Visual Place Recognition: A Survey
Open accessThe DOI matches its Crossref record; 233 of the 239 references it cites were found in a registry or an index.
Abstract
Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines-particularly recognition in computer vision and animal navigation in neuroscience-have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition-the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“with a mid-level convolutional neural network (CNN) feature [124] to identify and extract landmarks as illustrated in Fig.”
BackgroundHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 3×
“McManus et al. [120] used the global descriptor HOG [121] on image patches to learn condition invariant scene signatures, while Sünderhauf et al. [122] used the Edge Boxes object proposal method [123] combined with a mid-level convolutional neural network (CNN) feature [124] to identify and extract landmarks as illust…”
Method(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
A Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004 · cited 1×
“Lamon et al. [105] used a variety of image features—such as edges [106], corners [107], and color patches—combined into a fingerprint of a location.”
BackgroundObject 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 11×
“The U-SIFT [72] descriptor was shown to display the greatest lighting invariance of the tested descriptors.”
MethodInfluentialSURF: 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
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901 · cited 1×
“Lamon et al. [105] used a variety of image features—such as edges [106], corners [107], and color patches—combined into a fingerprint of a location.”
BackgroundBlei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
Baeza-Yates, R. A., & Ribeiro-Neto, B. A. (1999) · Cited by 11,505
ORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037 · cited 1×
“SIFT features as in [76], CenSurE features as in FrameSLAM [2], or ORB features [137] as in ORB-SLAM [136].”
Method
Research works printed but not linked: 6
- neira, 0, Mobile robot localization and map building using monocular vision, Proc 5th Symp Intell Robot Syst, 275
- lynch, 1960, The Image of the City
- 10.1177/0278364914551008 · DOI
- 10.1177/027836402761412467 · doi:10.1177/027836402761412467 · Paper page
- 10.21236/ADA576491 · doi:10.21236/ada576491 · Paper page
- sim, 2005, Vision-based SLAM using the Rao-Blackwellised particle filter, Proc IJCAI Workshop Reason Uncertainty Robot
Cited by
Items 801–900 of 1,000
Automatic calibration of a biologically inspired neural network for robot SLAM
Dall’Osto, D., Hausler, S., Jacobson, A., & Milford, M. J. (2018) · QUT ePrints (Queensland University of Technology) · Cited by 2
Self-citationThe Research Status of Visual Place Recognition
Wang, B., Wu, X., Chen, A., Chen, C., & Liu, H. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1518/1/012039 · Cited by 2
“Instead, the shape features of the object are directly obtained and used for place comparison [28].”
MethodPlace Inference via Graph-Based Decisions on Deep Embeddings and Blur Detections
Woźniak, P., & Kwolek, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77977-1_14 · Cited by 2
Condition-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
“Sequence-based approaches are widely used techniques exploiting the temporal information of image sequences [1].”
MethodVisual 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
Deep Learning Based Place Recognition for Challenging Environments
Kumar, D. (2016) · UWSpace (University of Waterloo) · Cited by 4
Change Detection under Global Viewpoint UncertaintyPreprint
Murase, T., & Tanaka, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00552 · Cited by 2
“Our approach is related to previous work on scene retrieval but with key differences: In contrast to visual place recognition or map relative viewpoint localization [14], we focus on retrieving not the whole image but a small object (i.e., the change) in the scene.”
BackgroundMethodInfluentialFast-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
Struckmeier, O., Tiwari, K., Dora, S., Pearson, M. J., Bohté, S. M., Pennartz, C. M. A., & Kyrki, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.07201 · Cited by 2
“The recent advances in visual sensors, computer vision and deep learning research have shifted the focus of previous research on place recognition towards using vision as the primary sensory modality [1].”
