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 701–800 of 987
Seeing Objects in Dark with Continual Contrastive Learning
Dutta, U. K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25075-0_21 · Cited by 7
“The Alderdey dataset [22] has day-night correspondences, but no annotations.”
BackgroundLeveraging cross-view geo-localization with ensemble learning and temporal awareness
Ghanem, A., Abdelhay, A., Salah, N. E., Eldeen, A. N., Elhenawy, M. M. Z., Masoud, M., Hassan, A. M., & Hassan, A. A. (2023) · PLoS ONE · doi:10.1371/journal.pone.0283672 · Cited by 3
Sequential Monte Carlo localization in topometric appearance maps
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231197723 · Cited by 4
“Several works have proposed to exploit the spatio-temporal consistency conferred by image sequences to improve the accuracy of VPR (Milford and Wyeth 2012; Vysotska and Stachniss 2015, 2017).”
BackgroundAWLC: Adaptive Weighted Loop Closure for SLAM with Multi-Modal Sensor Fusion
Zhou, G., Fei, H., Liu, W., Zhang, Y., Wei, H., & Hou, X. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126624502335 · Cited by 3
Wang, Z., Zhang, Y., Zhao, X., Ning, J., Zou, D., & Pei, M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611102 · Cited by 3
“However, VPR remains challenging due to dynamic environmental changes[4][5][6] and annoying perceptual aliasing[7].”
BackgroundRegressing Transformers for Data-efficient Visual Place Recognition
Leyva-Vallina, M., Strisciuglio, N., & Petkov, N. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611288 · Cited by 3
“It is an important component of visual navigation [1], [2] for autonomous driving and robotics [3].”
BackgroundMethodALCDNet: Loop Closure Detection Based on Acoustic Echoes
Liu, G., Cui, W., Jia, N., Xi, Y., Li, S., & Wang, Z. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3519906 · Cited by 3
“Loop closure detection: Loop closure detection techniques are primarily categorized into visual-based [4], [5], [6], [7], [8] and LiDAR-based [9], [10], [11] methods.”
Predicting the long-term robustness of visual features
Metka, B., Besetzny, A., Bauer-Wersing, U., & Franzius, M. (2015) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2015.7251497 · Cited by 3
Mobile robot localization by GPS and sequential appearance-based place recognition
Saito, T., & KURODA, Y. (2013) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2013.6776624 · Cited by 3
“In this study, we employ SeqSLAM [12][13] as sequential appearance-based place recognition.”
BackgroundMethodInfluentialMining visual experience for fast cross-view UAV localization
Taisho, T., Enfu, L., Kanji, T., & Naotoshi, S. (2015) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2015.7404949 · Cited by 3
“On the other hand, in [7], robust place recognition was realized by global feature approaches, whereby each input scene is described by a single global feature vector; however, it is explicitly assumed that image T. Tsukamoto, E. Liu, K. Tanaka, and N. Sugegaya are with Graduate School of…”
BackgroundMethodResultDéjà vu: Scalable place recognition using mutually supportive feature frequencies
Jacobson, A., Scheirer, W. J., & Milford, M. J. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206580 · Cited by 3
Self-citationLi, C.-T., Siu, W.-C., & Lun, D. P.-K. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917364 · Cited by 3
“In our experiments, we compare our proposed method with several state-of-the-art approaches, namely SeqSLAM [4], ABLE-M [7,8], CALC [12], and AlexNet conv3 feature-based approach [11,15,24], on 3 challenging datasets.”
BackgroundMethodInfluentialBio-inspired celestial compass yields new opportunities for urban localization
Dupeyroux, J., Viollet, S., & Serres, J. (2020) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med48518.2020.9183367 · Cited by 3
“(SLAM) ones, has led to outstanding results on-board cars, drones, and other ground vehicles for outdoor and indoor applications [4], [5], [6].”
BackgroundInertial Aided 3D LiDAR SLAM with Hybrid Geometric Primitives in Large-scale Environments
Chen, W., Zhao, H., Shen, Q., Xiong, C., Zhou, S., & Liu, Y. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561511 · Cited by 3
“Instead of detecting loops by finding the best single match with the smallest distance between descriptors, a more robust and accurate sequence-based matching approach [29] is employed.”
