The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection
Open accessThe DOI matches its Crossref record; 395 of the 397 references it cites were found in a registry or an index.
Abstract
Where am I? This is one of the most critical questions that any intelligent system should answer to decide whether it navigates to a previously visited area. This problem has long been acknowledged for its challenging nature in simultaneous localization and mapping (SLAM), wherein the robot needs to correctly associate the incoming sensory data to the database allowing consistent map generation. The significant advances in computer vision achieved over the last 20 years, the increased computational power, and the growing demand for long-term exploration contributed to efficiently performing such a complex task with inexpensive perception sensors. In this article, visual loop closure detection, which formulates a solution based solely on appearance input data, is surveyed. We start by briefly introducing place recognition and SLAM concepts in robotics. Then, we describe a loop closure detection system’s structure, covering an extensive collection of topics, including the feature extraction, the environment representation, the decision-making step, and the evaluation process. We conclude by discussing open and new research challenges, particularly concerning the robustness in dynamic environments, the computational complexity, and scalability in long-term operations. The article aims to serve as a tutorial and a position paper for newcomers to visual loop closure detection.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 4×
“combination of advances in GPU computational capabilities and large labeled datasets [217].”
BackgroundInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“CNN is a concept introduced by LeCun et al. in the late ’80s [207], [208].”
MethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 6×
“6b), inspired by SIFT, proposes a faster extraction version using an approximation of the determinant of Hessian blob detector for identifying regions-of-interest and the sum of the Haar wavelet response around each point for feature description.”
MethodInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · cited 2×
“, AlexNet [217], VGG [238], ResNet [239], Inception [240], DenseNet [241], and MobileNet [242].”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1×
“However, subsequent studies showed that the utilization of intermediate representations with and without the CNN’s fully connected layers could offer high performances [153], [155] and rich semantic information [234], [235].”
BackgroundFischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893
Research works printed but not linked: 18
- [276] J. Bruce, J. Wawerla, and R. Vaughan, 'The SFU mountain dataset: Semi-structured woodland trails under changing environmental conditions,' in Proc. IEEE Int. Conf. Robot. Automat. Workshop , Seattle, WA, USA, May 2015. -
- [178] I. Biederman, 'Aspects and extensions of a theory of human image understanding,' in Computational Processes in Human Vision: An Interdisciplinary Perspective . Norwood, NJ, USA: Ablex, 1988, pp. 370-428. -
- [151] S. Garg, N. Suenderhauf, and M. Milford, 'Don't look back: Robustifying place categorization for viewpointand condition-invariant place recognition,' in Proc. IEEE Int. Conf. Robot. Automat. (ICRA) , May 2018, pp. 3645-3652. -
- [404] S. L. Bowman, K. Daniilidis, and G. J. Pappas, 'Robust and efficient semantic SLAM with semantic keypoints,' in Proc. AAAI Nat. Conf. Artif. Intell. , 2021, pp. 1-13. <!-- image --> Konstantinos A. Tsintotas (Senior Member, IEEE) received the bachelor's degree from the Department of Automation, Technological Education Institute of Chalkida, Psachna, Greece, in 2010, the master's degree in mechatronics from the Department of Electrical Engineering, Technological Education Institute of Western Macedonia, Kila Kozanis, Greece, in 2015, and the Ph.D. degree in robotics from the Department of Production and Management Engineering, Democritus University of Thrace, Xanthi, Greece, in 2021. He is currently a Post-Doctoral Fellow with the Laboratory of Robotics and Automation, Department of Production and Management Engineering, Democritus University of Thrace. His work is supported through several research projects funded by the European Commission and the Greek Government. His research interests include vision-based methods for modern and intelligent mechatronics systems. Details are available at: https://robotics.pme.duth.gr/ktsintotas <!-- image --> Loukas Bampis received the Diploma degree in electrical and computer engineering and the Ph.D. degree in machine vision and embedded systems from the Democritus University of Thrace (DUTh), Greece, in 2013 and 2019, respectively. He is currently an Assistant Professor with the Laboratory of Mechatronics and Systems Automation (MeSA), Department of Electrical and Computer Engineering, DUTh. His work has been supported through several research projects funded by the European Space Agency, the European Commission, and the Greek Government. His research interests include real-time localization and place recognition techniques using hardware accelerators and parallel processing. More details about him are available at: https://robotics.pme.duth.gr/bampis <!