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 401–500 of 1,002
Visual precis generation using coresets
Paul, R., Feldman, D., Rus, D. L., & Newman, P. M. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907021 · Cited by 24
“This scenario is common for robot applications requiring high fidelity or large scale appearance-based mapping such as [1] and [2].”
BackgroundMethodSelf-citationEfficient on-line data summarization using extremum summaries
Girdhar, Y., & Dudek, G. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224657 · Cited by 31
“The seminal work by Cummins and Newman [2] on loop closure involves the ability to identify common geographic origins of images, which might not be completely similar; thereby producing a meaningful clustering of images, which could be used to generate summaries.”
BackgroundAutonomous Navigation of UAV through GPS-Denied Indoor Environment with Obstacles
Schnipke, E., Reidling, S., Meiring, J., Jeffers, W., Hashemi, M., Tan, R., Nemati, A., & Kumar, M. (2015) · AIAA Infotech@Aerospace Conference · doi:10.2514/6.2015-0715 · Cited by 24
A bionic autonomous navigation system by using polarization navigation sensor and stereo camera
Xian, Z., He, X., Lian, J., Hu, X., & Zhang, L. (2016) · Autonomous Robots · doi:10.1007/s10514-016-9596-7 · Cited by 24
On the use of binary feature descriptors for loop closure detection
Garcia‐Fidalgo, E., & Ortiz, A. (2014) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2014.7005121 · Cited by 26
“We evaluate our approach using two outdoor urban data sets, published for the validation of FAB-MAP [5].”
BackgroundMethodResultInfluentialDeep learning features exception for cross-season visual place recognition
Kenshimov, C., Bampis, L., Amirgaliyev, B., Arslanov, M., & Gasteratos, A. C. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.10.028 · Cited by 24
Don’t Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Porav, H., Bruls, T., & Newman, P. M. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917073 · Cited by 25
“Topological Localization: Similarly, widely used topological localization frameworks such as FABMAP [18], SeqSlam [19] or NetVLAD [20] achieve high recall and precision figures on clear, daytime images or when explicitly matching images with the same condition (e.g. winter-winter matching), but break down when the con…”
MethodSelf-citationPoint-Cloud-Based Place Recognition Using CNN Feature Extraction
Sun, T., Liu, M., Ye, H., & Yeung, D. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2937740 · Cited by 25
“However, FAB-MAP [2] needs the testing data to be similar to the training data, which is expensive to collect for robotic application, while our method leverages the transfer learning ability of CNN, i.”
InfluentialA review of Visual-Based Localization
Xin, X., Jiang, J., & Zou, Y. (2019) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1145/3366194.3366211 · Cited by 33
“[20] is based on the Bag-ofWords (BoW), which processes and models different visual words and their concurrency probability.”
MethodOn the Use of Optical Flow for Scene Change Detection and Description
Nourani‐Vatani, N., Borges, P. V. K., Roberts, J. M., & Srinivasan, M. V. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9840-8 · Cited by 23
“The bag-of-words dictionary used in the experiments presented here was generated offline from one million test images, while FAB-MAP by Cummins and Newman [17] generated a bag-of-words containing 35,000 test images.”
MethodYe, T., Yan, X., Wang, S., Li, Y., & Zhou, F. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3209727 · Cited by 23
“In recent years, vision-based place recognition methods [1], [2], [3] have been proposed; however, given that the visual sensor is highly sensitive to light, the visual-based approach is hugely unstable when applied in practice.”
BackgroundBio-inspired homogeneous multi-scale place recognition
Chen, Z., Lowry, S. M., Jacobson, A., Hasselmo, M. E., & Milford, M. J. (2015) · Neural Networks · doi:10.1016/j.neunet.2015.10.002 · Cited by 25
“7(b)) which is a large 70 km road-based dataset (2 × 35 km traverses) used in the FAB-MAP (Cummins & Newman, 2009) and SeqSLAM studies (Milford, 2013; Milford & Wyeth, 2012).”
InfluentialCamera tracking using concentric circle markers: Paradigms and algorithms
Calvet, L., Gurdjos, P., & Charvillat, V. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467121 · Cited by 23
“Those using key-frame selection [4, 5, 6] suffer from feature ambiguities and mismatches when the scene consists of repetitive structures / textures.”
