SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights
The DOI matches its Crossref record; 20 of the 22 references it cites were found in a registry or an index.
Abstract
Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This has led to develop new methods that explicitly account for such variations by matching sequences [173], gathering different visual appearances into a unified representation [48], or using spatial as well as appearance information [106].”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [173]
Citations
Cites
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 3×
“Many place recognition techniques rely on feature-finding algorithms such as SIFT [9] and SURF [10] which, despite their impressive rotation and scale invariant properties, are inherently unsuitable when dealing with extreme perceptual M.J. Milford and G.F. Wyeth are with the School of Electrical Engineering and Compu…”
MethodSURF: 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
MonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959 · cited 1×
“isual recognition of places and place sequences in the field of robotic navigation has advanced rapidly in recent years, with several techniques [1-5] now being competitive with laser range-based techniques.”
BackgroundA solution to the simultaneous localization and map building (SLAM) problem
Dissanayake, M. W. M. G., Newman, P., Clark, S., Durrant-Whyte, H. F., & Csorba, M. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.938381 · Cited by 2,661
Matching Local Self-Similarities across Images and Videos
Shechtman, E., & Irani, M. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383198 · Cited by 1,076 · cited 1×
“One promising step [15] towards reducing the reliance on consistent feature detection uses the self-similarity of objects within a frame or video sequence to robustly recognize objects under varying conditions.”
BackgroundIncremental mapping of large cyclic environments
Gutmann, J.-S., & Konolige, K. (2003) · Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375) · doi:10.1109/cira.1999.810068 · Cited by 568 · cited 1×
“There have been attempts to increase the robustness of visual techniques to environment change by performing sensor fusion with lasers at the level of landmarks [13] or dense depth maps [14].”
BackgroundFrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping
Konolige, K., & Agrawal, M. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004832 · Cited by 532
RatSLAM: a hippocampal model for simultaneous localization and mapping
Milford, M. J., Wyeth, G. F., & Prasser, D. (2004) · IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 · doi:10.1109/robot.2004.1307183 · Cited by 399 · cited 6×
“The approach taken in this work is partly inspired by the author's previous work in vision-based mapping in RatSLAM [16] [17] [18].”
MethodInfluentialSelf-citationMapping a Suburb With a Single Camera Using a Biologically Inspired SLAM System
Milford, M. J., & Wyeth, G. F. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004520 · Cited by 378 · cited 7×
“The approach taken in this work is partly inspired by the author's previous work in vision-based mapping in RatSLAM [16] [17] [18].”
BackgroundMethodInfluentialSelf-citationDynamic Maps for Long-Term Operation of Mobile Service Robots
Biber, P., & Duckett, T. (2005) · Robotics: Science and Systems I · doi:10.15607/rss.2005.i.003 · Cited by 334 · cited 1×
“The problem of visual place recognition across time has received far less attention, with relatively few attempts to address the problem [6, 7], including high dynamic range approaches [8].”
Background
Cited by
Items 901–987 of 987
Kanji, T. (2021) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9660079
Garcia‐Fidalgo, E., & Ortiz, A. (2018) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-75993-7_3
Stereo Visual SLAM System Reasonably Use Point and Line Features
Qiao, H., Ren, X., Niu, L., Yang, F., & Liu, S. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-6963-7_68
Haque, M. F., & Kang, D.-S. (2022) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2022.20.4.39
takeda, K., & Kanji, T. (2020) · doi:10.31224/osf.io/738bq
“Visual robot self-localization is one of most important issues in mobile robotics and has been studied in many different contexts, including multi-hypothesis pose tracking [9], map matching [10], image retrieval [11], view-sequence matching [3], etc.”
BackgroundActive Map-Matching: Active Self-localization by VPR-to-NBV Knowledge TransferPreprint
Kanji, T. (2021) · doi:10.31224/osf.io/gj6ry
Garcia‐Fidalgo, E., & Ortiz, A. (2018) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-75993-7_4
Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition
Alijani, F., & Rahtu, E. (2021) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp53017.2021.9733543
“Before the rise and dominance of DCNNs, VPR methods utilized conventional hand-crafted features such as local and global image descriptors, to match query images with the reference database [9]–[11].”