MethodGlobal Robot Ego-localization Combining Image Retrieval and HMM-based FilteringPreprint
Barz, C. L., Thome, N., Cord, M., Herbin, S., & Sanfourche, M. (2014) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 3
Connecting Visual Experiences using Max-flow Network with Application to Visual LocalizationPreprint
Hafez, A. H. A., Agarwal, N., & Jawahar, C. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.00208 · Cited by 3
“…of the displacement parameter k max , (b) show how the matching performance is improved when matching is done with respect to multiple image sequences, and finally (c) show the a comparison of our algorithm to the state-of-the-art image sequence matching methods, i.e. SeqSLAM [8] and ABLE-M [27].”
BackgroundMethodResultInfluentialLong-range stereo visual odometry for unmanned aerial vehicles
Warren, M. (2015) · QUT ePrints (Queensland University of Technology) · Cited by 4
Mining Minimal Map-Segments for Visual Place ClassifiersPreprint
Kanji, T. (2019) · doi:10.31224/osf.io/v74eq · Cited by 3
Mobile robot path drift estimation using Visual Streams
Filho, H. P., & Ohya, A. (2014) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2014.7028036 · Cited by 2
“sequence recognition [14] Monocular camera Outdoors Yes Yes Yes”
BackgroundWilliams, H. A., Browne, W. N., & Milford, M. J. (2012) · QUT ePrints (Queensland University of Technology) · Cited by 2
Self-citationMining Visual Phrases for Visual Robot Localization
Tanaka, K., Yuuto, C., & Ando, M. (2016) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2016.p0057 · Cited by 2
Night-to-Day Translation via Illumination Degradation Disentanglement
Lan, G., Yang, Y., Wang, Z., Wang, D., Li, X., & Zhao, B. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3700823 · Cited by 2
Visual Place Recognition in Unstructured Driving Environments
Rai, U., Gangisetty, S., Hafez, A. H. A., Subramanian, A., & Jawahar, C. V. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802708 · Cited by 2
“Chen et al. [25] leveraged the overfeat network [26] with Seq-SLAM [27].”
UniphorM: A New Uniform Spherical Image Representation for Robotic Vision
André, A. N., Morbidi, F., & Caron, G. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3547266 · Cited by 2
Zhang, S., Wu, J., Wang, K., & Deng, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3550799 · Cited by 2
Tao, H., Liu, B., Chen, C., Huang, T., Li, H., Cui, J., & Zhang, H. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247364 · Cited by 2
“During the past decade, researchers have conducted extensive studies to address challenges such as database scale [3], viewpoint variations [4], illumination changes [5], seasonal transitions [6] and computational efficiency [7], leading to remarkable advancements.”
A Review of Learning Based Visual Relocalization Methods
Lin, H., Wang, Y., Yin, B., & Yang, X. (2025) · Computational Visual Media · doi:10.26599/cvm.2025.9450492 · Cited by 3
Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition
Cheng, J., Li, W., He, Z., Jia, M., Chen, X., He, Z., Wu, J., Vong, C., & Zhang, W. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836434 · Cited by 2
Kim, H., Choi, J. H., Kim, J., Yang, G., Jeong, S., Lim, H., & Cho, Y. M. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261464202 · Cited by 2
Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition
Lau, Y. K. I., Chen, C., Jin, G., & Feng, C. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11695828 · Cited by 2
“Early Seq-VPR methods relied on handcrafted descriptors combined across frames, but these lacked robustness to environmental changes [12].”
Filko, D., Cupec, R., & Nyarko, E. K. (2016) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2016.03.007 · Cited by 2
Boosting the Performance of Scene Recognition via Offline Feature-Shifts and Search Window Weights
Li, C.-T., Siu, W.-C., & Lun, D. P.-K. (2018) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2018.8631883 · Cited by 2
Development of a semantic scene conversion model for image-based localization at night
Kim, D., Shin, S., Park, J., & Shin, S. Y. (2019) · ACM Conference on Research in Adaptive and Convergent Systems (RACS) · doi:10.1145/3338840.3355676 · Cited by 2
“For example, Milford and Wyeth proposed SeqSLAM [11] that utilizes multiple consecutive images to obtain enough visual features for localization at night.”
BackgroundMethodKanji, T. (2021) · IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) · doi:10.1109/civemsa52099.2021.9493670 · Cited by 2
Zhou, Z. S., Hu, Z., Xiao, H., & Tao, Q. (2022) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981221094585 · Cited by 2
“Milford and Wyeth (14) proposed a novel method named seqSLAM to enhance the accuracy and robustness of navigation by matching sequence images.”
