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 801–900 of 987
Filho, H. P., & Ohya, A. (2016) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2016.p0234 · Cited by 1
Deep learning based autonomous direction estimation
Yalçın, H., & Cılasun, H. (2016) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2016.7496072 · Cited by 1
“Yine SLAM sistemlerinin farklı koşullardaki performansını artırmaya yönelik çalışmalar da literatürde mevcuttur [7].”
Long-term place recognition using multi-level words of spatial densities
Maffei, R. D. Q., Jorge, V. A. M., Rey, V. F., Kolberg, M., & Prestes, E. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759504 · Cited by 2
“During the last years, various approaches for place recognition in dynamic scenarios have been presented in the literature, mostly based on computer vision and using a wide range of different strategies to find matches, such as template matching, feature extraction, Bag of Words, etc [11], [12], [13].”
BackgroundOutdoor Robot Navigation Based on View-Based Global Localization and Local Navigation
Inoue, Y., Miura, J., & Oishi, S. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-48036-7_63 · Cited by 1
“Milford and Wyeth [9] proposed the SeqS-LAM method which realizes a very robust image sequence matching even under an extreme view changes.”
MethodQiao, Y., Cappelle, C., Yang, T., & Ruichek, Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70353-4_24 · Cited by 1
“Sequence SLAM (SeqSLAM) [10], adopting sequences matching rather than single image matching for place recognition, achieves significant performance improvements with respect to FAB-MAP.”
MethodVisual navigation with efficient ConvNet features
Jaspers, H., Faßbender, D., & Wuensche, H. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206428 · Cited by 1
“SeqSLAM [8] instead uses low-resolution, contrast enhanced images for image matching.”
MethodResultMaldonado-Ramírez, A., & Torres-Méndez, L. A. (2017) · OCEANS 2017 – Anchorage · Cited by 1
Hierarchical Loop Closure Detection for Topological Mapping
Garcia‐Fidalgo, E., & Ortiz, A. (2018) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-75993-7_7 · Cited by 1
Robust Traffic Scene Recognition with a Limited Descriptor Length
Sikirić, I., Brkić, K., Krapac, J., & Šegvić, S. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · Cited by 2
Toward semantic loop closure in simultaneous localization and mapping systems
Zhang, Y.-C., Huang, C., Yang, C.-Y., & Chen, Y.-H. (2018) · Current Developments in Lens Design and Optical Engineering · doi:10.1117/12.2320035 · Cited by 1
“We use the same score equation as Equation (8) and the sentence is shown below: The effect of time and spatial sequence comparison is shown in Fig.”
MethodInfluentialMonocular Vision based Topological Map Generation in Real-time
Bhowmick, S., Deb, A. K., & Mukhopadhyay, J. (2018) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2018.8628883 · Cited by 1
“global descriptors, is SeqSLAM [18].”
MiNERVA: Toposemantic Navigation Model based on Visual Information for Indoor Enviroments
Hernandez, A. C., Gómez, C., & Barber, R. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.08.046 · Cited by 1
Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage Cost
Le, H., Xu, M., Hoang, T., & Milford, M. J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00992 · Cited by 2
“Disclaimer Our system is not a replacement for visual SLAM and localization systems like [28, 29], since we abstract away the choice of feature descriptors and focus on optimally clusters “similar” observations (e.g., class labels) under this new distance.”
BackgroundSelf-citationA Feature-Based Underwater Path Planning Approach using Multiple Perspective Prior Maps
Cagara, D., Dunbabin, M. D., & Rigby, P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196680 · Cited by 1
“In particular, SeqSLAM [14] shows how visual localisation can be realised under changing environmental conditions.”
BackgroundThe loop closure Detection Algorithm Based on Bag of Semantic Word For Robot Navigation
Yu, P., Ruan, X., & Zhu, X. (2020) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba50161.2020.9277317 · Cited by 1
“Milfold [11] and Naseer [12] proposed that the global descriptor method is more robust in the case of illumination changes.”
