR-Based Loop Closure Detection and Its Application
Wang, G., Wei, X., Chen, Y., Zhang, T., Hou, M., & Liu, Z. (2022) · Remote Sensing · doi:10.3390/rs14225877 · Cited by 6
Fast Scan Context Matching for Omnidirectional 3D Scan
Kihara, H., Kumon, M., Nakatsuma, K., & Furukawa, T. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981143 · Cited by 6
“For example, FAB-MAP incorporated the bag-of-words approach to store the appearance keys[2], a sequence of images was used to match in SeqSLAM[3] and BRIEF feature[4] was accepted as a descriptor in BRIEF-Gist[5].”
MethodA speeded-up online incremental vision-based loop-closure detection for long-term SLAM
Kawewong, A., Tongprasit, N., & Hasegawa, O. (2013) · Advanced Robotics · doi:10.1080/01691864.2013.826410 · Cited by 6
“The baselines used in this study are the original FAB-MAP of [3], the PIRF-Nav 1.0 [1] and the PIRF-Nav 2.0.”
BackgroundMethodResultInfluentialLAYOUT SLAM WITH MODEL BASED LOOP CLOSURE FOR 3D INDOOR CORRIDOR RECONSTRUCTION
Jahromi, A. B., Sohn, G., Jung, J., Shahbazi, M., & Kang, J. (2018) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-25-2018 · Cited by 6
Incremental Pose Map Optimization for Monocular Vision SLAM Based on Similarity Transformation
Liu, W., Wu, S., Zhong-bo, W., & Wu, X. (2019) · Sensors · doi:10.3390/s19224945 · Cited by 7
Estimation and navigation methods with limited information for autonomous urban driving
Chipka, J. B., & Campbell, M. (2019) · Engineering Reports · doi:10.1002/eng2.12054 · Cited by 6
Garcia‐Fidalgo, E., & Ortiz, A. (2022) · Autonomous Robots · doi:10.1007/s10514-021-10032-7 · Cited by 6
Developing a Framework for Reliable Autonomous Surface Mobility
Wettergreen, D. S., & Wagner, M. (2018) · Figshare · doi:10.1184/r1/6552599 · Cited by 6
Wide-Baseline Visible Features for Highly Dynamic Scene Recognition
Kawewong, A., Tangruamsub, S., & Hasegawa, O. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03767-2_88 · Cited by 6
“However, after SIFT [6] is popularized in the vision community, it nearly dominates the feature choice in place recognition systems [2], [10], [11], [14].”
BackgroundHolography map for home robot: an object-oriented approach
Wu, P., Kong, L., & Gao, S. (2012) · Intelligent Service Robotics · doi:10.1007/s11370-012-0109-z · Cited by 6
A novel loop closure detection method in monocular SLAM
Zhiwei, L., Gao, X., Chen, Y., & Songhao, Z. (2012) · Intelligent Service Robotics · doi:10.1007/s11370-012-0124-0 · Cited by 6
“Simultaneous localization and mapping (SLAM) is a key technique for mobile robots to achieve autonomous navigation [1–3], which can be performed using the robots to build up a map within an unknown environment (without a priori knowledge), while at the same time to keep track of their current…”
MethodZhang, X., Zhang, J., Rad, A. B., Mai, X., & Jin, Y. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491012 · Cited by 6
“The visual words were obtained from the SURF descriptors of the grabbed images.”
BackgroundMethodInfluentialCoarse-to-fine global localization for mobile robots with hybrid maps of objects and spatial layouts
Park, S., Cheong, H., & Park, S.-K. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354193 · Cited by 6
“Most place recognition-based systems [5, 6, 7, 8] 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 [9], extracted from the environmental images.”
BackgroundSimultaneous Localization and Mapping ( SLAM )
Birk, A., & Pfingsthorn, M. F. (2016) · Wiley eBooks · doi:10.1002/047134608x.w8322 · Cited by 12
LiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure DetectionPreprint
Company-Corcoles, J. P., Garcia‐Fidalgo, E., & Ortiz, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09897 · Cited by 6
“The following datasets were considered to validate LiPo-LCD: CityCentre [10] (CC), EuRoC Machine Hall 05 [9] (EuR5), KITTI 00 [16] (K00), KITTI 06 [16] (K06), Lip6Indoor [1] (L6I), Lip6Outdoor [1] (L6O) and Malaga 2009 Parking 6L [8] (MLG).”
MethodDeep learning based monocular visual-inertial odometry
Esfahani, M. A. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/152280 · Cited by 6
Visual Place Recognition for Simultaneous Localization and Mapping
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Wiley eBooks · doi:10.1002/9781394152636.ch4 · Cited by 7
To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition
Sferrazza, D., Berton, G., Trivigno, G., & Masone, C. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00268 · Cited by 13
“…by comparing it to a database of geo-tagged images [1, 2, 5, 11, 29, 40, 43, 89, 95]. and it serves as a critical first step in applications such as Structure-from-Motion (SfM) [44, 46, 65], simultaneous localization and mapping (SLAM) [21, 34, 63] and Visual Localization [44, 64, 76, 78].”