MethodAn efficient loop closure detection method based on spatially constrained feature matching
Zhang, H., Zhao, T., Zhong, Y., Yin, Y., Yuan, H., & Dian, S. (2022) · Intelligent Service Robotics · doi:10.1007/s11370-022-00423-9 · Cited by 2
“Meanwhile, sequence-based methods such as [17], which have robust performancewhen the illumination changes, are based on image sequence-to-sequence rather than frame-to-frame matching methods.”
MethodRelational graph location network for multi-view image localization
Yang, Y., & Liu, X. (2023) · Journal of Systems Engineering and Electronics · doi:10.23919/jsee.2023.000050 · Cited by 2
Semantic-based visual vocabulary for loop closure detection
Papapetros, I. T., Oikonomou, K. M., Kansizoglou, I., Tsintotas, K. A., & Gasteratos, A. C. (2023) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist59124.2023.10355694 · Cited by 7
Nakamura, Y., Sasaki, A., Toda, Y., & Kubota, N. (2024) · SICE International Symposium on Control Systems (SICE ISCS) · doi:10.23919/siceiscs60954.2024.10505755 · Cited by 2
“SeqSLAM [22] is a view-based localization method that performs robust matching by comparing the reference image sequence to the input sequence.”
MethodNPR: Nocturnal Place Recognition Using Nighttime Translation in Large-Scale Training Procedures
Liu, B., Fu, Y., Lu, F. H., Cui, J., Wu, Y., & Zhang, H. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3403247 · Cited by 6
VDNA-PR: Using General Dataset Representations for Robust Sequential Visual Place Recognition
Ramtoula, B., Martini, D. D., Gadd, M., & Newman, P. M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611379 · Cited by 2
“Methods such as SeqSLAM [16] and [17] belong to this family, where the first samples and validates feasible trajectories in the database to assess the most likely one and the second uses a matrix value decomposition to eliminate possible noisy detections.”
MethodTSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation
Shen, Y., Liu, M., Lu, H., & Chen, X. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611612 · Cited by 2
“Early work by Milford et al. [18] introduced SeqSLAM for outdoor VPR.”
MethodTao, Y., Liu, A., Yan, X., Yan, X., Ouyang, Y., Deng, X., Cong, X., & Zhang, F. (2024) · Journal of Field Robotics · doi:10.1002/rob.22451 · Cited by 2
LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition
Akcal, M. U., Raikov, I., Gribkova, E., Choudhuri, A., Kim, S. H., Gazzola, M., Gillette, R., Soltész, I., & Chowdhary, G. V. (2025) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1490267 · Cited by 2
“We compared our method with Sum-of-Absolute-Differences (SAD) [67], NetVLAD [48], the current best-performing SNN method, Ensemble SNNs [56], and a previous SNN method by the same authors, Weighted Assignment SNN (WNA) [55].”
Spatial–Temporal U-Net for Localizing Ground-Penetrating Radar
Chen, Y., Zhang, P., Bi, B., Shen, L. C., Jin, T., & Huang, X. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3572338 · Cited by 2
“To this end, a sequential search method called SeqSLAM [9] was developed, which performs local velocity searches in a column-normalized fractional matrix, followed by SeqVLAD [10], which compresses sequence descriptions, and SeqOT [11], which further enhances accuracy by incorporating an attention…”
NocPlace: Nocturnal Visual Place Recognition via Generative and Inherited Knowledge Transfer
Liu, B., Tao, H., Huang, T., Tang, F., Wu, Y., Cui, J., & Zhang, H. (2026) · Lecture notes in computer science · doi:10.2139/ssrn.6127003 · Cited by 2
Smooth localization independent of GPS using coarse height maps
Wei, C., Wu, T. T., & Fu, H. (2015) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2015.7162620 · Cited by 2
Using n-grams of spatial densities to construct maps
Maffei, R. D. Q., Jorge, V. A. M., Rey, V. F., Franco, G. S., Giambastiani, M., Barbosa, J., Kolberg, M., & Prestes, E. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353918 · Cited by 4
“Vision-based approaches are extensively used for loop detection [10], [5], [13].”
