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
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
“[173], gathering different visual appearances into a unified representation [49], or using spatial as well as appearance informa-”
Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
Badue, C., Guidolini, R., Carneiro, R. V., Azevedo, P., Cardoso, V. B., Forechi, A., Jesus, L., Berriel, R., Paixão, T. M., Mutz, F., et al. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113816 · Cited by 1,209
Visual Place Recognition: A Survey
Lowry, S., Sünderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., & Milford, M. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2496823 · Cited by 1,079
“SeqSLAM [118] used image sequences to perform place recognition through particularly visually challenging environments.”
BackgroundMethodInfluentialSelf-citationFrom Coarse to Fine: Robust Hierarchical Localization at Large Scale
Sarlin, P.-E., Cadena, C., Siegwart, R., & Dymczyk, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01300 · Cited by 1,044
“These include autonomous driving in GPS-denied environments [7, 29, 31, 5] and consumer devices with augmented reality features [30, 22], where a centimeter-accurate 6-DoF pose is crucial to guarantee reliable and safe operation and fully immersive experiences, respectively.”
BackgroundScan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map
Kim, G., & Kim, A. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593953 · Cited by 904
“SeqSLAM [17] proposed the route-based approach and showed far improved performance than FAB-MAP.”
MethodSimultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving
Bresson, G., Alsayed, Z., Yu, L., & Glaser, S. (2017) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2017.2749181 · Cited by 885
“Results on a 22 and 8-km data sets demonstrate the ability of SeqSLAM to handle day/night matching in real time (even though the computing time scales linearly with the size of the data set) with different weather conditions under which FAB-MAP is unable to properly operate.”
InfluentialBenchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., et al. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00897 · Cited by 699
“We also evaluate the de-facto standard approach for loop-closure detection in robotics [23, 36], where robustness to changing conditions is critical for long-term autonomous navigation [17, 37, 46, 49, 66, 69]: FAB-MAP [20] is an image retrieval approach based on the Bag-ofWords (BoW) paradigm [62] that explicitly mod…”
BackgroundMethodResultInfluentialPointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
Uy, M. A., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00470 · Cited by 670
Perception and sensing for autonomous vehicles under adverse weather conditions: A survey
Zhang, Y., Carballo, A., Yang, H., & Takeda, K. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.12.021 · Cited by 592
University of Michigan North Campus long-term vision and lidar dataset
Carlevaris-Bianco, N., Ushani, A. K., & Eustice, R. M. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915614638 · Cited by 576
PL-SLAM: A Stereo SLAM System Through the Combination of Points and Line Segments
Gomez-Ojeda, R., Moreno, F.-A., Zuniga-Noel, D., Scaramuzza, D., & Gonzalez-Jimenez, J. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2899783 · Cited by 560
On the performance of ConvNet features for place recognition
Sunderhauf, N., Shirazi, S., Dayoub, F., Upcroft, B., & Milford, M. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353986 · Cited by 544
“The recent literature proposes a variety of approaches to address the challenges of this field [1]–[14].”
BackgroundSelf-citationA review of multimodal image matching: Methods and applications
Jiang, X., Ma, J., Xiao, G., Shao, Z., & Guo, X. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.02.012 · Cited by 532
“[24] proposed a method called SeqSLAM, which is used to visualize navigation under changing conditions.”
MethodPatch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
Hausler, S., Garg, S., Xu, M., Milford, M., & Fischer, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01392 · Cited by 444
“Place matches obtained through global descriptor matching are often re-ranked using sequential information [26, 85, 49], query expansion [31, 13], geometric verification [41, 27, 52] and feature fusion [83, 86].”
BackgroundSelf-citationA survey of state-of-the-art on visual SLAM
Abaspur Kazerouni, I., Fitzgerald, L., Dooly, G., & Toal, D. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117734 · Cited by 383
Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free
Suenderhauf, N., Shirazi, S., Jacobson, A., Dayoub, F., Pepperell, E., Upcroft, B., & Milford, M. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.022 · Cited by 379
Self-citationReliable Patch Trackers: Robust visual tracking by exploiting reliable patches
Li, Y., Zhu, J., & Hoi, S. C. H. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298632 · Cited by 356
“In model-free tracking, Grabner et al. [28] proposed a boosting classifier to match the keypoint between different frames.”