MethodGarcia‐Fidalgo, E., & Ortiz, A. (2018) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-75993-7_2
Loop Closure Detection Based on Differentiable Manifold
Dong, T., Xue, B., Zhang, Q., Zhao, Y., Li, W., & Li, M. (2022) · Mobile Information Systems · doi:10.1155/2022/4373064
“Milford and Wyeth [13] constructed short image sequences by using local contrast enhancement processing method according to the deviation matrix between image sequences and then found local best matching for each query image in all short image sequences.”
MethodOptimization techniques for image representation in visual place recognition
Maltar, J., & Matijević, D. (2022) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro55190.2022.9803589
The Research of Loop Closure Detection Algorithm Based on DeepLabv3+
He, J., Song, X., Song, J., & Yang, L. (2021) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice54393.2021.00022
“The traditional loop closure detection algorithm is usually completed by the visual bag-of-words model [3], but due to the use of artificially designed features such as SIFT [4], SURF [5] and ORB [6] to describe the image, it can only deal with limited scenes variety.”
MethodLoop Closure Detection with Incremental Proximity Graph and Multi-words Quantization
Zhang, L., Yan, W., Li, H., & Li, B. (2022) · Asian Control Conference (ASCC) · doi:10.23919/ascc56756.2022.9828011
GDLR: A Robust 3D Laser Descriptor for Loop Closure Detection and Registration
Zhang, N., Rong, S., & Shang, C. (2022) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc55436.2022.00010
“SeqSLAM [7] tries to solve the problems of illumination changes and seasonal variations.”
BackgroundHou, Y., Wang, Y., Fu, Z., & Zhou, S. (2022) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae56463.2022.10056180
“In [6], the use of image sequences for feature extraction can easily achieve better performance than single-frame imagebased method.”
MethodInfluentialA novel Loop Closure Approach in 2D LIDAR SLAM
Wang, H., & Du, D. (2022) · International Conference on Computer Graphics, Image and Virtualization (ICCGIV) · doi:10.1109/iccgiv57403.2022.00006
Place Recognition under Occlusion and Changing Appearance via Disentangled Representations
Chen, Y., Chen, X., & Li, Y. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160506 · Cited by 1
“Typical place recognition includes feature extraction and matching, optionally followed by sequence fusion [11], [12] to reduce the false positive rates, among which this paper focuses on the first part.”
BackgroundSimilarity and Location-based Real-time Loop Closure: SNAPS for SLAM† in Unexplored-Environments
Fathi, K., Darvishy, A., & van de Venn, H. W. (2023) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins57856.2023.10189300
“Moreover, studies targeting traditional methods in loop detection suggest that local descriptors are not robust towards all scenarios, and they leave out the entire image level details [15], [16].”
BackgroundLong-Term LiDAR Place Recognition Based on Phase Congruency in Changing Environments
Cao, F., Li, C., & Wang, T. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10240582
“To achieve long-term place recognition, state-of-the-art visual methods mostly rely on either long image sequences [2-4] or deeply learnt features [5-7].”
BackgroundA Uniform Distribution of Landmarks for Efficient Map Compression
Bouaziz, Y., Royer, E., Bresson, G., & Dhome, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44137-0_29
Towards Full Deep Learning-based SLAM
Khoyani, A. (2023) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2023-15731
A Complementarity-Based Switch-Fuse System for Improved Visual Place Recognition
Waheed, M., Waheed, S., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341876
Self-citationLong-term localization with map compression based on solar information
Bouaziz, Y., Royer, E., Bresson, G., & Dhome, M. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422206
“Many works [6], [7] have addressed this challenge by using image based matching techniques since traditional feature-based comparison methods have shown weaknesses in changing conditions.”