BackgroundMethodInfluentialOmnidirectional Visual Place Recognition using Rotation Invariant Sequence Matching
Hansen, P., & Brett Browning, A. (2018) · KiltHub Repository · doi:10.1184/r1/6557057 · Cited by 2
Visual Localization Using Sequence Matching Based on Multi-feature Combination
Qiao, Y., Cappelle, C., & Ruichek, Y. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48680-2_29 · Cited by 2
Visual localization based on sequence matching using ConvNet features
Qiao, Y., Cappelle, C., Ruichek, Y., & Dornaika, F. (2016) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2016.7793293 · Cited by 2
A BRIEF-Gist based efficient place recognition for indoor home service robots
Jeon, Y., Lee, T., Kim, C., Yi, D.-H., & Cho, D. (2016) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2016.7832506 · Cited by 2
“SeqSLAM method [11] uses sum of absolute differences between contrast enhanced, low-resolution images.”
MethodVisual place recognition techniques for pose estimation in changing environments
Lowry, S. M., & Andreasson, H. (2016) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 2
Global Localization Using Low-frequency Image-based Descriptor and Range Data-based Validation
Park, C.-S., & Song, J. (2018) · International Journal of Control Automation and Systems · doi:10.1007/s12555-016-0491-y · Cited by 2
“Recently, a method of image-based place recognition has been proposed by preprocessing images such as SeqSLAM [18] to overcome the shortcomings of keypointbased methods.”
MethodVisual Localization in Changing Environments using Place Recognition Techniques
Xin, Z., Cai, Y., Cai, S., Zhang, J., Yang, Y., & Wang, Y. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545833 · Cited by 2
Em-SLAM: a Fast and Robust Monocular SLAM Method for Embedded Systems
Wu, Y., Li, Z., Shivakumara, P., & Lü, T. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545173 · Cited by 2
“Recently, SLAM have attracted lots of attentions from researchers and companies, since they can be deployed on different types of automatic agents, from mobile robots to drones, for navigation [4], map reconstruction [5] and so on.”
BackgroundA Collaborative Human-Robot Framework for Visual Topological Mapping of Coral Reefs
Maldonado-Ramírez, A., & Torres-Méndez, L. A. (2019) · Applied Sciences · doi:10.3390/app9020261 · Cited by 2
“For example, SeqSLAM [18] has been used to recognize places across different hours of the day or seasons of the year.”
BackgroundMethodResultInfluentialAppearance-Based Along-Route Localization for Planetary Missions
Grixa, I., Schulz, P., Stürzl, W., & Triebel, R. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594518 · Cited by 2
“Results of our method in comparison with the original SeqSLAM, performed on the datasets used in [5] and [24], as well as our own dataset from the Mt.”
BackgroundMethodInfluentialA Novel Global Localization Method Using 3D Laser Range Data in Large-Scale and Sparse Environments
Zhao, M. N., Wang, J., Chen, W., & Wang, H. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8664836 · Cited by 2
“description is widely used in the problem of visual localization and loop-closure detection [3].”
BackgroundTransforming multiple visual surveys of a natural environment into time-lapses
Griffith, S., Dellaert, F., & Pradalier, C. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919881205 · Cited by 2
“1 gets a boost in scalability owing to its low-resolution image alignment, similar to the idea to use compact image templates to keep image comparison fast (Arroyo et al., 2015; Milford and Wyeth, 2012).”
BackgroundMethodInfluentialNOSeqSLAM: Not only Sequential SLAM
Maltar, J., Marković, I., & Petrovic, I. K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-35990-4_15 · Cited by 2
“This insight into data sequentiality can help us build more robust systems [12], [16] and, as it will be seen, the proposed method strongly relies on it.”
MethodFeature-Agnostic Low-Cost Place Recognition for Appearance-Based Mapping
Kazmi, S. M. A. M., Mohamed, M. A., & Mertsching, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34995-0_5 · Cited by 2
Matching Image Sequences using Mathematical Programming: Visual Localization Applications
Abdulhafiz, A. H. (2020) · International Journal Of Engineering & Applied Sciences · Cited by 2
An Appearance and Viewpoint Invariant Visual Place Recognition for Seasonal Changes
Arshad, S., & Kim, G.-W. (2020) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas50221.2020.9268397 · Cited by 2
“[18] O O O X G Image pixel intensities”
BackgroundA Direct Approach of Path Planning Using Environmental Contours
Yu, H., Liang, L., Shi, P. J., & Jiang, Q. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01271-4 · Cited by 2
“Research on robotic exploration has focused on how to suppress sensor noises and acquire accurate positioning and mapping [21–23].”