MethodFault-Diagnosing Monocular-SLAM for Scale-Aware Change Detection
Sugimoto, T., Yamaguchi, K., Zhongshan, B., Minying, Y., Tomoe, H., & Kanji, T. (2021) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/ieeeconf49454.2021.9382715 · Cited by 1
Cooperative place recognition in robotic swarms
Brent, S., Yuan, C., & Stegagno, P. (2021) · ACM Symposium on Applied Computing · doi:10.1145/3412841.3441954 · Cited by 1
CUDA-based SeqSLAM for Real-Time Place Recognition
Ouerghi, S., Boutteau, R., Tlili, F., & Savatier, X. (2017) · HAL · Cited by 1
Global Localization for Single 3D Point Cloud using Voting Mechanism
Jin, Y., Chen, Q., Qian, J., Liu, J., & Zhang, J. (2021) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm52023.2021.9536101 · Cited by 1
Training-free probability models for whole-image based place recognition
Lowry, S. M., Wyeth, G. F., & Milford, M. J. (2013) · QUT ePrints (Queensland University of Technology) · Cited by 1
Self-citationZhang, K., Jiang, X., Mei, X., Zhou, H., & Ma, J. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636769 · Cited by 1
“Five algorithms including SeqS-LAM [29], Bampis et al. [4], iBoW-LCD [13], PREVIeW [5] and Tsintotas et al. [36] are adopted for comparison.”
MethodTowards predictive and decentralized bio-inspired navigation models for distributed systems
Gay, S. L., Truong, N.-T., Pissaloux, E. E., & Jamont, J.-P. (2021) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9659910 · Cited by 1
Evaluating and Optimizing Feature Combinations for Visual Loop Closure Detection
Wang, X., Zhang, H., & Peng, G. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01575-7 · Cited by 1
“The SeqSLAM [14] algorithm retrieves locations by matching local image sequences instead of individual images.”
MethodA new laser-based loop detection method for laneway environment 3D mapping
Huang, Z., & Lu, J. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9728410 · Cited by 1
Sequence matching enhanced 3D place recognition using candidate rearrangement
Li, C., Yan, F., & Zhuang, Y. (2022) · IET Cyber-Systems and Robotics · doi:10.1049/csy2.12054 · Cited by 1
SE-VPR: Semantic Enhanced VPR Approach for Visual Localization
Pei, H., Wang, J., & Chen, Z. (2022) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml55074.2022.00131 · Cited by 1
“[41,42,43], sequential information [44, 45, 46], ensembling [47,48] and etc.”
BackgroundTsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-09396-8_2 · Cited by 1
An Efficient Online Loop Closure Detection System With Local Spatial Co-Occurrence Information
Zhang, L., Yan, W., & Li, H. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3222696 · Cited by 1
“Some extra information (like spatial messages [8], [9], [10], [11])-aided representations also show distinctiveness to eliminate false positives.”
BackgroundReinforcement learning for rule extraction from labeled dataset
Rose, S. R., Tamizharasi, A., Abishekkannao, J. S., Chowdary, A. S. S., & Reddy, B. V. K. (2022) · AIP conference proceedings · doi:10.1063/5.0110939 · Cited by 1
Hierarchical Strategy for Sequence-based Visual Place Recognition
Chen, B., Song, X., & Zhu, R. (2022) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis57298.2022.10016434 · Cited by 1
Pandey, S. K., Mosin, V., Durisic, D., Koppisetty, A. C., & Staron, M. (2023) · Journal of Software Engineering for Autonomous Systems · doi:10.55060/j.jseas.231018.001 · Cited by 3
Han, S., Gao, W., & Hu, Z. (2023) · Sensors · doi:10.3390/s23239580 · Cited by 1
Learn to Triangulate Scene Coordinates for Visual Localization
Guo, X., Chen, T., Li, B., Liu, Q., Jia, H., & Dai, Y. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3362637 · Cited by 2
Li, J., Shen, Y., Xin, J., & Zheng, N. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10422004 · Cited by 1
“On the other hand, [11], [12] match two sequences based on similarity score calculated frame-by-frame.”