BackgroundDeep learning features at scale for visual place recognition
Chen, Z., Jacobson, A., Sunderhauf, N., Upcroft, B., Liu, L., Shen, C., Reid, I., & Milford, M. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989366 · Cited by 344
Self-citationStreet-view change detection with deconvolutional networks
Alcantarilla, P. F., Stent, S., Ros, G., Arroyo, R., & Gherardi, R. (2018) · Autonomous Robots · doi:10.1007/s10514-018-9734-5 · Cited by 320
Kim, G., Choi, S., & Kim, A. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3116424 · Cited by 319
Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
Wang, H., Wang, C., & Xie, L. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9196764 · Cited by 308
“1) Temporal consistency check: In a SLAM system, it is observed that the occurrence of single loop closure often implies high similarity on the neighbour LiDAR scans since the sensor feedback is continuous in time [25].”
BackgroundSemi-parametric Topological Memory for NavigationPreprint
Savinov, N., Dosovitskiy, A., & Koltun, V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00653 · Cited by 450
“We experiment with two variants of this method: with local contrast normalization (similar to Milford & Wyeth (2012)) and without.”
MethodInfluentialVisual place recognition: A survey from deep learning perspective
Zhang, X., Wang, L., & Su, Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107760 · Cited by 261
Are We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four Seasons
Suenderhauf, N., Neubert, P., & Protzel, P. (2013) · QUT ePrints (Queensland University of Technology) · Cited by 241
A survey on Visual-Based Localization: On the benefit of heterogeneous data
Piasco, N., Sidibé, D., Demonceaux, C., & Gouet-Brunet, V. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.09.013 · Cited by 236
“[199], car localization on road from [128], air-plane localization with aerial imagery from [212].”
BackgroundMethodMapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition
Warburg, F., Hauberg, S., Lopez-Antequera, M., Gargallo, P., Kuang, Y., & Civera, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00270 · Cited by 227
“Other hand-crafted approaches exploit geometric and/or temporal consistency [15, 17, 33] in image sequences.”
BackgroundExperience-based navigation for long-term localisation
Churchill, W., & Newman, P. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913499193 · Cited by 225
“An alternative would be to use the new SeqSLAM (Milford and Wyeth, 2012) system.”
MethodConvolutional Neural Network-based Place Recognition
Chen, Z., Lam, O., Jacobson, A., & Milford, M. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.1509 · Cited by 201
“SeqSLAM [Milford and Wyeth, 2012] directly uses pixel values to match image sequences and perform place recognition across extreme perceptual changes.”
MethodSelf-citationA Survey on Deep Visual Place Recognition
Masone, C., & Caputo, B. (2021) · IEEE Access · doi:10.1109/access.2021.3054937 · Cited by 192
Artificial Intelligence for Long-Term Robot Autonomy: A Survey
Kunze, L., Hawes, N., Duckett, T., Hanheide, M., & Krajnik, T. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2860628 · Cited by 191
Optimal Transport Aggregation for Visual Place Recognition
Izquierdo, S., & Civera, J. (2024) · 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/cvpr52733.2024.01672 · Cited by 330
“In both cases, geometric [18] and temporal [18, 38] consistency was sometimes enforced for enhanced performance.”
BackgroundLong-Term Visual Localization Revisited
Toft, C., Maddern, W., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., Pajdla, T., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3032010 · Cited by 190
“Sequence-based approaches for image retrieval are used for loop-closure detection in robotics [53], [57], [61].”
BackgroundMethodResultInfluentialFast LIDAR localization using multiresolution Gaussian mixture maps
Wolcott, R. W., & Eustice, R. M. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139582 · Cited by 188
Robust Visual Robot Localization Across Seasons Using Network Flows
Naseer, T., Spinello, L., Burgard, W., & Stachniss, C. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.9057 · Cited by 186
“The goal of the work of Milford and Wyeth (2012), which has a similar overall aim as our approach, is to match a sequence of query images to a sequence of database images.”