BackgroundHu, H., Wang, H., Liu, Z., & Chen, W. (2020) · arXiv (Cornell University) · Cited by 2
Kong, D., Fang, Z., Li, H., Hou, K., Coleman, S., & Kerr, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03290 · Cited by 2
Advances in Inference and Representation for Simultaneous Localization and MappingPreprint
Rosen, D. M., Doherty, K., Espinoza, A. T., & Leonard, J. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.05041 · Cited by 2
“(15) addressed the specific problem of place recognition, which is closely related to issues of environmental representation and semantic mapping but aimed primarily at the problem of identifying loop closures.”
BackgroundSelf-citationBaumgartl, H., & Buettner, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11187 · Cited by 6
“ROBUSTNESS is of critical importance in many mobile robot applications such as inertia measurement [1], visual odometry [2] or visual navigation [3], simultaneous localization and mapping (SLAM) [4], [5] and visual place recognition [6], [7].”
BackgroundSeanNet: Semantic Understanding Network for Localization Under Object DynamicsPreprint
Li, X., Du, Y., Zeng, Z., & Jenkins, O. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02276 · Cited by 3
“Meanwhile, there is significant progress in outdoor visual place recognition [12] (VPR) under changing perceptual conditions [13]–[15].”
Role of Artificial Intelligence in Autonomous VehiclesPreprint
Waghmare, A. A., Ganesan, S., & Chen, J. (2024) · Preprints.org · doi:10.20944/preprints202408.0974.v1 · Cited by 2
Image Geolocation Method Based on Attention Mechanism Front Loading and Feature Fusion
Lu, H., Yang, C., Qi, B., Zhu, M., & Xu, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7168451 · Cited by 1
To Sparsify or not to Sparsify: Simplifying Visual Feature Maps for Mobile Agents
Eger, S., Pries, R., Sörös, G., Adam, M. G., Piccolrovazzi, M., & Steinbach, E. G. (2022) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism55400.2022.00020 · Cited by 1
TAU-Indoors Dataset for Visual and LiDAR Place Recognition
Dag, A., Alijani, F., Peltomäki, J., Suomela, L., Rahtu, E., Edelman, H., & Kämäräinen, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31438-4_22 · Cited by 1
Application of an improved VGG and RPN network in precision parts recognition
Li, D., Wang, M., Zhang, Y., & Zhai, C. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-231730 · Cited by 1
Visual 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
Semantic Topology and Global Descriptors Based Localization for UGV in Prior Air-View Map
Song, Q., Yan, F., Zhuang, Y., & Wang, W. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10367071 · Cited by 1
“Visual-based localization [2, 3, 4, 5, 6] has been studied extensively and achieved good recognition results due to the image data is easy to obtain and contains rich textures.”
BackgroundHierarchical 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
“Formally, given a visual traversal, the loop detection task is to compute correct loop pairs within a radius, say 5 m. Vision based loop detection task utilises VPR (visual place recognition) [24] solutions as core modules.”
MethodDual-attention-transformer-based semantic reranking for large-scale image localization
Xiao, Y., Du, S., Chen, X., Liu, M., & Sun, M. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05539-2 · Cited by 1
Enhancing Visual Place Recognition With Hybrid Attention Mechanisms in MixVPR
da Hu, J., Nie, J., Ning, Z., Feng, C., Wang, L., Li, J., & Cheng, S. (2024) · IEEE Access · doi:10.1109/access.2024.3487171 · Cited by 1
“Extensive research endeavors in Visual Place Recognition (VPR) have been comprehensively documented in numerous surveys and tutorials over the years [32], [33], [34] heavily on traditional handcrafted local features, which have very poor robustness to drastic changes in scene appearance.”
BackgroundTao, 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
“In this paper, we focus on LiDAR ‐ based approaches and refer to the survey paper by Lowry et al. (2015) and Luo et al. (2024).”
Malone, C., Vora, A., Peynot, T., & Milford, M. J. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802570 · Cited by 2
“Research in the VPR field often focuses on improving robustness to challenges such as viewpoint and appearance changes due to perspective and the environment [3], [4].”
Self-citationTraining-free Adapter for Multi-Modal Image Matching for All-Day Visual Place Recognition
Uggi, A., & Channappayya, S. S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889993 · Cited by 2
“In the same way, a machine achieves this by matching the query image with the pre-acquired reference images in the representation space [2], [3].”
CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition
Liang, J., Deng, Z., Zhou, Z., Sun, M., Ghasemalizadeh, O., Kuo, C.-H., Sen, A., & Manocha, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3551080 · Cited by 2
“However, the potential of RGB-D data is overlooked; especially for indoor environments, the depth information can be crucial for place recognition [4], [11], [12].”
InfluentialEFormer-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
“In recent years, Visual place recognition (VPR) has at-tracted significant attention in the computer vision and robotics communities [1]–[3], which is a key prerequisite for many robots and plays a pivotal role in autonomous driving and augmented reality.”
Shang, J., Liu, Y., Xu, Y., Xiao, J., & Ma, D. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3590549 · Cited by 6
3D Foundation Model-Based Loop Closing for Decentralized Collaborative SLAM
Lajoie, P., Ramtoula, B., Martini, D. D., & Beltrame, G. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3609204 · Cited by 5
“This task becomes particularly challenging when the robots’ viewpoints differ significantly due to varying trajectories and diverse sensor placements, making it difficult to indentify overlapping map sections and generate reliable inter-robot loop closures [1].”
Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAM
Laserna, J., Gupta, S., Mozos, Ó. M., Stachniss, C., & Segundo, P. S. (2025) · European Conference on Mobile Robots · doi:10.1109/ecmr65884.2025.11163179 · Cited by 1
“While these models can perform well on curated datasets, their robustness in diverse and previously unseen real-world conditions remains a challenge [17].”
Continual Learning of Regions for Efficient Robot Localization on Large Maps
Scucchia, M., & Maltoni, D. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3619058 · Cited by 1
“Despiteextensive research, LCD [2], [3], [4] remains a critical issue in large and dynamic environments due to two primary challenges: 1) Appearance Variation: When the robot navigates in a known place the observation can be different with respect to past observations, not only due to unavoidable…”
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
“Visual Place Recognition (VPR) is a global localization task based on image retrieval, which aims to find images from a reference image database that represent the same place as the query image [1].”
Promoting Cultural Heritage: Deep Learning-Based Temple Recognition for Karnataka Tourism
Shet, V. R., & Thenmozhi, S. (2025) · IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE) · doi:10.1109/icwite64848.2025.11307053 · Cited by 1
Visual place recognition with panoramic images using hybrid neural network models
Offermann, L. (2026) · Scientific Reports · doi:10.1038/s41598-025-34473-7 · Cited by 1
“Collecting the P, R K for all thresholds results in a precision-recall curve, a standard tool for evaluating the quality of VPR algorithms 37,39 .”
Wang, L., Lan, C., Wu, B., Yao, F., Wei, Z., Gao, T., & Yu, H. W. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115285 · Cited by 1
Tennakoon, K. B., Silva, O. D., Mann, G. K. I., Jayasiri, A., & Gosine, R. G. (2026) · IEEE transactions on field robotics. · doi:10.1109/tfr.2026.3657293 · Cited by 1
“VPR builds its index o ffl ine using geo-tagged reference images, which can be manually collected or sourced from aerial or web-based imagery [1].”
The Overlooked Value of Test-Time Reference Sets in Visual Place Recognition
Zaffar, M., Nan, L., Scherer, S., & Kooij, J. F. P. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00751 · Cited by 1
“1 Traditionally, the most investigated challenges in VPR have been viewpoint and appearance changes between the matching query and reference images, the so-called query-1 ref domain gap [29].”
Nguyen, S. T., Fontan, A., Milford, M. J., & Fischer, T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00026 · Cited by 3
“Visual localization problems in outdoor scenes often involve a vast search space [4, 31].”
Self-citationKim, J., & Chaitanya, J. V. K. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.03.030 · Cited by 1
Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors
Nguyen, S. T., Fontan, A., Milford, M. J., & Fischer, T. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00792 · Cited by 1
“Global descriptors enable finding the most similar database images to an input query image by encoding image-wide visual characteristics into compact representations [38, 39].”