From Satellite to Ground: Satellite Assisted Visual Localization with Cross-view Semantic Matching
Guo, X., Peng, H., Hu, J., Bao, H., & Zhang, G. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611658 · Cited by 5
“The second step entails pose estimation, utilizing feature matching techniques to align the current frame’s feature points with 3D map points observed in associated frames [7], [8].”
MethodDK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking, and Loop Closing
Qu, H., Zhang, L., Mao, J., Tie, J., He, X., Hu, X., Shi, Y., & Chen, C. (2025) · Applied Sciences · doi:10.3390/app15147838 · Cited by 6
Context Graph-Based Visual-Language Place Recognition
Woo, S., & Kim, S.-W. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127699 · Cited by 6
“Among these methods, FAB-MAP [12] integrates SURF and BoWs techniques for place recognition, demonstrating high efficiency and robust performance against viewpoint changes.”
Hierarchical appearance-based classifiers for qualitative spatial localization
Fazl-Ersi, E., Elder, J. H., & Tsotsos, J. K. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354577 · Cited by 5
“In a more recent approach by Cummins et al [18], visual words are used in a probabilistic framework for image matching, where the statistical relationships between the visual word are modeled through Chow Liu trees, capturing the fact that certain combinations of visual words are likely to appear…”
MethodVisual Localization by Place Recognition Based on Multifeature (D- λ LBP++HOG)
Qiao, Y., & Zhang, Z. (2017) · Journal of Sensors · doi:10.1155/2017/2157243 · Cited by 5
“FAB-MAP (Fast Appearance Based Mapping) method [3] can be considered as the milestone in the field of visual localization.”
MethodLoop Closure Detection Based on Image Semantic Segmentation in Indoor Environment
Li, J., Wang, P., Ni, C., & Rong, W. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/7765479 · Cited by 6
Stable keypoints selection for 2D LiDAR based place recognition with map data reduction
Douadi, L., Dupuis, Y., & Vasseur, P. (2022) · Robotica · doi:10.1017/s0263574722000613 · Cited by 6
“One popular algorithm in this context is FAB-MAP for fast appearance based mapping, introduced by Cummins and Newman [4, 5], a probabilistic approach for place recognition in the context of SLAM.”
MethodLocality-constrained continuous place recognition for SLAM in extreme conditions
Yadav, R., Pani, V., Mishra, A., Tiwari, N., & Kala, R. (2023) · Applied Intelligence · doi:10.1007/s10489-022-04415-1 · Cited by 5
“One of the best techniques for place recognition across domains is FAB-MAP [4] which can align between two distinctive domains with different conditions.”
MethodColonMapper: topological mapping and localization for colonoscopy
Morlana, J., Tardós, J. D., & Montiel, J. M. M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610426 · Cited by 7
“Traditional methods for topological SLAM [12– 14] relied on features like SIFT [15].”
MethodArshad, S., & Kim, G.-W. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3452158 · Cited by 5
“A match is considered a true positive if it lies within a range of 10 meters, a thresholding similar to [6], [7], and [53].”
RING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning
Lu, S., Xu, X., Zhang, D., Wu, Y., Lu, H., Chen, X., Xiong, R., & Wang, Y. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3543267 · Cited by 14
“Traditional global localization approaches, originating from early visual methods [3], [6], [7], typically follow a paradigm: first place recognition (PR) then pose estimation (PE).”
Augmenting RatSLAM using FAB-MAP-based visual data association
Maddern, W., Glover, A., Milford, M. J., & Wyeth, G. F. (2009) · Cited by 5
Underwater visual SLAM with loop-closure using image-to-image link recovery
Hong, S., Kim, T., & Kim, J. (2015) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-genova.2015.7271448 · Cited by 5
“Although FAB-MAP shows impressive results by mapping a 978-1-4799-8736-8/15/$31.00 ©2015 IEEE large-scale area in real-time, the results depend on the trainingset because offline training is unavoidable.”
MethodInfluentialGeometric constraints for robot navigation using omnidirectional camera
Wang, M.-L., Wu, H., He, C.-H., Huang, W.-T., & Lin, H. (2012) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2012.6377986 · Cited by 5
SAIL-MAP: Loop-closure detection using saliency-based features
Birem, M., Quinton, J., Berry, F., & Mezouar, Y. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943206 · Cited by 5
“Many powerful approaches have been proposed recently to address this problem efficiently [1], [2], [3], [4].”