BackgroundMethodX-View: Graph-Based Semantic Multi-View Localization
Gawel, A., Don, C. D., Siegwart, R., Nieto, J., & Cadena, C. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2801879 · Cited by 183
AntBot: A six-legged walking robot able to home like desert ants in outdoor environments
Dupeyroux, J., Serres, J. R., & Viollet, S. (2019) · Science Robotics · doi:10.1126/scirobotics.aau0307 · Cited by 179
Tsintotas, K. A., Bampis, L., & Gasteratos, A. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3175656 · Cited by 175
“Each of the techniques mentioned above can be effi-ciently adopted in sequence-of-images-based methods ( e.g., SeqSLAM [111], HMM-SeqSLAM [250], ABLE-M [251], S-VWV [115], MCN [252]).”
BackgroundMethodInfluentialVision-based topological mapping and localization methods: A survey
Garcia-Fidalgo, E., & Ortiz, A. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.11.009 · Cited by 175
“[39] M. Milford, G. Wyeth, Mapping a Suburb With a Single Camera Using a Biologically Inspired SLAM Sys- tem, IEEE Transactions on Robotics 24 (5) (2008) 1038–1053. doi:10.1109/TRO.2008.2004520.900 [40] M. Milford, G. Wyeth, SeqSLAM: Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights, in: IEE…”
BackgroundMethodInfluentialReference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis
Zhang, Z., Sattler, T., & Scaramuzza, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01399-8 · Cited by 200
iBoW-LCD: An Appearance-Based Loop-Closure Detection Approach Using Incremental Bags of Binary Words
Garcia-Fidalgo, E., & Ortiz, A. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2849609 · Cited by 167
“The results reported are taken from the original papers, except the ones corresponding to Cummins [3] and Milford [24] which were obtained by ourselves in a previous work [20].”
BackgroundResultLightweight Unsupervised Deep Loop Closure
Merrill, N., & Huang, G. P. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.032 · Cited by 171
OpenFABMAP: An open source toolbox for appearance-based loop closure detection
Glover, A., Maddern, W., Warren, M., Reid, S., Milford, M., & Wyeth, G. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224843 · Cited by 162
Self-citationZaffar, M., Garg, S., Milford, M. J., Kooij, J. F. P., Flynn, D., McDonald-Maier, K. D., & Ehsan, S. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01469-5 · Cited by 212
“Operating on sequences of raw RGB-images, Seq-SLAM (Milford and Wyeth (2012)) uses normalized pixel-intensity matching in a global fashion to perform VPR in challenging conditionally-variant environments.”
MethodSelf-citationKhaliq, A., Ehsan, S., Chen, Z., Milford, M. J., & McDonald-Maier, K. D. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2956352 · Cited by 182
“Standard FABMAP implementation and three sequential frames configuration for SEQSLAM were used in [7].”
MethodInfluentialSelf-citationA Survey on Global LiDAR Localization: Challenges, Advances and Open Problems
Yin, H., Xu, X., Lu, S., Chen, X., Xiong, R., Shen, S., Stachniss, C., & Wang, Y. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02019-5 · Cited by 202
“From the systems above (He et al., 2020; Huang et al., 2021; Xie et al., 2021; Zhong et al., 2022; Xu et al., 2023), it can be concluded that inter-robot LCD methods enable cross-robot localization in large-scale environments.”
InfluentialOnly look once, mining distinctive landmarks from ConvNet for visual place recognition
Chen, Z., Maffra, F., Sa, I., & Chli, M. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202131 · Cited by 172
“However, it is worth noting that our approach only requires a single image instead of a sequence of images required in SeqSLAM.”
BackgroundMethodInfluentialA comparison of vector symbolic architectures
Schlegel, K., Neubert, P., & Protzel, P. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-10110-3 · Cited by 149
“This simple averaging is known to significantly improve the place recognition performance, in particular in case of changing environmental conditions [39].”
BackgroundMethodInfluentialWhere Is Your Place, Visual Place Recognition?
Garg, S., Fischer, T., & Milford, M. J. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/603 · Cited by 147
Self-citationDeep regression for monocular camera-based 6-DoF global localization in outdoor environments
Naseer, T., & Burgard, W. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205957 · Cited by 144
“Milford and Wyeth [15] proposed an approach for place recognition across large perceptual changes by performing linear sequential filtering on image matchings.”
BackgroundVision-based place recognition: how low can you go?