BackgroundMetric learning with generator for closed loop detection in VSLAM
Chang, J., Dong, N., Li, D., Ip, W. H., & Yung, K. L. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-020-01067-7 · Cited by 2
“Many excellent appearance-based loop detection methods refer to the Bag of Words (BoW) [10, 11], for instance, FAB-MAP [12] and SeqSLAM [13] initially used a pure topology system for loop detection.”
MethodCondition-Invariant Robot Localization Using Global Sequence Alignment of Deep Features
Oh, J., Han, C., & Lee, S. (2021) · Sensors · doi:10.3390/s21124103 · Cited by 2
“To compare the performances of the proposed method, the resulting path of the SeqSLAM [15] and DP [33] are also presented.”
BackgroundMethodInfluentialRobust Pose Estimation Based on Normalized Information Distance
Chen, Z., & Heckman, C. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636532 · Cited by 2
“…are capable of coping with extreme illumination changes, like for example experienced based mapping [3] or localizing against a navigation sequence [4], these techniques mitigate the problem by simply using redundant information and storing all the different conditions in maps that are…”
BackgroundA Loop Closure Detection Algorithm Based on Geometric Constraint in Dynamic Scenes
Cheng, H., Zhao, B., & Wang, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93046-2_44 · Cited by 2
Mixture of histograms of autocorrelation based Chordiogram image descriptor for image retrieval
Sathiamoorthy, S., Saravanan, A., & Ponnusamy, R. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13200-8 · Cited by 2
Visual Place Recognition Using Region of Interest Extraction with Deep Learning Based Approach
Sasikumar, P., & Sathiamoorthy, S. (2022) · Smart innovation, systems and technologies · doi:10.1007/978-981-19-2541-2_28 · Cited by 2
Open Challenges and Conclusion
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-09396-8_6 · Cited by 2
Dynamic Places’ Definition for Sequence-Based Visual Place Recognition
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-09396-8_4 · Cited by 2
Loop Closure Detection Based on Compressed ConvNet Features in Dynamic Environments
Jiang, S., Zhou, Z., & Sun, S. (2023) · Applied Sciences · doi:10.3390/app14010008 · Cited by 2
Deep Learning Based Place Recognition for Challenging Environments
Kumar, D. (2016) · UWSpace (University of Waterloo) · Cited by 4
ARTiS: Appearance-based Action Recognition in Task Space for Real-Time Human-Robot CollaborationPreprint
Eich, M., Rowlands, S., & Wyeth, G. F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05432 · Cited by 2
“AND HEAD OF THE ASSEMBLER WE COMPARE OUR TWO APPROACHES WITH THE SEQSLAM [18] WHICH IS A FAST ONLINE METHOD FOR PLACE”
BackgroundMethodSelf-citationFast-SeqSLAM: Place Recognition and Multi-robot Map Merging
Siam, S. M. (2017) · ERA: Education and Research Archive (University of Alberta) · doi:10.7939/r3ff3mb9s · Cited by 2
Loop-Closure Detection Based on 3D Point Cloud Learning for Self-Driving Industry Vehicles.Preprint
Liu, Z., Suo, C., Zhou, S., Chen, W., Wang, H., & Liu, Y. (2019) · arXiv (Cornell University) · Cited by 2
Learning Condition Invariant Features for Retrieval-Based Localization from 1M ImagesPreprint
Thoma, J., Paudel, D. P., Chhatkuli, A., & Gool, L. V. (2020) · Lirias · doi:10.48550/arxiv.2008.12165 · Cited by 2
“It is worth noting that, apart from feature learning, image retrieval can also benefit from works on improving feature matching [37,50], as well as map image summarization [51], and exploiting temporal closeness of images [31,30].”
Appearance-Invariant 6-DoF Visual Localization using Generative Adversarial NetworksPreprint
Lin, Y., Huang, J., & Lian, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13191 · Cited by 3
“SeqSLAM [11] attempts to match sequences of images rather than individual images.”
SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place RecognitionPreprint
Garg, S., & Milford, M. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11481 · Cited by 2
“However, most of these methods only focus on robustly aggregating single image match scores along a sequence [25, 26, 23, 35], where single image representations are agnostic to this post sequential processing.”
BackgroundMethodSelf-citationDeep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene DescriptorPreprint
Kanji, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.02786 · Cited by 2
““a[m]” (a ∈ [1,10]) is a naive strategy that repeats the same forward movement a[m] at every viewpoint, independent of the RRFs.”