BackgroundMethodScalable and Efficient Hierarchical Visual Topological Mapping
Ramachandran, S., Horgan, J., Sistu, G., & McDonald, J. (2023) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar58858.2023.10406394
“There have also been a number of works suitable for very large scale mapping and localization [9, 10, 11] without using an explicit metric representation.”
BackgroundHardware Software Co-design of an Embedded RGB-D SLAM System
Bouazzaoui, I. E. (2022) · theses.fr (ABES) · doi:10.70675/93ba9ad1z0570z4270z90eezd7685a1eec33 · Cited by 1
Lifelong SLAM Based on Environmental Semantic and Depth Information in Dynamic Scenes
Yu, N., Wang, Y., Gan, M., Ma, N., & Huang, G. (2023) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait60137.2023.10528652
“Instead of computing the similarity by a single image, it uses an image sequence to handle scene environment changes, achieving good experimental results in weather-changing scene recognition tasks [17].”
MethodAdaptive Robust Visual Place Recognition via Image Wise Automatic Method Selection
Wickramasinghe, H. (2024) · Queensland University of Technology · doi:10.5204/thesis.eprints.251496
Spatiotemporal Localization of GPR Sequence Images With 3DResNet18
Hu, Y., Zhang, P., Bi, B., Chen, Y., Xin, Q., & Huang, X. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2887/1/012034
Visual Loop Closure Detection with Thorough Temporal and Spatial Context Exploitation
Li, J., Wang, Z., Di, H., Li, J., & Liang, W. G. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802228
Sequential Semantic Descriptor from 3D Point Clouds for Place Recognition
Lin, C., Liu, Y., Chen, A., & Gao, H. (2024) · International Conference on Algorithms, Computing and Artificial Intelligence (ACAI) · doi:10.1109/acai63924.2024.10899587
“The SeqSLAM [10] is a seminal example of sequence matching.”
Liu, L., Xiong, P., & Liu, F. (2025) · IET Image Processing · doi:10.1049/ipr2.70040
SpikingVPR: Spiking Neural Network-Based Feature Aggregation for Visual Place Recognition
Wang, G., Ren, Z., Zhang, Q., & Cheng, J. S. (2024) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd64214.2024.10920604
“To further enhance the performance of local descriptors, techniques like the Bag of Visual Words (BoVW) [11] and sequence-based methods [12], [13] were introduced.”
A Simulated Dataset to Evaluate the Visual-Inertial Odometry Algorithms
Zhu, X., Zhou, J., Liang, J., Zhou, D., Qiu, Z., Wang, Y., Wu, S., & Wu, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-3349-4_24
Robust outdoor trajectory mapping using CNN features and loop closure optimization
Kazi, K., Khizer, A. N., Memon, F., Memon, T. R., & Memon, A. R. (2025) · Mehran University Research Journal of Engineering and Technology · doi:10.22581/muet1982.0351
LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM
Nakshbandi, M.-M., Sharawy, Z., & Grigorescu, S. M. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097447
“SeqSLAM [7] compares image sequences rather than individual frames for greater robustness, whereas FAB-Map [8] finds loops by comparing the similarities between current and previously recorded frames.”
SeqBEV: Bayesian Sequential Localization Using BEV LiDAR Map
Lu, S., Wei, Y., Xiong, R., & Wang, Y. (2025) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar65431.2025.11139435
“These methods [15]–[24] typically integrate place recognition or direct pose regression with techniques such as Monte Carlo Localization (MCL) and sequential matching.”
Bringing Loop Closure To Event-based SLAM: A Place Recognition Approach
Mirhajianmoghadam, H., & Carrillo, L. R. G. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163738
“Place recognition is crucial in SLAM for identifying previously visited locations [4].”
Loop Closure Detection Based on Spatial Constraints and Weighted Feature Matching
Liang, Z., Wei, Y., Chen, L., Zha, H., Ma, F., Zhang, Q., & Liu, W. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268083
“These maps are fused into feature vectors to reduce the impact of dynamic object occlusions[10].”