BackgroundVisual place recognition with fusion event cameras
Liu, Y., Yu, L., Yu, H., & Yang, W. T. (2024) · Journal of Image and Graphics · doi:10.11834/jig.230003 · Cited by 1
A Semantic Spatial Structure-Based Loop Detection Algorithm for Visual Environmental Sensing
Cheng, X., Zhang, Y., Kang, M., Wang, J., Jiao, J., Dong, L., & Jiao, L. (2024) · Remote Sensing · doi:10.3390/rs16101720 · Cited by 1
Peng, Z., Song, R., Yang, H., Li, Y., Lin, J., Xiao, Z., & Yan, B. (2024) · Applied Sciences · doi:10.3390/app14146276 · Cited by 1
“Therefore, the learning-based frameworks are intuitively applied to solve LCD problems [5].”
BackgroundMethodResultInfluentialEfficient Visual Navigation with Bio-inspired Route Learning Algorithms
Kagioulis, E., Knight, J. C., Philippides, A. O., Ghosh, A., Amin, A. A., Graham, P., & Nowotny, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71533-4_1 · Cited by 1
Concepts of Robotics, AI, and Internet of Things (IoT) in Agriculture
Bandil, D. K., & Rahi, P. (2024) · Wiley eBooks · doi:10.1002/9781394302994.ch6 · Cited by 1
Beyond Handcrafted Features: A Deep Learning Framework for Optical Flow and SLAM
Kazi, K., Khizer, A. N., Memon, F., Memon, A. R., & Iqbal, M. (2025) · Journal of Imaging · doi:10.3390/jimaging11050155 · Cited by 1
“For instance, viewpoint changes can significantly alter handcrafted features, leading to inaccurate map creation [28].”
Robust Loop Closure Detection Using Bayes Filters and CNN Features
Liu, Q., & Duan, F. (2019) · International Journal of Humanoid Robotics · doi:10.1142/s0219843619500117 · Cited by 1
Active Cross-domain Self-localization Using Pole-like Landmarks
Kanji, T. (2021) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma52036.2021.9512691 · Cited by 1
“Many studies have focused on designing or training a detector for domain-invariant visual features, such as view-sequences [15] and bag-of-words [12], along with using the intermediate signals of deep neural networks DCN [2], GAN [1], and autoencoder [3].”
BackgroundSelf-localization Using Visual Experience Across DomainsPreprint
Taisho, T., & Tanaka, K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.07618 · Cited by 1
“calization algorithm to be extremely fast (to work in a fast robot navigation) and to recognize the place from a single frame [1] (i.e., without temporal tracking [7] and visual sequence measurements [8]). One of most popular approaches to address the problem of single-view localization is bag-of-words methods [1], [5…”
BackgroundPerformance Improvements for Lidar-based Visual Odometry
Dong, H. (2013) · TSpace (University of Toronto) · Cited by 2
Long-Distance Loop Closure Using General Object Landmarks.Preprint
Holliday, A. G. C., & Dudek, G. (2017) · arXiv (Cornell University) · Cited by 1
Excavate Condition-invariant Space by Intrinsic EncoderPreprint
Xu, J. B., Wang, C., Shi, C., & Xiao, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.11306 · Cited by 1
“For comparison, SeqSLAM [35] is employed as a baseline for long-term place recognition because our intrinsic encoder is the first method that can solve multiple different environmental changes simultaneously in place recognition as far as we know.”