BackgroundVisual textures as realizations of multivariate log-Gaussian Cox processes
Nguyen, H.-G., Fablet, R., & Boucher, J. (2011) · 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.2011.5995340 · Cited by 26
“While no explicit references to spatial point processes and associated descriptive statistics, it can be noted that second-order descriptive statistics of spatial keypoint patterns were previously considered for application to scene categorization [15] and robot navigation [5].”
BackgroundMethodA visual exploration algorithm using semantic cues that constructs image based hybrid maps
Krishnan, A. K., & Krishna, K. M. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5649870 · Cited by 23
“In recent years, lot of work has been done on image based navigation along the lines of appearance based mapping [3] and topological SLAM[4].”
BackgroundVisual triage: A bag-of-words experience selector for long-term visual route following
MacTavish, K., Paton, M., & Barfoot, T. D. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989238 · Cited by 23
Spatio-Semantic ConvNet-Based Visual Place Recognition
Camara, L. G., & Přeučil, L. (2019) · European Conference on Mobile Robots · doi:10.1109/ecmr.2019.8870948 · Cited by 23
“Loop closure is typically approached in the literature by using Bag of (visual) Words (BoW) models [4, 11, 12] or the closely related VLAD [5, 13, 14] and Fisher vectors [15, 16].”
MethodDeep regression for LiDAR-based localization in dense urban areas
Yu, S., Wang, C., Yu, Z., Li, X., Cheng, M., & Zang, Y. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.12.013 · Cited by 28
Face detection and recognition with SURF for human-robot interaction
An, S., Ma, X., Song, R., & Li, Y. (2009) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2009.5262624 · Cited by 23
“SURF has been used for object recognition in a museum guide application [10], robot localization with images [11] [12] and visual SLAM [13], face components detection [14],”
MethodInfluentialPosition-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes
Kawewong, A., Tangruamsub, S., & Hasegawa, O. (2010) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e93.d.2587 · Cited by 22
“Naı̈ve template matching involving a rigid relation is often insufficiently flexible in the face of undersegmentation or over-segmentation, which is often true with unconstrained environments, such as outdoors.”
BackgroundMethodGPSlam: Marrying Sparse Geometric and Dense Probabilistic Visual Mapping
Pirker, K., Rüther, M., Schweighofer, G., & Bischof, H. (2011) · British Machine Vision Conference (BMVC) · doi:10.5244/c.25.115 · Cited by 22
“Detection of loop closure is handled by the FAB-MAP algorithm [5], followed by a geometric consistency check, which robustly delivers a single potential loop closing frame P l .”
MethodEfficient descriptor learning for large scale localization
Loquercio, A., Dymczyk, M., Zeisl, B., Lynen, S., Gilitschenski, I., & Siegwart, R. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989359 · Cited by 26
“On the other hand, strong illumination, viewpoint, or scene changes, as well as perceptual aliasing [1], can quickly hinder descriptors repeatability and discriminability.”
BackgroundTB-Places: A Data Set for Visual Place Recognition in Garden Environments
Leyva-Vallina, M., Strisciuglio, N., López-Antequera, M., Tyleček, R., Blaich, M., & Petkov, N. (2019) · IEEE Access · doi:10.1109/access.2019.2910150 · Cited by 26
“The methods proposed in [4], [24] employ Bag of Visual Words represen-”
BackgroundMethodInfluentialTree bark re-identification using a deep-learning feature descriptor
Robert, M., Dallaire, P., & Giguère, P. (2020) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv50864.2020.00012 · Cited by 22
“We assume that I q has a meaningful match in our database, i.e., we are not solving an open-set problem; See FAB-MAP [7] for novel locations detection.”
MethodInfluentialGarg, S., & Milford, M. J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196827 · Cited by 22
“In the context of visual place recognition and localization, the underlying datasets are usually sequentially ordered [2], [6], [49].”
BackgroundMethodInfluentialJo, H., & Kim, E. (2020) · IEEE Access · doi:10.1109/access.2020.2988464 · Cited by 22
“Methods based on deep learning exploit the advantages of metric localization [23] and place recognition [33] resulting in fast estimation of sensor pose using only one image.”