Loop closure with a low power millimeter wave radar sensor using an autoencoder
Meiresone, P., Hamme, D. V., & Philips, W. (2024) · Ghent University Academic Bibliography (Ghent University) · Cited by 2
Detecção de fechamento de loop utilizando sequências em uma estratégia hierárquica de três níveis
Rodrigues, F. (2020) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
Visual Place-aided Pedestrian Dead-reckoning System for Large-scale Navigation Applications
Zhang, L., Liu, Y., Zhu, B., Liu, J., Wang, Y., Wang, Z., & Yang, X. (2025) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac66630.2025.11150094
“Seq-SLAM [9] proposed by Milford et al. uses the normalized pixel intensity for global matching to deal with the VPR problem in a challenging IMU Camera Fig.”
He, Q., Wang, Y., Chai, Y., Huang, Q., Zhang, T., Im, S.-K., & Zhang, J. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3635446
“TheseminalSeqSLAM[16] introducedsequencematchingthroughimagesimilarityma-trices,demonstratingstrongperformanceunderappearance changes.”
Yu, M., Zhang, Z., Zhang, X., Zhang, J., Zhou, B., & Chen, B. (2026) · Electronics · doi:10.3390/electronics15030528
A neuromorphic model of the insect visual system for natural image processingPreprint
Hines, A., Nordström, K., & Barron, A. B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.06405
“…using the differences D of the absolute pixel values of a query image to every reference image, where the minimum value is the closest match [42]: where x, y are the spatial coordinates of the image, R x , R y are the dimensions of the downsampled image, and p are the pixel intensity values.”
Trivigno, G. (2025) · PORTO@Iris · doi:10.13121/polito/porto/3002976 · Cited by 1
Location models for visual place recognition
Stumm, E. S. (2015) · theses.fr (ABES) · doi:10.70675/13541cbazaefdz42e7z83bbzdde6e2e8aebb · Cited by 1
How Roboticists Think about Navigation and Major Unsolved Challenges
Milford, M. J. (2026) · Springer eBooks · doi:10.1007/978-3-032-20563-6_3
Self-citationChirca, M. (2016) · theses.fr (ABES) · doi:10.70675/05d3fc79z9919z4035z81c2z685dabe2b74c · Cited by 7
“Cummins est une technique de navigation et cartographie qui n’utilise que la comparaison d’images sans utiliser aucune information métrique [Cummins and Newman, 2008; Paul and Newman, 2010; Cummins and Newman, 2011; Glover et al., 2012; Milford and Wyeth, 2012].”
de Chamisso, F. M. (2016) · theses.fr (ABES) · doi:10.70675/895a1208z3a55z4cbbzaef8zd97c2f15d05a
Place recognition based visual localization in changing environments
Qiao, Y. (2017) · theses.fr (ABES) · doi:10.70675/2bdcab63zaa48z4e94zab82zf631c089b57d
“weather conditions, or poor visibility [72, 82].”
BackgroundMethodInfluentialLocalisation par l'image en milieu urbain : application à la réalité augmentée
Fond, A. (2018) · theses.fr (ABES) · doi:10.70675/ecbf8e26zc6bcz4a54zbba7z5fef9ba17cd1
“Ainsi dans [84], les auteurs montrent que ces descripteurs sont plus robustes aux changements d’illumination ou de conditions climatiques que les approches locales.”