MethodInfluentialTowards A Deep Insight into Landmark-based Visual Place Recognition: Methodology and PracticePreprint
Yang, B., Li, J., Xu, X., & Zhang, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.07572 · Cited by 1
“Visual place recognition, which is widely used in the localization and navigation systems [1-7], aims to identify whether the current view corresponds to the place or location that has been already visited [8].”
BackgroundImage-based Navigation using Visual Features and Map.Preprint
Thoma, J., Paudel, D. P., Chhatkuli, A., Probst, T., & Gool, L. V. (2018) · arXiv (Cornell University) · Cited by 1
SIVO: Semantically Informed Visual Odometry and Mapping
Ganti, P. (2018) · UWSpace (University of Waterloo) · Cited by 2
Mining Minimal Map-Segments for Visual Place ClassifiersPreprint
Kanji, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09594 · Cited by 1
“The developed VPC systems were evaluated in challenging cross-season VPR scenarios [17], using the publicly available NCLT dataset [18].”
MethodImproving Place Recognition Using Dynamic Object DetectionPreprint
Munoz, J. P., & Dexter, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04698 · Cited by 3
“More recently, sophisticated approaches are capable of localizing an agent with great accuracy based on a single image that is associated with a pose of the agent, e.g., [6] [7] [8] [9] [10][11][12][13][14].”
BackgroundMethodRobust and light-weight simultaneous localization and mapping for autonomous vehicles
Wang, H. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/151717 · Cited by 1
Yoshida, M., Yamamoto, R., & Kanji, T. (2021) · arXiv (Cornell University) · Cited by 1
The role of motion-and-visual perception in robot place learning and navigation
LEON, M. A. C. (2022) · Queensland University of Technology · doi:10.5204/thesis.eprints.229769 · Cited by 2
CityLearn: Diverse Real-World Environments for Sample-Efficient Navigation Policy LearningPreprint
Chancán, M. (2020) · doi:10.36227/techrxiv.12063582.v1 · Cited by 1
Bridging the divide between Visual Place Recognition and SLAM
Xu, M. (2023) · Queensland University of Technology · doi:10.5204/thesis.eprints.240786 · Cited by 1
Spiking Neural Networks for Scalable Visual Place Recognition
Hussaini, S. (2024) · Queensland University of Technology · doi:10.5204/thesis.eprints.253913 · Cited by 1
The Data Market: Policies for Decentralised Visual LocalisationPreprint
Gadd, M., & Newman, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05607 · Cited by 1
“To date, roboticists have effectively dispatched lifelong navigation systems [3, 4] to deal with stark scene change.”
BackgroundHybrid mapping for large urban environments
Üzer, F. (2016) · theses.fr (ABES) · doi:10.70675/8f51d6f5z6aecz435ez93fcz9b89660ff07b · Cited by 1
Visual SLAM with automatic map update in dynamic environments
Bouaziz, Y. (2021) · theses.fr (ABES) · doi:10.70675/0a8cc3afz3814z4402z9d42z4e18bea20a59 · Cited by 1
Integrated neuro-robotic approaches for autonomous vehicle localisation and navigation.
Colomer, S. (2022) · theses.fr (ABES) · doi:10.70675/13af83bcze330z4614z8d11zfd0c4a5bf80d · Cited by 1
Odometry-driven inference to link multiple exemplars of a location
Lowry, S. M., Wyeth, G. F., & Milford, M. J. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696403 · Cited by 1
“Sequences of images have been used to match locations despite drastic changes in lighting and weather [8].”
MethodSelf-citationMobile robot localization system in frequent GPS-denied situations
Saito, T., Kiuchi, K., & KURODA, Y. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907431
“In this study, we employ SeqSLAM[7][8] as a sequential appearance-based PR.”