Milford, M. J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913490323 · Cited by 143
“If the environment changes, feature-based techniques may also fail since visual features can change radically over day– night, weather and seasonal cycles (Milford and Wyeth, 2012).”
BackgroundMethodSelf-citationRobust Visual Localization Across Seasons
Naseer, T., Burgard, W., & Stachniss, C. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2788045 · Cited by 142
“shown a great improvement over feature-based global image localization [34], [35].”
BackgroundMethodInfluentialGil, G., Casagrande, D. E., Cortés, L. P., & Verschae, R. (2022) · Smart Agricultural Technology · doi:10.1016/j.atech.2022.100069 · Cited by 160
Shady dealings: Robust, long-term visual localisation using illumination invariance
McManus, C., Churchill, W., Maddern, W., Stewart, A. D., & Newman, P. M. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6906961 · Cited by 140
“The SeqSLAM [11] algorithm is able to achieve successful”
MethodSemantic Graph Based Place Recognition for 3D Point Clouds
Kong, X., Yang, X., Zhai, G., Zhao, X., Zeng, X., Wang, M., Liu, Y., Li, W., & Wen, F. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341060 · Cited by 140
Zheng, H., Zhong, Z., Hu, R., Xiao, B., Wu, Y., Yu, F., Liu, X., Li, G., & Deng, L. (2024) · Nature Communications · doi:10.1038/s41467-023-44614-z · Cited by 184
“The former uses temporally captured images for placerecognition, suchas SeqSLAM 53 , FlyNet 54 and sequential place learning 55 , while the latter 56,57 uses neuromorphic sensors such as event cameras 7,8 as an extra data source for improving recognition accuracy.”
LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics
Garg, S., Sünderhauf, N., & Milford, M. J. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.022 · Cited by 137
Self-citationAll-environment visual place recognition with SMART
Pepperell, E., Corke, P., & Milford, M. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907067 · Cited by 131
“As with SeqSLAM, comparisons are made with the resolution reduced, patch-normalised frames – a process performed by dividing the image into patches, then taking each pixel and subtracting its patch mean and dividing by its patch standard deviation [9].”
BackgroundMethodInfluentialSelf-citationSemantics-aware visual localization under challenging perceptual conditions
Naseer, T., Oliveira, G. L., Brox, T., & Burgard, W. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989305 · Cited by 144
“1, they do not show much robustness [18], [21].”
BackgroundVision-Based Offline-Online Perception Paradigm for Autonomous Driving
Ros, G., Ramos, S., Granados, M., Bakhtiary, A., Vázquez, D., & López, A. M. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.38 · Cited by 138
“This topic is gaining recognition in the literature [10, 19, 21, 23], but still is a young problem.”
BackgroundSemantics for Robotic Mapping, Perception and Interaction: A Survey
Garg, S., Sünderhauf, N., Dayoub, F., Morrison, D., Cosgun, A., Carneiro, G., Wu, Q., Chin, T.-J., Reid, I. D., Gould, S. J., et al. (2020) · Foundations and Trends in Robotics · doi:10.1561/2300000059 · Cited by 167
Self-citationVisual SLAM Integration With Semantic Segmentation and Deep Learning: A Review
Pu, H., Luo, J., Wang, G., Huang, T., Liu, H., & Luo, J. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3306371 · Cited by 132
“Milford and Wyeth [72] and Cummins’s [73] framework achieved a recall of 85.7% when tested on the Eynsham dataset (total distance of 70 km and 9575 keyframes) and outperformed SeqSLAM (51”
MethodInfluentialA New Wave in Robotics: Survey on Recent MmWave Radar Applications in Robotics
Harlow, K., Jang, H., Barfoot, T. D., Kim, A., & Heckman, C. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3463504 · Cited by 158
“These rotation invariant matrices were then processed into difference matrices to perform backward loop closure detection in SeqSLAM [86] for relocalization with mirrored search to account for visiting trajectories from opposite directions.”