-- image --> Antonios Gasteratos (Senior Member, IEEE) received the M.Eng. and Ph.D. degrees from the Department of Electrical and Computer Engineering, Democritus University of Thrace (DUTh), Greece. He is currently a Professor and the Head of the Department of Production and Management Engineering, DUTh. He is also the Director of the Laboratory of Robotics and Automation (LRA), DUTh, where he is teaching the courses of robotics, automatic control systems, electronics, mechatronics and computer vision. From 1999 to 2000, he was a Visiting Researcher with the Laboratory of Integrated Advanced Robotics (LIRALab), DIST, University of Genoa, Italy. He has served as a reviewer for numerous scientific journals and international conferences. He has published more than 220 papers in books, journals, and conferences. His research interests include mechatronics and robot vision. He is a Fellow Member of IET. He is a Subject Editor of Electronics Letters and an Associate Editor of the International Journal of Optomechatronics and he has organized/co-organized several international conferences. More details about him are available at: https://robotics.pme.duth.gr/antonis
- [211] W. Maddern, A. Stewart, C. McManus, B. Upcroft, W. Churchill, and P. Newman, 'Illumination invariant imaging: Applications in robust vision-based localisation, mapping and classification for autonomous vehicles,' in Proc. IEEE Int. Conf. Robot. Automat. , May 2014, p. 3. -
- [215] P. Rolet, M. Sebag, and O. Teytaud, 'Integrated recognition, localization and detection using convolutional networks,' in Proc. Eur. Conf. Mach. Learn. , 2012, pp. 1255-1263. -
- [119] S. Lynen, M. Bosse, P. Furgale, and R. Siegwart, 'Placeless placerecognition,' in Proc. 2nd Int. Conf. 3D Vis. , Dec. 2014, pp. 303-310. -
- [18] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning , vol. 1, no. 2. Cambridge, MA, USA: MIT Press, 2016. -
- [351] K. MacTavish and T. D. Barfoot, 'Towards hierarchical place recognition for long-term autonomy,' in Proc. IEEE Int. Conf. Robot. Automat. Workshop , May 2014, pp. 1-6. -
- [22] F. Capezio, F. Mastrogiovanni, A. Sgorbissa, and R. Zaccaria, 'Robotassisted surveillance in large environments,' J. Comput. Inf. Technol. , vol. 17, no. 1, pp. 95-108, 2009. -
- [379] M. G. Gollub, R. Dubé, H. Sommer, I. Gilitschenski, and R. Siegwart, 'A partitioned approach for efficient graph-based place recognition,' in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst./Workshop Planning, Perception Navigat. Intell. Veh. , Sep. 2017, pp. 1-5. -
- [52] B. Kuipers and Y.-T. Byun, 'A robust qualitative method for spatial learning in unknown environments,' in Proc. 7th AAAI Nat. Conf. Artif. Intell. , 1988, pp. 774-779. -
- [43] A. Rosinol, M. Abate, Y. Chang, and L. Carlone, 'Kimera: An opensource library for real-time metric-semantic localization and mapping,' in Proc. IEEE Int. Conf. Robot. Automat. (ICRA) , May 2020, pp. 1689-1696. -
- [41] G. H. Lee, F. Fraundorfer, and M. Pollefeys, 'Robust pose-graph loopclosures with expectation-maximization,' in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst. , Nov. 2013, pp. 556-563. -
- [95] M. Milford, H. Kim, S. Leutenegger, and A. Davison, 'Towards visual SLAM with event-based cameras,' in Proc. Robot. Sci. Syst. , 2015, pp. 1-8. -
- [94] R. Finman, L. Paull, and J. J. Leonard, 'Toward object-based place recognition in dense RGB-D maps,' in Proc. IEEE Int. Conf. Robot. Automat. , vol. 76, May 2015, pp. 1-8. -
- [93] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard, and J. McDonald, 'Real-time large-scale dense RGB-D SLAM with volumetric fusion,' Int. J. Robot. Res. , vol. 34, nos. 4-5, pp. 598-626, 2015. - · DOI
- [322] H. Porav, W. Maddern, and P. Newman, 'Adversarial training for adverse conditions: Robust metric localisation using appearance transfer,' in Proc. IEEE Int. Conf. Robot. Automat. (ICRA) , May 2018, pp. 1011-1018. - · DOI
Cited by
Review of simultaneous localization and mapping (SLAM) for construction robotics applications
Yarovoi, A., & Cho, Y. K. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105344 · Cited by 128
A review of visual SLAM for robotics: evolution, properties, and future applications
Al-Tawil, B., Hempel, T., Abdelrahman, A. A., & Al-Hamadi, A. K. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1347985 · Cited by 126
Konstantinidis, F. K., Myrillas, N., Tsintotas, K. A., Mouroutsos, S. G., & Gasteratos, A. C. (2023) · International Journal of Production Research · doi:10.1080/00207543.2023.2270588 · Cited by 77
Self-citationVisual Place Recognition: A Tutorial [Tutorial]
Schubert, S., Neubert, P., Garg, S., Milford, M. J., & Fischer, T. (2023) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2023.3310859 · Cited by 102
“In fact, one of the original drivers for VPR research was the generation of loop closures for SLAM systems, that is, recognizing a place when revisiting it (e.g., in a loop) and tying the current observation with that already in the map (i.e., closure) [8].”
BackgroundLiDAR, IMU, and camera fusion for simultaneous localization and mapping: a systematic review
Fan, Z., Zhang, L., Wang, X., Shen, Y., & Deng, F. Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11187-w · Cited by 112
Metadata
- Authors
- Tsintotas, K. A., Bampis, L., & Gasteratos, A.
- Affiliations
- Democritus University of Thrace (GR)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2022-11
- Volume
- 23
- Issue
- 11
- Pages
- 19929-19953
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W4225108957
- Cited by
- 175
- References
- 397
- Citations by year
- 2026: 28 · 2025: 44 · 2024: 51 · 2023: 40 · 2022: 12
- FWCI
- 16.35
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- SLAM, place recognition, feature extraction, environment representation, dynamic environments, robot navigation, map consistency
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.