BackgroundTowards persistent visual navigation using SMART
Pepperell, E., Corke, P., & Milford, M. J. (2013) · QUT ePrints (Queensland University of Technology) · Cited by 22
Scene change detection for vision-based topological mapping and localization
Nourani‐Vatani, N., & Pradalier, C. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652556 · Cited by 24
“During localization, the database is searched for a match to close the loop or possibly to extend the map [3], [4].”
BackgroundOzog, P., & Eustice, R. M. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907415 · Cited by 24
“Appearance-only methods such as [21], [22] utilize a bag-of-words representation for visual feature descriptors, where each descriptor is quantized to a word in the vocabulary.”
MethodDynamic scene models for incremental, long-term, appearance-based localisation
Johns, E., & Yang, G. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630953 · Cited by 22
“A probabilistic approach to appearance-based SLAM, denoted FAB-MAP, was presented in [5] whereby a Chow-Liu tree structure models the correlations between observed visual words.”
BackgroundMethodInfluentialA Potential-Game Approach for Information-Maximizing Cooperative Planning of Sensor Networks
Han-lim Choi, A., & Lee, S. (2015) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2015.2403475 · Cited by 22
Topological map construction and scene recognition for vehicle localization
Lin, H., Yao, C.-W., Cheng, K.-S., & Tran, V. L. (2017) · Autonomous Robots · doi:10.1007/s10514-017-9638-9 · Cited by 22
“The FAB-MAP system only relies on the appearance information for navigation and mapping, which leads to several retrieval instance failures in the experiments.”
MethodInfluentialEfficient 3D LIDAR based loop closing using deep neural network
Yin, H., Ding, X., Tang, L., Wang, Y., & Xiong, R. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324463 · Cited by 22
“[9] proposed a method that takes into account of the probabilities of features and is able to work out the probability that two images show the same region of the world.”
MethodOdoViz: A 3D Odometry Visualization and Processing Tool
Ramachandran, S., & McDonald, J. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564712 · Cited by 21
SeqSLAM++: View-based robot localization and navigation
Oishi, S., Inoue, Y., Miura, J., & Tanaka, S. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.10.014 · Cited by 25
“FAB-Map [8,18] improves this approach by constructing and using a generative model of visual words based on their probabilistic relationships.”
Esfahani, M. A., Wu, K., Yuan, S., & Wang, H. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.06.014 · Cited by 21
Appearance-Based Loop Closure Detection via Locality-Driven Accurate Motion Field Learning
Zhang, K., Jiang, X., & Ma, J. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3086822 · Cited by 22
Coresets for visual summarization with applications to loop closure
Volkov, M., Rosman, G., Feldman, D., Fisher, J. S., & Rus, D. L. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139704 · Cited by 25
“Theoretically, the retrieval time of the relevant coreset is poly-logarithmic in the size of the related video stream using the properties and structures of the coreset tree.”
BackgroundMethodInfluentialA pure vision-based topological SLAM system
Lui, W. L. D., & Jarvis, R. A. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364911435160 · Cited by 22
“It uses a combination of visual cues extracted from the image and builds a visual dictionary such as those proposed by Angeli et al. (2008) and Cummins and Newman (2008).”
BackgroundMethodResultInfluentialIndoor localization via multi-view images and videos
Lu, G., Yan, Y., Sebe, N., & Kambhamettu, C. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.05.003 · Cited by 21
Are you ABLE to perform a life-long visual topological localization?
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., & Romera, E. (2017) · Autonomous Robots · doi:10.1007/s10514-017-9664-7 · Cited by 23
“The methods based on single images (BRIEF-Gist, WI-SURF, FAB-MAP) obtain better results in Fig.”
MethodInfluentialGeo-Distinctive Visual Element Matching for Location Estimation of Images
Li, X., Larson, M., & Hanjalić, A. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2763323 · Cited by 21
Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments
Wang, S., Lv, X., Liu, X., & Ye, D. (2020) · IEEE Access · doi:10.1109/access.2020.2982228 · Cited by 22
“For these two datasets (NC and CC), GT is provided by the author in [14].”