BackgroundNeuroSLAM: a brain-inspired SLAM system for 3D environments
Yu, F., Shang, J., Hu, Y., & Milford, M. J. (2019) · Biological Cybernetics · doi:10.1007/s00422-019-00806-9 · Cited by 118
“In addition, some approaches have focused on the loop closure component of the SLAM problem, such as FrameSLAM (Konolige and Agrawal 2008), FAB-MAP (Cummins and Newman 2008; Paul and Newman 2010), SeqSLAM (Milford and Wyeth 2012) and CAT-SLAM (Maddern et al. 2012).”
MethodSelf-citationSeqNet: Learning Descriptors for Sequence-Based Hierarchical Place Recognition
Garg, S., & Milford, M. J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3067633 · Cited by 118
“A list of top candidates Ri based on K lowest distance values is then considered for re-ranking using a simplified version of SeqSLAM [2], operating directly on descriptor distances without its velocity searching.”
BackgroundMethodInfluentialSelf-citationLearning Context Flexible Attention Model for Long-Term Visual Place Recognition
Chen, Z., Liu, L., Sa, I., Ge, Z., & Chli, M. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2859916 · Cited by 117
“[14] M. Milford and G. Wyeth, "SeqSLAM: Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights," in IEEE International Conference on Robotics and Automation, St Paul, United States, 2012.”
BackgroundMethodInfluentialScene Signatures: Localised and Point-less Features for Localisation
McManus, C., Upcroft, B., & Newmann, P. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.023 · Cited by 117
“Low-level point features can be thought of as being on one extreme of a localisation paradigm, while using wholeimage information, such as SeqSLAM [3], can be thought of as being on the opposite end of that spectrum.”
BackgroundMethodInfluentialBridging the Day and Night Domain Gap for Semantic Segmentation
Romera, E., Bergasa, L. M., Yang, K., Álvarez, J. M., & Barea, R. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8813888 · Cited by 115
“Alderley and Milford ones were discarded due to their poor conversion results in the Cityscapes domain.”
MethodInfluentialHybrid Indoor Localization Using IMU Sensors and Smartphone Camera
Poulose, A., & Han, D. S. (2019) · Sensors · doi:10.3390/s19235084 · Cited by 121
“The SLAM technique is classified as extended Kalman filter (EKF) SLAM [65,66], FastSLAM [67], low dimensionality (L)-SLAM [68], GraphSLAM [69], Occupancy Grid SLAM [70–72], distributed particle (DP)-SLAM [73], parallel tracking and mapping (PTAM) [74], stereo parallel tracking and mapping (S-PTAM) [75], dense tracking a…”
MethodAn Introduction to Hyperdimensional Computing for Robotics
Neubert, P., Schubert, S., & Protzel, P. (2019) · Künstliche Intell. · doi:10.1007/s13218-019-00623-z · Cited by 113
“To account for a slightly varying speed between the sequences, the original SeqSLAM algorithm evaluates line segments with different slopes and uses the best choice.”
MethodInfluentialReal-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding
Glocker, B., Shotton, J., Criminisi, A., & Izadi, S. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2360403 · Cited by 124
ForkGAN: Seeing into the Rainy Night
Zheng, Z., Wu, Y., Han, X., & Shi, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_10 · Cited by 111
“Evaluation metric results of different methods for night → day translation task on Alderley dataset [19].”
BackgroundMethodLaMAR: Benchmarking Localization and Mapping for Augmented Reality
Sarlin, P.-E., Dusmanu, M., Schönberger, J. L., Speciale, P., Gruber, L., Larsson, V., Mikšík, O., & Pollefeys, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20071-7_40 · Cited by 166
Appearance change prediction for long-term navigation across seasons
Neubert, P., Sünderhauf, N., & Protzel, P. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698842 · Cited by 108
“Precision recall plots obtained by combining SeqSLAM [14] with the proposed SC-ACP (dashed lines) compared with SeqSLAM alone (solid lines).”
BackgroundMethodInfluentialSummary Maps for Lifelong Visual Localization
Mühlfellner, P., Bürki, M., Bosse, M. C., Derendarz, W., Philippsen, R., & Furgale, P. (2015) · Journal of Field Robotics · doi:10.1002/rob.21595 · Cited by 107
“This goal is distinct from long-term, condition-invariant place recognition [see, e.g. Milford & Wyeth (2012)], which does not provide pose estimates.”