BackgroundParameterization of Vector Symbolic Approach for Sequence Encoding Based Visual Place Recognition
Kempitiya, T., Silva, D. D., Kahawala, S., Haputhanthri, D., Alahakoon, D., & Osipov, E. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892397 · Cited by 1
“SeqSLAM is an algorithm that works best in these challenging changing environments [4].”
MethodSelf-Supervised Lidar Place Recognition in Overhead Imagery Using Unpaired Data
Tang, T. Y., Martini, D. D., & Newman, P. M. (2023) · Robotics: Science and Systems · doi:10.15607/rss.2023.xix.098 · Cited by 2
“SeqSLAM [42] proposes 1-”
Deng, Y., Xiao, R., Li, J., & Lv, J. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8070-3_30 · Cited by 1
“2 shows the comparison of the PR curves obtained by our proposed method and the original Ratslam, DBoW2 [21], and SeqSLAM [22] algorithms for LCD on four datasets, including NC’s, and CiC’s left and right image datasets.”
MethodVisual Place Recognition Under a High-Dimensional Subspace Clustering Perspective
Silva, A. F. L. A. D., Júnior, M. R. D. S., Araujo, A. F. R., & Petiteville, A. D. (2023) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre59448.2023.10332995 · Cited by 1
Hierarchical Unsupervised Topological SLAM
Sharma, A., Mehan, Y., Dasu, P., Garg, S., & Krishna, K. M. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421878 · Cited by 1
EFormer-VPR: Fusing Events and Frames with Transformer for Visual Place Recognition
Zhang, Y., Shen, Y., Zhu, Z., Hai, R., Chen, S., & Zheng, N. (2024) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc58415.2024.10919907 · Cited by 1
“SeqSlam [33] matches locations for short image sequences, using the relative position information between consecutive frames.”
A Visual SLAM Loop Closure Detection Method for Spraying Robots in Hilly Orchard
Cai, Y., Zhang, G., Xian, K., Dong, J., Gu, X., Liu, Y., & Liu, B. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934481 · Cited by 1
“Enhancements to traditional algorithms such as Bag of Words (BoW) [1] and SeqSLAM[2], along with the integration of deep learning approaches—like Convolutional Neural Networks (CNNs) [3] for feature extraction and matching—have markedly improved system robustness and accuracy in general…”
Li, P., Wen, S., Yu, F. R., & Qiu, T. Z. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3583760 · Cited by 1
Li, Z., Jiang, J., Fan, J., & Yan, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_28 · Cited by 1
Wang, J., Liu, D., Jizhuo, C., Da, J., Hu, J., Xue, Z., Kästner, L., & Soh, H. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696152 · Cited by 1
SF-Loc: A Visual Mapping and Geo-Localization System Based on Sparse Visual Structure Frames
Zhou, Y., Li, X., Li, S., Xia, C., Wang, X., & Feng, S. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3625563 · Cited by 1
Jingsi, 黄. H., Siyu, 李. L., Qingwu, 段. D., & Zheng, 李. L. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250782 · Cited by 1
Pan, Y., Zhu, Y., Peng, X., Liao, J., & Zhou, B. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3669806 · Cited by 1
Yao, C.-W., Cheng, K.-S., & Lin, H. (2014) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2014.6918701 · Cited by 1
“used the feature-based image retrieval called sequential simultaneous localization and mapping (SeqSLAM) [7].”
MethodPart-based SLAM for partially changing environments
Yuuto, C., Kanji, T., & Masatoshi, A. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739700 · Cited by 1
“Discriminatively matching global feature vectors typically requires knowledge of image sequences and a sequence-based image matching algorithm, such as SeqSLAM [2].”
BackgroundA view-based wearable personal navigator with inertial speed estimation
Harada, M., Miura, J., & Satake, J. (2013) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2013.6705516 · Cited by 1
“, [7], [8]).”
Geometric Indexing for Recognition of Places
Lara-Álvarez, C. A., Rojas‐Domínguez, A., & Bayro-Corrochano, E. J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_67 · Cited by 1
“[0, 0, 1] (I1, 1); (I2, 2) [0, 0, 2] (I1, 2); (I2, 1) [2, 4, 8] (I2, 1) [5, 6, 7] (I2, 1)”
BackgroundMethodRobust Localization in Environmental Variation Using GPS and Sequential Images to Sensor Integration
Kiuchi, K., Yokota, T., Saito, T., & KURODA, Y. (2015) · Transactions of the Society of Instrument and Control Engineers · doi:10.9746/sicetr.51.57 · Cited by 1
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.