BackgroundSalehi, A. (2018) · theses.fr (ABES) · doi:10.70675/78c7864fz5568z47d0z92dez87c9d22c84c0
“[2, 81]) permettent d’obtenir des résultats fiables en faisant la mise en correspondance entre des séquences d’images plutôt qu’entre des images indi-”
BackgroundInfluentialNavigation autonome bio-inspirée appliquée à un robot hexapode
Dupeyroux, J. (2019) · theses.fr (ABES) · doi:10.70675/cc20144bz6874z4fdfz84fcz9d1a7d3d38f6 · Cited by 2
Localisation d'un robot humanoïde en milieu intérieur non-contraint
Nowakowski, M. (2019) · theses.fr (ABES) · doi:10.70675/781e415ez63c5z46c6zba5cz318e64361ca6
Robotique coopérative aéro-terrestre : Localisation et cartographie hétérogène
Renaudeau, B. (2019) · theses.fr (ABES) · doi:10.70675/b782366azea3fz45a3zbd5ezff6912417939
Localisation visuelle par approche neuromimétique dans le contexte de la délégation de conduite
Espada, Y. (2020) · theses.fr (ABES) · doi:10.70675/bec8f2e5z48fez49a7zb8e2z2678dbac10d8 · Cited by 1
Robustness of Visual SLAM techniques to light changing conditions
Wang, X. (2022) · theses.fr (ABES) · doi:10.70675/cebde6b6zdf19z49ebz9810z166c5d46c923
Vehicle localization based on scene perception
Liu, L. (2021) · theses.fr (ABES) · doi:10.70675/43424a72z2eedz41d7z9829z41cfa8ff911a
PHMRNet: Persistent Homology Based Mamba–RWKV Network for LiDAR Place Recognition
Zhou, D., Jiang, X., Chen, S., Cai, Z., Wu, J., Chen, X., Yang, J., & Vong, C. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3683589
Pedestrian Localization Using Smartphone LiDAR in Indoor Environments
Sung, K., & Kim, J. (2026) · Electronics · doi:10.3390/electronics15091810
A Fast Visual Triangle Descriptor for Multi-sensor Loop Closure Detection
Chen, L., Li, Z., Li, M., & Liang, K. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487507
“Consequently, alternative strategies like SeqSLAM [20] have emerged, utilizing route-based temporal information to surpass the performance of traditional frameworks like FAB-MAP, particularly when visual consistency is absent.”
Cheng, Y., Liu, X., Chen, S., & Xu, C. (2026) · Remote Sensing · doi:10.3390/rs18101556
Real-Time Visual Place Recognition via Cluster-Aware Hierarchical CNNs
Hafez, A. H. A., Alqaraleh, S., & Jouma, A. E. (2026) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi68585.2026.11539770
“Sequence methods such as SeqSLAM further boost recall but add latency/assumptions about temporal continuity [10].”
HOG-supervised compact CNNs for real-time visual place recognition
Hafez, A. H. A., & Odeh, I. (2026) · Scientific Reports · doi:10.1038/s41598-026-54833-1
“Whereas SeqSLAM 32 showed that patch-normalized gradient-based features could even achieve robustness to extreme seasonal variations, global scene representations like Gist 33 and probabilistic appearance-based approaches like FAB-MAP 34 allowed recognition across moderate viewpoint and…”
Wen, S., Bai, K., LI, P., Zhao, Q., Liu, H., & Yu, F. R. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3702406
Robust Visual Place Recognition via modern Hopfield networks and foundation models
Hashimoto, T., Isokawa, T., Kobayashi, M., & Kamiura, N. (2026) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.17.932
Khan, E. U., & Kim, G.-W. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3709583
Wampamba, A., Elahi, M. H., & Masih‐Tehrani, M. (2026) · Engineering Archive (engrXiv) · doi:10.31224/6485
TileLoc: Sequential Visual Place Recognition of UAVs using Public Tile Maps
Heo, D., 전승표, Choi, J. H., Jeong, D., Wi, H., Jang, I. S., & Choi, S. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3715032
Hybrid State Space Modeling for Sequence-Based Robot Localization Under Challenging Environments
Li, Z., & Shang, T. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3714880
“Early sequential approaches, such as SeqSLAM [14] and [15], employed simple template-matching strategies that compared entire image sequences but lacked advanced temporal modeling capabilities.”