MethodCAT-GRAPH+: Towards Odometry-driven Place Consolidation in Changing Environments
Lowry, S. M., Wyeth, G. F., & Milford, M. J. (2012) · QUT ePrints (Queensland University of Technology)
Self-citationCo-designing software abstraction and optimisation for productivity and performance
Barrett, C. (2015) · Research Explorer (The University of Manchester)
An online implementation of robust RGB-D SLAM
Athari, M., & Taghirad, H. D. (2014) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom.2014.6990920
“As existence of many false positive loop can affect the accuracy of robust back-end, we have proposed a method based on the idea of [10] to reduce the impact of threshold on accuracy.”
MethodGeometric indexing for recognition of places based on expanded delaunay triangulation
Lara-Álvarez, C. A., & Rojas‐Domínguez, A. (2016) · Intelligent Data Analysis · doi:10.3233/ida-160848
“For example, Milford and Wyeth compare short sequences of images to recognize coherent sequences, showing good results even when the perceptual change in the datasets is extreme [22].”
Introduction of a human based attention model for robotic navigation
Williams, H. A., Naqvi, S. S., Browne, W. N., & Hollitt, C. (2015) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2015.7761508
“Milford et al. introduced a new approach SeqSLAM [1], that relies upon matching a sequence of images over conventional approaches which make single place to place matches.”
BackgroundMethodInfluentialBiologically-inspired place recognition with neural networks
Chen, Z. (2016) · Queensland University of Technology · doi:10.5204/thesis.eprints.98550
Multisensory Omni-directional Long-term Place Recognition: Benchmark Dataset and AnalysisPreprint
Mathur, A., Han, F., & Zhang, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.05215
“Few methods [15, 16] have shown that matching a query image with many possible sequences and then finding a global match yields robust solutions to the perceptual aliasing and long term appearance change problem.”
MethodSaito, T., & KURODA, Y. (2013) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2013._1a2-h02_1
NAKAGAWA, S., Masatoshi, A. N. D. O., Yuuto, C., Inagaki, Y., Shogo, H., & Kanji, T. (2014) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2014._1p1-w06_1
Multi-descriptor retrieval in digitalized photographs collections
Bhowmik, N. (2017) · theses.fr (ABES) · doi:10.70675/1a62ff5dz0e8fz4d53zb0cczc01b30ac200d
Yang, S., Jiang, R., Wang, H., & Ge, S. S. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-67792-7_34
Decision Assist for Self-driving Cars
Subramanian, S. G., Sambee, J. S., Ghojogh, B., & Crowley, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-89656-4_44 · Cited by 1
“A complete system for a fully autonomous vehicle capable of mapping and localization and low-level navigation planning was proposed in [7].”
BackgroundPlace detection through analysis of descriptor sequences of 3D point clouds
Mihankhah, E. (2018) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/73719
A Forward-Viewing Mono-Camera Based SLAM System for Indoor Service Robots
이태재 (2017) · Seoul National University Open Repository (Seoul National University)
Partitioned environments for visual localization
Abdulhafez, A. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404239
Probabilistic Voting for Sequence Based Visual Place Recognition
Xin, Z., Cai, Y., Zhang, J., Yang, Y., & Wang, Y. Q. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545338
“In SeqSLAM, the difference matrix is generated based on raw image data.”
BackgroundMethodInfluentialAn incremental loop closure detection method based on depth information for indoor dynamic scenes
Deng, Z., Wu, Q., Jiao, J., Sun, Y., Mo, Y., & Zhang, C. (2018) · Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC) · doi:10.2991/jimec-18.2018.59
“The whole image descriptors used in the SeqSLAM SLAM system demonstrate robustness against the environmental change[12].”
MethodScalable Change Retrieval Using Deep 3D Neural CodesPreprint
Yusuke, K., Kanji, T., Naiming, Y., & Yuji, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03552
“However, SLAM in non-stationary environments remains a significant challenge [2]–[5].”