Self-citationThe S3LI Vulcano Dataset: A Dataset for Multi-Modal SLAM in Unstructured Planetary Environments
Giubilato, R., Muller, M. G., Sewtz, M., González, L., Folkesson, J. B., & Triebel, R. (2026) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero66936.2026.11519802 · Cited by 5
“First, road-bound vehicles can traverse environments in two directions, imposing significant constraints on the diversity of viewpoints and perspectives and affecting positively the performances of place recognition algorithms for detection of loop closures [28].”
SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization
Zhang, X., Liu, Y., Liang, J., Li, K., Huang, Z., & Xiao, H. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3716172 · Cited by 1
“In large-scale search spaces, repetitive global structures may produce deceptively high PnP inlier counts even for incorrect candidate poses [40].”
A bag of relevant regions model for visual place recognition in coral reefs
Maldonado-Ramírez, A., & Torres-Méndez, L. A. (2016) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans.2016.7761188 · Cited by 1
Adaptive video object proposals by a context-aware model
Geng, W., Zhang, C., & Wu, G. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4561-9 · Cited by 1
“object tracking [26, 67], image/video segmentation [21, 43] and classification [13, 31, 59, 65], video summarization [22, 38], activity recognition [6, 66], object retrieval [47, 58, 63], multimodality retrieval [10, 12, 61], landmark recognition [11, 36, 50], and image/video storytelling [14, 35, 62].”
BackgroundIntegration of contextual information into the scene classification problem
Rubio, F., Martínez-Gómez, J., Flores, M. J., & Puerta, J. M. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.08.010 · Cited by 1
“The most common interpretation of scene classification is by means of semantic annotations describing the robot’s surroundings [11].”
BackgroundLearning Long-Term Invariant Features for Vision-Based Localization
Mithun, N. C., Simons, C., Casey, R. T., Hilligardt, S., & Roy–Chowdhury, A. K. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00225 · Cited by 3
“The authors in [31] and [16] offer comprehensive reviews on state-of-the-art approaches to vision-based localization.”
BackgroundAGs: Local descriptors derived from the dependent effects model
Mandeljc, R., & Maver, J. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.008 · Cited by 1
Baca, A., Haßmann, M., Kornfeind, P., & Cizgin, P. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-14526-2_10 · Cited by 1
Neural Network-Based Long-Term Place Recognition from Omni-Images
Lee, J., & Kim, A. (2019) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/urai.2019.8768636 · Cited by 1
“Visual place recognition is a robotics task that focuses on the perceptional ability of an agent to identify places already visited [1].”
BackgroundFast Landmark Recognition in Photo Albums
Stefani, P., & Oprean, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29891-3_45 · Cited by 1
Evaluating image features in real-world scenarios
Remmen, F., Dubbelman, G., & de With, P. H. N. (2020) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip49896.2020.9339363 · Cited by 2
“An optimal low-cost representation of the visual characteristics of a scene in a multitude of real-world conditions is an open topic [3].”
BackgroundSheng, J., Chen, L., Gao, Y., Changqing, S., & Rongchuan, S. (2021) · Chinese Journal of Electronics · doi:10.1049/cje.2020.11.005 · Cited by 1
Lecat, P., Blettery, E., Delavoipière, L., Saly-Giocanti, F., Conord, S., Gouet-Brunet, V., Devaux, A., Brédif, M., & Moret, F. (2021) · Humanités numériques · doi:10.4000/revuehn.1946 · Cited by 1
SMCN: Simplified mini-column network for visual place recognition
Huang, G., Chen, A., Gao, H., & Yang, P. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2024/1/012032 · Cited by 1
“Performing VPR needs to consider the various appearance of places due to uncertain factors such as day-night changes, view-point changes, and season changes, which makes VPR a challenging problem[1][2].”
BackgroundNie, J., Feng, J.-M., Xue, D., Pan, F., Liu, W., da Hu, J., & Cheng, S. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956385 · Cited by 3
“There are lots of metrics introduced in [1], [28] to evaluate the performance of VPR technologies.”