Background4D crop monitoring: Spatio-temporal reconstruction for agriculture
Dong, J., Burnham, J. G., Boots, B., Rains, G. C., & Dellaert, F. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989447 · Cited by 107
Localizing Ground Penetrating RADAR: A Step Toward Robust Autonomous Ground Vehicle Localization
Cornick, M., Koechling, J. C., Stanley, B., & Zhang, B. (2015) · Journal of Field Robotics · doi:10.1002/rob.21605 · Cited by 105
“Nuske et. al (Nuske, Roberts, & Wyeth, 2009) used a multi-hypothesis particle filter to select among matches to 3D edges in the environment.”
BackgroundSemantic–geometric visual place recognition: a new perspective for reconciling opposing views
Garg, S., Sünderhauf, N., & Milford, M. J. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919839761 · Cited by 116
“The Sum of Absolute Difference of Patch-normalized images (PN-SAD), which are hand-crafted image representations, has been demonstrated to be useful for appearance-invariant place recognition using SeqSLAM (Milford and Wyeth 2012).”
BackgroundMethodInfluentialSelf-citationSobbahi, R. A., & Tekli, J. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116848 · Cited by 104
LocNet: Global Localization in 3D Point Clouds for Mobile Vehicles
Yin, H., Tang, L., Ding, X., Wang, Y., & Xiong, R. (2018) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2018.8500682 · Cited by 119
“Based on this scheme, sequences of images were considered for matching instead of single frame to improve the precision [7].”
MethodAitken, J. M., Evans, M. H., Worley, R., Edwards, S., Zhang, R., Dodd, T. J., Mihaylova, L. S., & Anderson, S. (2021) · IEEE Access · doi:10.1109/access.2021.3115981 · Cited by 114
“Therefore, SeqSLAM was developed [41], which uses a sequence of images to perform appearance recognition and tends to be a more robust approach.”
MethodTowards life-long visual localization using an efficient matching of binary sequences from images
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., & Romera, E. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7140088 · Cited by 102
“For these reasons, in the present paper we follow some of these concepts about binary description and matching, but now improved for applying them in a life-long localization context.”
BackgroundMethod3D LiDAR-Based Global Localization Using Siamese Neural Network
Yin, H., Wang, Y., Ding, X., Tang, L., Huang, S., & Xiong, R. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2905046 · Cited by 113
“Based on this scheme, sequences of image frames were considered for matching instead of single frame to improve the precision [15].”
MethodRobust visual SLAM across seasons
Naseer, T., Ruhnke, M., Stachniss, C., Spinello, L., & Burgard, W. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353721 · Cited by 101
“There has been a tremendous progress in the area of visual Simultaneous Localization and Mapping (SLAM) over the last couple of years, especially in the context of appearancebased place recognition, which is an essential building block to successfully find loop closures in the context of SLAM [6], [17], [18].”
BackgroundFusion and binarization of CNN features for robust topological localization across seasons
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., & Romera, E. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759685 · Cited by 100
“single images in CNN-VTL, similarly to [17] and [20].”
BackgroundMethodInfluentialFoundations of spatial perception for robotics: Hierarchical representations and real-time systems
Hughes, N., Chang, Y., Hu, S., Talak, R., Abdulhai, R., Strader, J., & Carlone, L. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241229725 · Cited by 143
“Alternative approaches investigate place recognition using image sequences (Garg and Milford 2021; Milford and Wyeth 2012; Schubert et al., 2021) or deep learning (Arandjelovic et al., 2016).”
CricaVPR: Cross-Image Correlation-Aware Representation Learning for Visual Place Recognition
Lu, F. H., Lan, X., Zhang, L., Jiang, D., Wang, Y., & Yuan, C. (2024) · 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/cvpr52733.2024.01587 · Cited by 159
“The former performs image sequence matching (i.e. utilize temporal continuity) [17, 20, 24, 41, 47] to realize robust VPR in challenging environments.”
BackgroundLocus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling
Vidanapathirana, K., Moghadam, P., Harwood, B., Zhao, M., Sridharan, S., & Fookes, C. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560915 · Cited by 96
“In visual place recognition (VPR), SeqSLAM [21] incorporated sequential information by comparing feature similarity over time and demonstrated dramatic performance improvement when dealing with changing appearance.”