Deep recurrent visual place recognition based on softmax fine-tuned image representations
Maltar, J., Marković, I., Matijević, D., & Petrović, I. (2026) · Engineering review · doi:10.30765/er.3383
Hybrid Guided Variational Autoencoder for Visual Place Recognition
Wang, N., You, Z., Neftci, E., & Schoepe, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31933-3_8
Unordered Landmark Visual Navigation
Ren, H., Zhu, J., Li, Y., Bi, Z., Zheng, L., Li, Z., Yuan, Y., Wan, Z., Zhang, D., Qi, L., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37135-5_22
GSSeq: Rendered-Reference Sequential Loop Verification for UAV 3D Gaussian Splatting SLAM
Park, J., Park, C., Sa, I., Kim, S., Lee, H.-M., Noh, D., & Ahn, H. S. (2026) · Drones · doi:10.3390/drones10090643
Spatio-temporal Self-organizing Visual Place RecognitionPreprint
da Silva, A. F. L. A., Araujo, A. F. R., & Petiteville, A. D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7379993
TRAIL: Trajectory-Aware Visual Place Recognition Against Unordered Databases
Kloepfer, D. A., & Wenzel, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37321-2_22
“Sequence-based localization originates from loop closure detection, where SeqSLAM [32] and its variants [5,36] match query sequences against previously visited locations.”
Tsukahara, K., Kanji, T., Iwata, D., Liang, J. T. Y., & Xie, W. (2026) · SN Computer Science · doi:10.1007/s42979-026-05297-7
“Compared to other self-localization tasks, including image retrieval [12], map matching [13], sequence matching [14], and multiple-hypothesis tracking [15], VPR is particularly scalable.”
Joint Multicondition Representation Modeling via Matrix Factorization for Visual Place Recognition
Ismagilov, T., Majeed, S., Milford, M. J., Nguyen, T. V. T., Ramchurn, S. D., & Ehsan, S. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3734352
“Section II reviews related work.”
Self-citationGorodnichev, M. G. (2026) · Smart Cities · doi:10.3390/smartcities9100163
“SeqSLAM aligns image sequences under severe appearance change [42]; HMM/Viterbi formulations impose temporal transition structure [43]; and OpenSeqSLAM2.”
A Survey of Map Construction and Management Methods for Single Embodied Agents
Yan, C., Feng, Z., Ye, F., Sun, Y., Gong, Y., & Liu, Y. (2026) · Sensors · doi:10.3390/s26196242
Recovering from Pose-Selection Failures in Repeated Visual LocalizationPreprint
Kim, J., Kang, W., & Kim, T.-W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.16409
“Sequence-based place recognition uses temporal context for reference matching [7], [8], [9], [10], while odometry-based verification propagates past estimates [11].”
TRACE-Loc: Causal Trajectory-Constrained Cross-View Localization for GNSS-Denied UAVs
廖, 守., Chen, H., Li, Z., & Liu, Z. (2026) · Drones · doi:10.3390/drones10110794
An Environment-Matching-Based Anti-Cloning System for IoT Visual Surveillance Devices
Cai, Z., Luo, J., Zhang, G., Wang, J., & Wu, Q. (2026) · International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR) · doi:10.1145/3847445.3847489
“SeqSLAM [10] introduced sequence-based matching for robust place recognition under appearance changes.”
Hafez, A. H. A. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105438
Automated road position alignment of multi-year pavement image sequences with support checks
Raisher, J. A., Lou, Z., Yang, Z., Wang, H., & Tsai, Y. J. (2026) · International Journal of Pavement Engineering · doi:10.1080/10298436.2026.2760913
Metadata
- Authors
- Milford, M. J., & Wyeth, G. F.
- Affiliations
- Queensland University of Technology (AU)
- Venue
- 2012 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2012-05
- Pages
- 1643-1649
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2110405746
- Cited by
- 981
- References
- 22
- Citations by year
- 2026: 22 · 2025: 44 · 2024: 66 · 2023: 61 · 2022: 82 · 2021: 115 · 2020: 110 · 2019: 125 · 2018: 99 · 2017: 74 · 2016: 52 · 2015: 61 · 2014: 38 · 2013: 25 · 2012: 7
- FWCI
- 78.04
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- visual SLAM, visual navigation, route recognition, seasonal variation, heavy rainfall, vehicle-mounted camera, trajectory matching
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.