Reinforcement 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
Some Key Explorations in Planetary Rover Autonomy for ISRU Roles on the Moon
Ellery, A. A. (2023) · ASCE International Conference on Engineering, Science, Construction, and Operations in Challenging Environments (Earth and Space) · doi:10.1061/9780784484470.019 · Cited by 2
Minimum Sensing Strategy for a Path-following Problem via Discrete-time Control Barrier Functions⋆
Funada, R., Miyama, K., Toyooka, T., Tanaka, T., & Sampei, M. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.1417 · Cited by 1
Mechanistic data-driven combined modelling and predictive control method for coal-fired power unit
Hu, J., Han, Z., Zhao, J., & Wang, W. (2023) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai59504.2023.10327603 · Cited by 1
“Data-driven modeling (DDM) methods have been well developed for decades, such as system identification, machine learning (ML), and deep learning (DL) approaches, which are reported to be successfully applied for robotics, autonomous driving, chemical plant control [2]-[4].”
MethodSemSCo: Semantic Frequency Domain Scan Context for LiDAR-Based Place Recognition
Li, J., Qian, H., & Du, X. (2023) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar58858.2023.10406379 · Cited by 1
“However, cameras are sensitive to illumination, resulting in lower reliability in outdoor environments [5].”
BackgroundArcanjo, B., Ferrarini, B., Fasli, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3367275 · Cited by 2
“itself in the runtime environment using only image data [1].”
MethodSelf-citationAn Approach to Cooperative, Wide Area Visual Navigation by Leveraging Blockchain Consensus
Lyons, D. M., & Rahouti, M. (2023) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc59093.2023.00020 · Cited by 1
“This problem is related to place recognition [16] and object recognition but quite distinct from both.”
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
Location retrieval using qualitative place signatures of visible landmarks
Wei, L., Gouet-Brunet, V., & Cohn, A. G. (2024) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2024.2348736 · Cited by 3
“…where accurate satellite positioning information is not available, sensing modalities such as visual information have been explored for localization (Korrapati et al. 2012, Zamir et al. 2016, Piasco et al. 2018, Pion et al. 2020) or place recognition (Lowry et al. 2016, Ali-Bey et al. 2023).”
Distance-Ranking-Based Weighted Triplet Loss for Visual Place Recognition
Xiong, Y., Shi-xiong, X., & Meng, G. (2023) · International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR) · doi:10.1109/aihcir61661.2023.00022 · Cited by 1
“The relentless progress in deep learning and computer vision technologies has immensely driven the evolution of visual place recognition [1]-[3].”
BackgroundDeep Learning in Autonomous Vehicles: A Review
Patra, B., & Mahalwar, A. (2020) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.61841/turcomat.v11i1.14634 · Cited by 1
“Deep learning algorithms are used to enhance the accuracy and reliability of these techniques by incorporating sensor data and environmental features into the localization process (Kuipers, 2018).”
MethodA 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
NPR: 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
“V ISUAL Place Recognition (VPR) stands as a fundamental taskwithinthefieldsofintelligentrobotics[1],[2],[3],[4], [5], [6], [7] and computer vision [8], [9], [10], [11], [12], [13], which involves returning database images that are similar to a query image by comparing it with known large-scale…”
BackgroundGadd, M., Ramtoula, B., Martini, D. D., & Newman, P. M. (2024) · Springer proceedings in advanced robotics · doi:10.1007/978-3-031-63596-0_53 · Cited by 2
Self-citationScene Action Maps: Behavioural Maps for Navigation without Metric Information
Loo, J., & Hsu, D. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610489 · Cited by 5
“Purely topological approaches go further by avoiding metric information, instead representing the world relationally as a graph of perceptually significant places [16].”
BackgroundKamal, A. M., Dadson, N. K. N., Gegg, D., & Barbălată, C. (2024) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim55361.2024.10637187 · Cited by 1
“This additional information has been shown to improve localization when there is a large viewpoint difference, low texture, or noise [3].”