Method2-point RANSAC for scene image matching under large viewpoint changes
Chou, C. C., & Wang, C. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139705 · Cited by 21
Perceptual Aliasing++: Adversarial Attack for Visual SLAM Front-End and Back-End
Ikram, M. H., Khaliq, S., Anjum, M. L., & Hussain, W. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3150031 · Cited by 26
PlaceNet: A multi-scale semantic-aware model for visual loop closure detection
Osman, H. A., Darwish, N. M., & Bayoumi, A. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105797 · Cited by 21
Siagian, C., Chang, C. K., & Itti, L. (2014) · Journal of Field Robotics · doi:10.1002/rob.21505 · Cited by 23
Efficient keyframe-based real-time camera tracking
Dong, Z., Zhang, G., Jia, J., & Bao, H. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.08.005 · Cited by 20
“There are approaches which employ invariant features for object and location recognition [44,42,43,12,13,2].”
Towards persistent indoor appearance-based localization, mapping and navigation using CAT-Graph
Maddern, W., Milford, M. J., & Wyeth, G. F. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386186 · Cited by 26
“[14, 15] describes a data association procedure upon loop closure detection, but the later approach adopted in [16] simply adds multiple representations.”
MethodOn-line visual vocabularies for robot navigation and mapping
Nicosevici, T., & García, R. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354392 · Cited by 20
“Often, similarity measurements are represented by distances in the n-dimensional data space, including: Euclidean distance, Manhattan distance [15], Chebyshev norm [12], Mahalanobis distance [18], vector angle, etc.”
BackgroundWhere am I? Creating spatial awareness in unmanned ground robots using SLAM: A survey
Dhiman, N. K., Deodhare, D., & Khemani, D. (2015) · Sadhana · doi:10.1007/s12046-015-0402-6 · Cited by 25
“FAB-MAP (Cummins & Newman 2008) uses a probabilistic framework for a fast appearance based mapping which has been able to overcome these problems.”
BackgroundMethodInfluentialTowards Persistent Localization and Mapping with a Continuous Appearance-based Topology
Maddern, W., Milford, M. J., & Wyeth, G. F. (2012) · Robotics: Science and Systems · doi:10.15607/rss.2012.viii.036 · Cited by 20
“Aerial view of test environment wi The Aerial view of test environment with route overlaid. and CAT-Graph only require calibration or image nearest neighbour algorithm used for comparison is for the detector functions of [19].”
MethodFinding Home: Landmark Ambiguity in Human Navigation
Jetzschke, S., Ernst, M. O., Froehlich, J., & Boeddeker, N. (2017) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2017.00132 · Cited by 24
“…simultaneous localization and mapping (SLAM) algorithms from robotics that involve probabilistic approaches for cue combination, suffer from similar constraints as human navigation performance when the objects to be recognized are ambiguous (Cummins and Newman, 2008; Mullane et al., 2011).”
BackgroundHigh order visual words for structure-aware and viewpoint-invariant loop closure detection
Bampis, L., Amanatiadis, A. A., & Gasteratos, A. C. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206289 · Cited by 20
“teristics was chosen, namely Bicocca 2009-02-25b [9] (BC), Malaga 2009 Parking 6L [43] (MG6L), New College [44] (NC), City Centre [15] (CC), Lip6 Indoor [18] (L6I) and Lip6 Outdoor [18] (L6O).”
MethodLong-Term Robot Navigation in Indoor Environments Estimating Patterns in Traversability Changes
Nardi, L., & Stachniss, C. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197078 · Cited by 30
“In the context of SLAM, FAB-MAP [3] uses the Chow-Liu approximation for modeling the joint distribution of a set of visual features.”
MethodLoopNet: Where to Focus? Detecting Loop Closures in Dynamic Scenes
Osman, H. A., Darwish, N. M., & Bayoumi, A. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3142901 · Cited by 21
Fusing Convolutional Neural Network and Geometric Constraint for Image-Based Indoor Localization
Song, J., Patel, M., & Ghaffari, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3140832 · Cited by 23
“Following BoW, other methods used SIFT probability [21], deep CNN framework [22] and contextual re-weight network [23] to generate image descriptors.”
MethodLearning to close the loop from 3D point clouds
Granström, K., & Schön, T. B. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5651013 · Cited by 23
“[8] 0 37/48 Images, City Centre/New College”
BackgroundSLAM in O(log n) with the Combined Kalman - Information filter
Cadena, C., & Neira, J. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354521 · Cited by 20
Place recognition survey: An update on deep learning approachesPreprint
Barros, T., Pereira, R., Garrote, L., Premebida, C., & Nunes, U. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10458 · Cited by 32
“These frameworks are mainly used in pure retrieval tasks and resort, for retrieval efficiency, to k-dimensional [33], [34], Chow Liu trees [35] or Hierarchical Navigable Small World (NSW) [36] to accelerate nearest neighbor search.”