BackgroundCondition-invariant Place Recognition Using Deep Convolutional Auto-encoder
Oh, J., & Lee, B.-H. (2019) · The Journal of Korea Robotics Society · doi:10.7746/jkros.2019.14.1.008
Increasing the Efficiency of 6-DoF Visual Localization Using Multi-Modal Sensory DataPreprint
Clark, R., Wang, S., Wen, H., Trigoni, N., & Markham, A. (2016) · arXiv (Cornell University)
Place Recognition for Stereo Visual Odometry using LiDAR DescriptorsPreprint
Mo, J., & Sattar, J. (2019) · arXiv (Cornell University)
Superpixel Description and Indexing for Visual Loop Closure Detection
Euch, R. E., Garcia‐Fidalgo, E., Ortiz, A., Chaabane, F., & Ghazel, A. (2019) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2019.8869091
“The results [2] and [7] are taken from [4].”
BackgroundRobust Visual Place Recognition Based on Context Information
Dai, D., Chen, Z., Wang, J., Bao, P., & Zhao, H. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.11.046
Multi-condition Place Generator for Robust Place Recognition
Cheng, Y., Wang, Y., Qi, L., & Zhang, W. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37731-1_16
Illumination Robust Loop Closure Detection with the Constraint of Pose
Yan, D., Tuo, W., Wang, W., & Li, S. (2020) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/2352096513999200422141150
Advanced SeqSLAM using Discriminative Information for Light-Rail Localization at High Frame Rate.
Meng, Y., Jia, K., & Siu, W.-C. (2019) · J. Inf. Hiding Multim. Signal Process.
Neural network models for learning representations of 3D objects via tactile exploration
Yan, X. (2020) · Otago University Research Archive (University of Otago)
Digging Hierarchical Information For Visual Place Recognition With Weighting Similarity Metric
Liu, H., Zhang, Q., Hua, G., & Zhao, C. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190898
“Visual place recognition (VPR), which aims to match a query place with previously visited places, has received considerable attention for its applications in autonomous navigation [1, 2], mobile robotics [3, 4], and augmented reality [5, 6].”
BackgroundLearning from limited experience: Real-world robot navigation from a single traversal
Bruce, J. (2020) · Queensland University of Technology · doi:10.5204/thesis.eprints.205492
Global Alignment of Deep Features for Robot Localization in Changing Environment
Oh, J. H., & Lee, H.-J. (2019) · European Conference on Electrical Engineering and Computer Science (EECS) · doi:10.1109/eecs49779.2019.00026
“The sum-of-difference (SAD) method, which converts an image into a low-dimensional image and compares it with contrast, was proposed in [10].”
BackgroundMethodLong-Term Visual Robot Localization using Computational Models of the Neocortex
Pizzino, C. A. P., Vargas, P. A., & Costa, R. R. (2020) · Congresso Brasileiro de Automática · doi:10.48011/asba.v2i1.1036
“Milford and Wyeth (2012) proposed the SeqSLAM, a sequence based place recognition algorithm, which adopts sequence matching rather than single image matching and achieves significant performance improvements to lighting changes.”
BackgroundWang, T., Jia, K., & Yao, M. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378494
“6, compared with without the key frame retrieval mechanism method SeqSLAM [17] (black curve) and SeqCNNSLAM [15] (red curve), the proposed method (blue curve) achieves better scene tracking results.”
MethodFusing CAMs-weighted features and temporal information for robust loop closure detection
Li, Y., Zhong, S.-H., Ren, T., & Liu, Y. (2021) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3444685.3446309
“Seq-SLAM [18] does not rely on feature extraction but utilizes normalized pixel-intensity matching (in global fashion) between a sequence of images to achieve LCD.”
Self-Supervised Learning and Network Architecture Search for Domain-Adaptive Landmark DetectorPreprint
Kanji, T. (2020) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/45pq7
Self-Supervised Learning and Network Architecture Search for Domain-Adaptive Landmark DetectorPreprint
Kanji, T. (2020) · Engineering Archive (engrXiv) · doi:10.31224/osf.io/26xnj
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.