BackgroundCross-View Geo-Localization via Effective Negative Sampling
Park, J., Sung, C., Lee, S., Kang, D., & Myung, H. (2024) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas63016.2024.10773330 · Cited by 1
“Current approaches to CVGL focus on image retrieval [2] based on deep learning, treating it similarly to a visual place recognition [3] (VPR) task.”
PoCo: Point Context Cluster for RGBD Indoor Place Recognition
Liang, J., Deng, Z., Zhou, Z., Ghasemalizadeh, O., Manocha, D., Sun, M., Kuo, C.-H., & Sen, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802135 · Cited by 2
“Visual Place Recognition (VPR) is typically formulated as an image retrieval problem, i.e., retrieving candidate frames from a database by comparing similarities to a given query frame [2], [1].”
InfluentialCBGL: Fast Monte Carlo Passive Global Localisation of 2D LIDAR Sensor
Filotheou, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802235 · Cited by 1
“Various sensor and map modalities have been investigated in the literature: from 2D and 3D LIDAR sensors [1], [2], RGBD cameras [3], and RFID equipment [4], to keyframe-based submaps [5] and metric maps [6].”
Zhao, S., Jain, M., & Dev, S. (2024) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei64163.2024.10906249 · Cited by 1
“Visual place recognition [12] plays a key role in addressing these challenges by helping to align the maps and trajectories of different agents.”
SkyLoc: Cross-Modal Global Localization With a Sky-Looking Fish-Eye Camera and OpenStreetMap
Ma, W., Huang, S., & Sun, Y. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3550941 · Cited by 1
“To relieve the need of GNSS, place recognition and re-localization with visual cameras or LiDARs have been extensively studied in the research community [7], [8], [9], [10], [11], [12], [13].”
DJIST: Decoupled joint image and sequence training framework for sequential visual place recognition
Wan, S., Kang, L., Wei, Y., Shen, T., Wang, H., & Zuo, C. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131622 · Cited by 1
A bag of relevant regions for visual place recognition in challenging environments
Maldonado-Ramírez, A., Torres-Méndez, L. A., & Castelán, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899826 · Cited by 1
“For a comprehensive recent review of place recognition techniques, see [5].”
BackgroundInfluentialToward 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
“11, published that a survey about visual place recognition which is useful for loop closure detection.”
BackgroundVisual Place Recognition based on Multi-level CNN Features
Bao, Z., Li, A., Cui, Z., & Zhang, J. (2018) · International Conference on Robotics, Control and Automation (ICRCA) · doi:10.1145/3265639.3265684 · Cited by 1
“Generally speaking, visual place recognition systems contain three key components—an image processing module to interpret the incoming visual data, a map that maintains a representation of the robot’s knowledge of the world, and a belief generation module, which uses the incoming visual sensor data in combination with…”
BackgroundRobust 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
An Approach of Data Fusion for FuzzyART Based Visual Recognition
Dechemi, A., & Achour, N. (2019) · National Conference on Electrical and Electronics Engineering (ELECO) · doi:10.1109/iceee2019.2019.00024 · Cited by 1
“Visual place recognition systems contain three key components [6]: an image processing module to convert the incoming visual data, a map that maintain a representation of the robot knowledge of the world, and a belief generation module that make a decision whether the place is familiar or not using the incoming sensor…”
BackgroundMiNERVA: 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
Feature-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
Robust uncalibrated visual stabilization for nonholonomic mobile robots
Huang, Y., & Su, J. (2020) · Advanced Robotics · doi:10.1080/01691864.2020.1717993 · Cited by 1
“…localization and mapping is such a methodology to simultaneously build a map of an unknown environment and determine the location within the map via observing the external landmarks, which means it can provide a more accurate pose estimation of the mobile robot than the internal sensor [2,3].”
MethodHierarchical 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
“This demand has inspired a large body of work that address the visual place recognition problem, a key component of SLAM systems, with encouraging results [12, 22].”