MethodAirLoop: Lifelong Loop Closure Detection
Gao, D., Wang, C., & Scherer, S. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811658 · Cited by 23
“To achieve this, traditional LCD methods like Galvez-Lṕez and Tardós [32], FAB-MAP [33], and FAB-MAP 3D [34] build a BoW model with visual words generated from handcrafted features offline.”
MethodSequence-based mapping for probabilistic visual loop-closure detection
Tsintotas, K. A., Bampis, L., An, S., Fragulis, G. F., Mouroutsos, S. G., & Gasteratos, A. C. (2021) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist50367.2021.9651458 · Cited by 19
Applications of Spiking Neural Networks in Visual Place Recognition
Hussaini, S., Milford, M. J., & Fischer, T. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3508053 · Cited by 29
“The VPR problem can also be posed as a template matching problem, similar to an image classification problem, where associated templates of all [48],[49],[99],[100]orasequenceofimages[41], [42], [101].”
Lu, Y., Song, D., & Yi, J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907056 · Cited by 21
Kawewong, A., Tongprasit, N., & Hasegawa, O. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.05.007 · Cited by 20
Bubble space and place representation in topological maps
Erkent, Ö., & Bozma, H. I. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913481393 · Cited by 19
“Let it be noted that while this data has been used in the experimental evaluation of localization tasks (Cummins and Newman, 2008; Maddern et al., 2012), to the best of authors’ knowledge, it has not been used in place learning and recognition tasks.”
MethodResultInfluentialGarcia‐Fidalgo, E., & Ortiz, A. (2014) · Robotica · doi:10.1017/s0263574714000782 · Cited by 19
“Probably the most popular solution based on the BoW approach is Fast Appearance-Based Mapping (FAB-MAP),14 where a Chow-Liu tree approximates the co-occurrences between the visual words in the vocabulary.”
BackgroundMethodInfluentialDistance metric learning for feature-agnostic place recognition
Chen, Z., Lowry, S. M., Jacobson, A., Ge, Z., & Milford, M. J. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353725 · Cited by 19
Omnidirectional Multisensory Perception Fusion for Long-Term Place Recognition
Siva, S., & Zhang, H. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461042 · Cited by 20
“edu on individual frames [10], [11] or frame sequences [1], [12], [13] were also implemented.”
MethodLearning to Fuse Multiscale Features for Visual Place Recognition
Mao, J., Hu, X., He, X., Zhang, L., Wu, L., & Milford, M. J. (2018) · IEEE Access · doi:10.1109/access.2018.2889030 · Cited by 20
“Previous approaches have used handcraft-features [5], [22]–[25] and pixel density [26], [27] for visual place recognition.”
BackgroundMethodConvNet and LSH-Based Visual Localization Using Localized Sequence Matching
Qiao, Y., Cappelle, C., Ruichek, Y., & Yang, T. (2019) · Sensors · doi:10.3390/s19112439 · Cited by 19
LookUP: Vision-Only Real-Time Precise Underground Localisation for Autonomous Mining Vehicles
Zeng, F., Jacobson, A., Smith, D., Boswell, N., Peynot, T., & Milford, M. J. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794453 · Cited by 19
“Traditional feature-based place recognition algorithms such as FAB-MAP [10], [11] work poorly in mine-tunnel”
MethodKidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning
Săftescu, Ş., Gadd, M., Martini, D. D., Barnes, D., & Newman, P. M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196682 · Cited by 81
“02 for VGG -16/ NETVLAD . by a global optimisation using Global Positioning System (GPS), robust Visual Odometry (VO) [33], and visual loop closures from FAB-MAP [8].”