MethodZaffar, M., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2969917 · Cited by 116
“Seq-SLAM [34] does not perform feature extraction but uses normalized pixel-intensity matching (in global fashion) between a sequence of camera frames to achieve VPR in highly challenging environments.”
Self-citationFast-SeqSLAM: A fast appearance based place recognition algorithm
Siam, S. M., & Zhang, H. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989671 · Cited by 93
“Milford and Wyeth [4] proposed a sequence based place recognition algorithm, known as SeqSLAM, which finds a sequence of images in the robot map, rather than a single image, that are the best match for the current image sequence being captured by a moving robot.”
BackgroundMethodInfluentialHierarchical Place Recognition for Topological Mapping
Garcia‐Fidalgo, E., & Ortiz, A. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2704598 · Cited by 91
“0 [6] and SeqSLAM [29], which can be considered as state-of-the-art approaches of each paradigm, respectively.”
BackgroundMethodBrain-inspired multimodal hybrid neural network for robot place recognition
Yu, F., Wu, Y., Ma, S., Xu, M., Li, H., Qu, H., Song, C., Wang, T., Zhao, R. J., & Shi, L. (2023) · Science Robotics · doi:10.1126/scirobotics.abm6996 · Cited by 90
Robust Long-Term Registration of UAV Images of Crop Fields for Precision Agriculture
Chebrolu, N., Labe, T., & Stachniss, C. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2849603 · Cited by 89
“Visual localization and place recognition for longterm applications require robust image matching in presence of strong illumination and seasonal changes [14], [18].”
BackgroundRobotic Room-Level Localization Using Multiple Sets of Sonar Measurements
Liu, H., Sun, F., Fang, B., & Zhang, X. (2016) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2016.2618978 · Cited by 88
“Milford et al. [28] proposed to calculate the best candidate matching location within every local navigation sequence, instead of calculating the single location most likely given a current image.”
BackgroundHybrid CNN-Transformer Features for Visual Place Recognition
Wang, Y., Qiu, Y., Cheng, P., & Zhang, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3212434 · Cited by 88
“Therefore, the above mentioned techniques are known as supervised learning-based VPR. Gomez-Ojeda et al. [62] built triplets based on KITTI Dataset [63], Alderley Dataset [64] and Nordland Dataset [65] to fine-tune CaffeNet [66] for VPR.”
MethodMulti-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods
Hausler, S., Jacobson, A., & Milford, M. J. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2898427 · Cited by 87
“The quality score, inspired by SeqSLAM [4], is a ratio between the maximum score in a column of the emission matrix”
BackgroundMethodInfluentialSelf-citationFeature Co-occurrence Maps: Appearance-based localisation throughout the day
Johns, E., & Yang, G. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631024 · Cited by 84
“In this paper, we present three key novelties and demonstrate their contribution towards the overall system, together with comparisons against two state-of-the art methods: FABMAP [10] and SeqSLAM [4].”
MethodSuperpixel-based appearance change prediction for long-term navigation across seasons
Neubert, P., Sünderhauf, N., & Protzel, P. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.08.005 · Cited by 83
“By applying this approach, we are able to significantly improve the place recognition performance of SeqSLAM [17] and BRIEF-Gist [21] on the new, publicly available large-scale Nordland dataset [20] that traverses an environment in winter and summer under extremely different environmental conditions.”
BackgroundMethodResultInfluentialFast loop-closure detection using visual-word-vectors from image sequences
Bampis, L., Amanatiadis, A. A., & Gasteratos, A. C. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917740639 · Cited by 82
“To evaluate the performance of SeqSLAM algorithm (Milford and Wyeth, 2012), one of the most representative sequencebased LCD techniques that groups camera measurements based on their matching similarities, we made use of the OpenSeqSLAM2 implementation.”
MethodResultInfluentialGOSMatch: Graph-of-Semantics Matching for Detecting Loop Closures in 3D LiDAR data
Zhu, Y., Ma, Y., Chen, L. F., Liu, C., Ye, M., & Li, L. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341299 · Cited by 82
“Though many vision-based methods have been proposed in recent years [2]–[4], it may draw unreliable results in the cases of dramatic changes on illumination [5] or viewpoint [6].”
Background
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.