ResultSelf-citationSpatial Perception by Object-Aware Visual Scene Representation
Lee, C.-Y., Lee, H., Hwang, I., & Zhang, B. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00467 · Cited by 1
“Although there have been many deep neural network-based methods recently [25, 1, 14, 13], ORB-SLAM2 is still an advanced method that works robustly in real-world environments based on advantages of the ORB descriptor.”
MethodMerging of appearance-based place knowledge among multiple robots
Karaoğuz, H., & Bozma, H. I. (2020) · Autonomous Robots · doi:10.1007/s10514-020-09911-2 · Cited by 1
Object-based Place Recognition for Mobile Robots using Laplace's Rule of Succession
Oh, J. H., & Lee, H.-J. (2020) · International Conference on Computer and Automation Engineering · doi:10.1145/3384613.3384651 · Cited by 1
“The demand for mobile robots that can perform autonomous navigation, simultaneous localization and mapping (SLAM) has intensified in recent years [1].”
BackgroundObject Boundary Identification using Two-phase Incremental Clustering
Gopalapillai, R., & Gupta, D. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.04.025 · Cited by 1
Robust Navigation under Incomplete Localization Using Reinforcement Learning
Xue, W., Ying, R., Chu, X., Miao, R., Qian, J., & Liu, P. (2020) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans46316.2020.9109920 · Cited by 1
“Given an image of current position, VPR system refers to a dataset of the environment and calculates N most similar images in the dataset [19].”
BackgroundWigley, E. (2021) · Annals of the American Association of Geographers · doi:10.1080/24694452.2020.1838256 · Cited by 2
“…and developing a large data set full of previous experiences of driving this route including in different lighting or climatic conditions or when certain features such as cars have moved (Newman 2014; Lowry et al. 2016) enables the onboard software to recognize and orient itself as it drives.”
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
“In single view setups, there is a vast literature on place recognition [15], using cameras (e.”
BackgroundMulti-modal sensing positioning technology for intelligent verification of stacked kilogram weights
Zhao, D., Ma, J., Yu, W., & Liu, G. (2021) · International Conference on Mechanical Engineering, Measurement Control, and Instrumentation · doi:10.1117/12.2611108 · Cited by 1
Bielecki, A., & Śmigielski, P. (2021) · Sensors · doi:10.3390/s21217270 · Cited by 1
“Local feature descriptors determine parts of the image to retain local features, whereas global place descriptors are based on color histograms or principal component analysis [9].”
BackgroundMethodRoad-Pulse: Pavement Vibration Features from Accelerator to Enhance Intelligent Vehicle Localization
Zhou, Z. S., Hu, Z., Li, N., Xiao, H., & Zhang, J. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575510 · Cited by 1
Coarse-to-Fine Visual Place Recognition
Qi, J., Wang, R., Wang, C., & Cao, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-92273-3_3 · Cited by 1
Metadata
- Authors
- Lowry, S., Sünderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., & Milford, M. J.
- Affiliations
- Queensland University of Technology (AU)
- University of Oxford (GB)
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- Harvard University (US)
- ORCID
- Venue
- IEEE Transactions on Robotics
- Published
- 2016-02
- Volume
- 32
- Issue
- 1
- Pages
- 1-19
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2284029970
- Cited by
- 1,079
- References
- 239
- Citations by year
- 2026: 47 · 2025: 63 · 2024: 111 · 2023: 112 · 2022: 109 · 2021: 148 · 2020: 156 · 2019: 132 · 2018: 100 · 2017: 72 · 2016: 29
- FWCI
- 97.28
- Type
- journal article
- Language
- en
- Open access
- green
- purl.org
- Licence
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- QUT ePrints (Queensland University of Technology) (submittedVersion)
- Funders
- ARC Future Fellowship (FT140101229)
- Australian Centre for Robotic Vision
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Spatial Cognition and Navigation
- Keywords
- visual place recognition, place recognition, appearance changes, animal navigation, semantic scene understanding, audio description, deep learning
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.