MethodSelf-citationFast and Robust Loop-Closure Detection via Convolutional Auto-Encoder and Motion Consensus
Ma, J., Wang, S., Zhang, K., He, Z., Huang, J., & Mei, X. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3120141 · Cited by 21
Improving synthetic 3D model-aided indoor image localization via domain adaptation
Li, Q., Cao, R., Zhu, J., Hou, X., Liu, J., Jia, S., Li, Q., & Qiu, G. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.10.005 · Cited by 20
IVPR: An Instant Visual Place Recognition Approach Based on Structural Lines in Manhattan World
Pei, L., Liu, K., Zou, D., Li, T., Wu, Q., Zhu, Y., Li, Y., He, Z., Chen, Y., & Sartori, D. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2941359 · Cited by 23
“The pure topological map contains the information about relative pose between places but does not contain geometric or metric information [27].”
BackgroundHow to localize humanoids with a single camera?
Alcantarilla, P. F., Stasse, O., Druon, S., Bergasa, L. M., & Dellaert, F. (2012) · Autonomous Robots · doi:10.1007/s10514-012-9312-1 · Cited by 20
“Even simple, our method can detect very efficiently loop closure situations although incremental Bag of Visual Words methods can be also used (Cummins and Newman, 2008; Angeli et al, 2008).”
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., & Romera, E. (2016) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2016.7795672 · Cited by 18
“broadly studied in the recent past, especially after the definition of FAB-MAP [12].”
BackgroundInfluentialA Review of Common Techniques for Visual Simultaneous Localization and Mapping
Dai, Y., Wu, J., & Wang, D. (2023) · Journal of Robotics · doi:10.1155/2023/8872822 · Cited by 25
Meng, C., Duan, Y., He, C., Wang, D., Fan, X., & Zhang, Y. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3377562 · Cited by 23
“Initially, Cummins et al. [17] propose a non-learning method called FAB-MAP that uses SIFT features to construct a Bag-of-visual-words (Bow) architecture for place recognition.”
MethodVisual place recognition for aerial imagery: A survey
Moskalenko, I., Kornilova, A., & Ferrer, G. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104837 · Cited by 24
“The classic approach for Visual Place Recognition , as employed in early works (16; 23), involves utilizing descriptors, which are compact representations of images.”
MethodAnderson, S., MacTavish, K., & Barfoot, T. D. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915589642 · Cited by 19
“It is based on the Fast Appearance Based Mapping (FAB-MAP) algorithm by Cummins and Newman (2008) and the implementation by Glover et al. (2012). Loop closures are proposed by computing the likelihood that a query intensity image (or group of images) came from each previously visited location.”
MethodInfluentialKnowing Where I Am: Exploiting Multi-Task Learning for Multi-view Indoor Image-based Localization
Lu, G., Yan, Y., Sebe, N., & Kambhamettu, C. (2014) · British Machine Vision Conference (BMVC) · doi:10.5244/c.28.125 · Cited by 18
“Methods [2, 5] based on the Simultaneous Localization and Mapping (SLAM) algorithm [10, 20] estimate camera pose based on the online-built 3D model.”
MethodMulti-scale bio-inspired place recognition
Chen, Z., Jacobson, A., Erdem, U. M., Hasselmo, M. E., & Milford, M. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907109 · Cited by 18
“Some of the most significant vision-based mapping and localization algorithms proposed over the past decade include FAB-MAP [10] [11], MonoSLAM [12], RatSLAM [13] [14] [15] [16], FrameSLAM [17] and SeqSLAM [18] [19].”
MethodAcquiring semantics induced topology in urban environments
Singh, G., & Košecká, J. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225282 · Cited by 18
Checkout my map: Version control for fleetwide visual localisation
Gadd, M., & Newman, P. M. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759843 · Cited by 18
“co-occurrence of vocabulary elements are used in robust place recognition [2], and aggregation of scene variation [3].”
BackgroundSelf-citationBampis, L., & Gasteratos, A. C. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.01.004 · Cited by 18
Ferrarini, B., Waheed, M., Waheed, S., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · NASA/ESA Conference on Adaptive Hardware and Systems (AHS) · doi:10.1109/ahs.2019.00011 · Cited by 18
“Other approaches undertaken include the use of FABMAP [22] as it alleviated the BoW performance but its applicability in a UAV is restricted by the high variance in performance to even small viewpoint change.”