BackgroundMethodResultInfluentialZhang, D., Kurazume, R., Iwashita, Y., & Hasegawa, T. (2011) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2011.6147425 · Cited by 5
“In another study, the experimental results were not evaluated explicitly under significant changes in illumination [3].”
ResultTowards Vision-Based Pose- and Condition-Invariant Place Recognition along Routes
Pepperell, E., Corke, P., & Milford, M. J. (2014) · QUT ePrints (Queensland University of Technology) · Cited by 5
Vision-Based SLAM Navigation for Vibro-Tactile Human-Centered Indoor Guidance
Gulde, T., Kärcher, S. M., & Curio, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48881-3_24 · Cited by 5
Patterns of approximated localised moments for visual loop closure detection
Erhan, C., Sarıyanidi, E., Şencan, O., & Temeltaş, H. (2017) · IET Computer Vision · doi:10.1049/iet-cvi.2016.0237 · Cited by 5
“A popular method in the first category is FAB-MAP [2].”
BackgroundMethodInfluentialJayasuriya, M., Dissanayake, G., Ranasinghe, R., & Gandhi, N. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917454 · Cited by 5
“However most of these approaches tend to fail under extreme appearance, illumination, occlusion and weather changes, common in autonomous driving scenarios [22], [23], [24], [25].”
BackgroundFast and Consistent Matching for Landmark-Based Place Recognition
Liu, Q., & Duan, F. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-01108-9 · Cited by 5
3D Surfel Map-Aided Visual Relocalization with Learned Descriptors
Ye, H., Huang, H., Hutter, M., Sandy, T., & Liu, M. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561005 · Cited by 6
Feature-based visual odometry and featureless place recognition for SLAM in 2.5D environments
Milford, M. J., McKinnon, D. H., Warren, M., Wyeth, G. F., & Upcroft, B. (2011) · QUT ePrints (Queensland University of Technology) · Cited by 5
Loop Closure Detection in RGB-D SLAM by Utilizing Siamese ConvNet Features
Xu, G., Xiang, L., Zhang, X., Xing, G., & Pan, F. (2021) · Applied Sciences · doi:10.3390/app12010062 · Cited by 5
Improving Road Segmentation in Challenging Domains Using Similar Place Priors
Malone, C., Garg, S., Xu, M., Peynot, T., & Milford, M. J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3146894 · Cited by 5
“From large-scale appearance-based mapping techniques [25] to appearancerobust day-night place recognition [26], recent VPR research focus has shifted more to the use of learning-based techniques to better represent and match places under a range of practical challenges [27], [28], [29], [30].”
BackgroundDeng, H., Pei, Z., Tang, Z., Zhang, J., & Yang, J. (2023) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma57826.2023.10215550 · Cited by 5
“Visual-based approaches such as FAB-MAP [9] and DBoW [10] usually leverage the bag-of-words model (BoW) which uses pre-trained visual dictionary and measures the distance of BoW vectors to identify loop closure.”
MethodThe Next Generation of Unmanned Ground Vehicles
Hester, G., Smith, C. M. M., Day, P., & Waldock, A. (2012) · Measurement and Control · doi:10.1177/002029401204500404 · Cited by 5
Place Recognition and Online Learning in Dynamic Scenes with Spatio-Temporal Landmarks
Johns, E., & Yang, G. (2011) · British Machine Vision Conference (BMVC) · doi:10.5244/c.25.10 · Cited by 5
“The recognition of a place instance represented in an image has seen a wide range of applications [1, 2, 3, 4].”
BackgroundCity-scale continuous visual localization
López-Antequera, M., Petkov, N., & González-Jiménez, J. (2017) · European Conference on Mobile Robots · doi:10.1109/ecmr.2017.8098692 · Cited by 5
“With this philosophy, FAB-MAP [8] is an approach to solve the place recognition problem by building a probabilistic model on top of a bag-of-words representation of images.”
MethodVisual place recognition with CNNs: From global to partial
Xin, Z., Cui, X., Zhang, J., Yang, Y., & Wang, Y. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310121 · Cited by 6
“The bag-of-words models, such as FAB-MAP [6] and DBoW3 [10], transform the feature space into a visual vocabulary which can be retrieved efficiently.”
MethodSpherical Panoramic Image-based Localization by Deep Learning
UMEDA, M., & Hisashi, D. A. T. E. (2018) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.54.483 · Cited by 5
Loop Closure Detection for Visual SLAM Based on Deep Learning
Hu, H., Zhang, Y., Duan, Q., Hu, M., & Pang, L. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446473 · Cited by 5
“[7] proposed the famous FAB-MAP, which made use of the image feature as a visual representation to achieve the detection.”