MethodLoop Closure Detection With Reweighting NetVLAD and Local Motion and Structure Consensus
Zhang, K., Ma, J., & Jiang, J. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105635 · Cited by 19
Topological SLAM Using Fast Vision Techniques
Werner, F., Maire, F., & Sitte, J. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03983-6_23 · Cited by 18
Vision-based sparse topological mapping
Korrapati, H., & Mezouar, Y. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.03.015 · Cited by 18
“Normalization-to-highest is also a simple alternative to using the average image [4,5] andmean field approximation [6,7,34].”
BackgroundMethodMulti-sensor Appearance-Based Place Recognition
Collier, J. A., Se, S., & Kotamraju, V. (2013) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2013.35 · Cited by 21
“To overcome these problems, appearance-based place recognition can be used to decouple the loop closing process from the geometric SLAM algorithm[2],[3],[4].”
MethodAvoiding negative depth in inverse depth bearing-only SLAM
Parsley, M. P., & Julier, S. (2008) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2008.4651118 · Cited by 21
“An example is the use of image data to detect when loop closing has occured [10].”
BackgroundMILD: Multi-index hashing for appearance based loop closure detection
Han, L., & Fang, L. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019479 · Cited by 18
“CityCentre [4] contains 1237 images of size 1280×480.”
BackgroundMethodResultInfluentialAdaptive localization and mapping with application to planetary rovers
Hidalgo‐Carrió, J., Poulakis, P., & Kirchner, F. (2018) · Journal of Field Robotics · doi:10.1002/rob.21790 · Cited by 19
“Appearance based techniques use directly the image sequence is described in (Cummins and Newman, 2008).”
MethodImproved appearance-based matching in similar and dynamic environments using a Vocabulary tree
Sabatta, D., Scaramuzza, D., & Siegwart, R. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509382 · Cited by 18
“The emergence of ever improving, fast, visual appearance matching techniques such as VideoGoogle [11] and later the Vocabulary Tree [5] and FabMAP [12], allowed real-time appearance-based map building and localisation using local features.”
MethodOptimized SC-F-LOAM: Optimized Fast LiDAR Odometry and Mapping Using Scan Context
Liao, L., Fu, C., Feng, B., & Su, T. (2022) · CAA International Conference on Vehicular Control and Intelligence (CVCI) · doi:10.1109/cvci56766.2022.9964574 · Cited by 18
“solutions have been proposed in the literature, such as [13-15].”
BackgroundMemory efficient large-scale image-based localization
Lu, G., Sebe, N., Xu, C., & Kambhamettu, C. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-1977-3 · Cited by 18
“Methods proposed in [9] and [7] estimate the camera pose based on the online-build 3D model based on the Simultaneous Localization and Mapping (SLAM) algorithm [26, 41], which is limited to small scenes.”
MethodLowry, S. M., Wyeth, G. F., & Milford, M. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6906932 · Cited by 18
“The dataset used was the Oxford originally presented in [4].”
BackgroundMethodInfluentialImage Sequence Partitioning for outdoor mapping
Korrapati, H., Courbon, J., Mezouar, Y., & Martinet, P. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224892 · Cited by 17
“Quite a few loop closure techniques for topological maps have been proposed recently for both indoor [4], [12], [10], [11], [2], [22] and outdoor environments [9], [8], [13], [15].”
Background
Metadata
- Authors
- Cummins, M., & Newman, P.
- Affiliations
- University of Oxford (GB)
- Corresponding author
- Cummins, Mark
- Newman, Paul
- ORCID
- Newman, Paul
- Venue
- The International Journal of Robotics Research
- Publisher
- SAGE Publications
- Published
- 2008-06
- Volume
- 27
- Issue
- 6
- Pages
- 647-665
- ISSN
- 0278-3649 (ISSN-L)
- 1741-3176
- OpenAlex
- W2144824356
- Cited by
- 1,472
- References
- 57
- Citations by year
- 2026: 28 · 2025: 43 · 2024: 60 · 2023: 59 · 2022: 119 · 2021: 122 · 2020: 103 · 2019: 117 · 2018: 105 · 2017: 127 · 2016: 90 · 2015: 103 · 2014: 72 · 2013: 83 · 2012: 71
- FWCI
- 116.69
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- The International Journal of Robotics Research (publishedVersion)
- Funders
- Engineering and Physical Sciences Research Council
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- place recognition, perceptual aliasing, loop closure detection, mobile robots
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.