MethodCamera Localization in Outdoor Garden Environments Using Artificial Landmarks
Strisciuglio, N., Vallina, M. L., Petkov, N., & Muñoz‐Salinas, R. (2018) · IEEE International Work Conference on Bioinspired Intelligence (IWOBI) · doi:10.1109/iwobi.2018.8464139 · Cited by 5
“Camera pose estimation is a common problem in many applications requiring precise localization in the environment, such as augmented and virtual reality [1], [2], mobile robotics [3]–[7] and autonomous driving [8], [9].”
BackgroundSalient Feature Selection for CNN-Based Visual Place Recognition
Chen, Y., Wenyan, G. A. N., Jiao, S., Xu, Y.-W., & Feng, Y. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edp7175 · Cited by 5
“As the most popular feature extraction methods, appearance-based methods mainly focus on hand-crafted feature extraction, such as SIFT (scale-invariant feature transforms) [2], SURF (speeded up robust features) [3] and FAB-MAP [4], [5].”
MethodRobust ConvNet Landmark-Based Visual Place Recognition by Optimizing Landmark Matching
Kong, Y., Liu, W., & Chen, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2901984 · Cited by 7
LandmarkBoost: Efficient visualContext Classifiers for Robust Localization
Dymczyk, M., Gilitschenski, I., Nieto, J. I., Lynen, S., Zeisl, B., & Siegwart, R. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594100 · Cited by 5
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-aliased Indoor Environments
Tourani, S., Desai, D., Parihar, U. S., Garg, S., Sarvadevabhatla, R. K., Milford, M. J., & Krishna, K. M. (2021) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010230804090416 · Cited by 5
Chen, S., Wu, J., Lu, Q., Wang, Y., & Lin, Z. (2021) · International Journal of Advanced Robotic Systems · doi:10.1177/17298814211050560 · Cited by 5
“18 LCD is to determine whether the robot has returned to a location that has been visited before, and it is, in essence, the same as global localization and place recognition.”
BackgroundPlanning on topological map using omnidirectional images and spherical CNNs*
Taniguchi, A., Sasaki, F., Muroi, M., & YAMASHINA, R. (2021) · Advanced Robotics · doi:10.1080/01691864.2021.1997641 · Cited by 5
“Besides, whereas traditional vSLAM [3–5] often uses bag-of-visual-words with handcrafted local features such as SIFT [6], SURF [7], and ORB [8], it is challenging CONTACT Asuto Taniguchi asuto.taniguchi@jp.ricoh.com ∗ Portions of this work were previously presented at the 26th Robotics Symposia…”
MethodSelf-help: Seeking out perplexing images for ever improving topological mapping
Paul, R., & Newman, P. M. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913509859 · Cited by 5
“// Introspection for each image di ∈ ObS[t] // Estimate topics proportions θdi ← Topic_Proportions_Est(di, φ) // Estimate redundancy R(di|SS[t]) using eq:16 end // Determine the most novel image dNovel ∈ ObS[t] using eq:17 // Retrieval for each image dj ∈ DB // Estimate likelihood using eq:10,14 Mult_dist[j] ← p(dNove…”
BackgroundMethodSelf-citationPlace recognition from disparate views
Frampton, R., & Calway, A. D. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.111 · Cited by 5
“Notably, FAB-MAP [6] has demonstrated the ability to work on datasets of over 100,000 images in real-time.”
BackgroundAn efficient index for visual search in appearance-based SLAM
Hajebi, K., & Zhang, H. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6906881 · Cited by 5
Q-Link: A general planning architecture for navigation with qualitative relational information
Padgett, J., & Campbell, M. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.07.001 · Cited by 6
Girdhar, Y., & Dudek, G. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980094 · Cited by 6
“The seminal work by Cummins and Newman [7] on loop closure involves ability to identify the common geographic origin of images, which might not be completely similar; thereby producing a meaningful clustering of images, which could be used to generate summaries.”
BackgroundConstruction of Semantic Maps for Personal Mobility Robots in Dynamic Outdoor Environments
Hatao, N., Kagami, S., Hanai, R., Yamazaki, K., & Inaba, M. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-40686-7_19 · Cited by 5
“Firstly, FAB-MAP selects the most similar image with the current image in the image sequence obtained when the Road Map is constructed.”
MethodInfluentialSLAM with a Heterogeneous Prior Map
Parsley, M. P., & Julier, S. (2009) · Cited by 5
Geometry-Aware Learning of Maps for Camera LocalizationPreprint
Brahmbhatt, S., Gu, J., Kim, K., Hays, J. H., & Kautz, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.03342 · Cited by 5
“Examples include 3D landmarks for general visual SLAM methods [34, 35, 42], 3D lines and patches in semi-dense SLAM methods and indoor scenes [20, 43, 56], object-level context in semantic SLAM methods [10, 45], bag of visual word features on key frames for camera relocalization [12, 46, 47].”
Method
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.