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 101–200 of 1,000
Visual Place Recognition: A Tutorial [Tutorial]
Schubert, S., Neubert, P., Garg, S., Milford, M. J., & Fischer, T. (2023) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2023.3310859 · Cited by 102
“A number of survey and benchmarking papers have discussed the challenges, open questions, and achievements in the field of VPR [1], [2], [3], [4], [5], [6].”
BackgroundSelf-citationA Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to ImitationPreprint
Tai, L., Zhang, J., Liu, M., Boedecker, J., & Burgard, W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.07139 · Cited by 143
Xia, L., Cui, J., Shen, R., Xu, X. W., Gao, Y., & Li, X. (2020) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881420919185 · Cited by 76
Localizing Discriminative Visual Landmarks for Place Recognition
Xin, Z., Cai, Y., Lu, T., Xing, X., Cai, S., Zhang, J., Yang, Y., & Wang, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794383 · Cited by 71
“Although holistic features are much more robust against appearance changes, they are sensitive to viewpoint changes and partial occlusions [1].”
BackgroundEmmi, L., Flécher, E. L., Cadenat, V., & Devy, M. (2021) · Precision Agriculture · doi:10.1007/s11119-020-09773-9 · Cited by 66
Benchmarking Image Retrieval for Visual Localization
Pion, N., Humenberger, M., Csurka, G., Cabon, Y., & Sattler, T. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00058 · Cited by 82
“For more details see recent survey papers that cover different aspects of visual localization [13, 29, 58, 67, 107] and benchmark these methods [79, 81, 100].”
BackgroundGround-Level Mapping and Navigating for Agriculture Based on IoT and Computer Vision
Zhao, W., Wang, X., Qi, B., & Runge, T. M. (2020) · IEEE Access · doi:10.1109/access.2020.3043662 · Cited by 65
“…[7]; work done to provide mapping with high robustness under illumination and seasonal variation using scene recognition and localization [8], [9]; a spatial-temporal map that was highly robust to season variations [10]; and a LIDAR system that was adopted to obtain the information in a…”
MethodAutonomous Navigation in Inclement Weather Based on a Localizing Ground Penetrating Radar
Ort, T., Gilitschenski, I., & Rus, D. L. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2976310 · Cited by 74
“Particularly for visual SLAM [1], [2], an extensive body of research explicitly focuses on addressing these types of problems.”
BackgroundSemantic localization on BIM-generated maps using a 3D LiDAR sensor
Yin, H., Lin, Z., & Yeoh, J. K. W. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104641 · Cited by 82
“A typical semantic-based visual localization is retrieving query images from database, namely visual place recognition or global localization [29].”
BackgroundRecovering Stable Scale in Monocular SLAM Using Object-Supplemented Bundle Adjustment
Frost, D., Prisacariu, V. A., & Murray, D. W. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2820722 · Cited by 70
“for previously observed landmarks in the map is simply not feasible, notwithstanding progress in the use of geometric and appearance cues [9].”
BackgroundOREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
Schaupp, L., Bürki, M., Dubé, R., Siegwart, R., & Cadena, C. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968094 · Cited by 66
“However, visual place recognition algorithms struggle to cope with strong appearance changes that commonly occur during longterm applications in outdoor environments, and fail under certain ill-lighted conditions [1].”
BackgroundImage Feature Information Extraction for Interest Point Detection: A Comprehensive Review
Jing, J., Gao, T. S., Zhang, W., Gao, Y., & Sun, C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3201185 · Cited by 84
“for object tracking [4] and 3D reconstruction [5].”
BackgroundOlayode, I. O., Du, B., Severino, A. G., Campisi, T., & Alex, F. J. (2023) · Journal of Traffic and Transportation Engineering (English Edition) · doi:10.1016/j.jtte.2023.07.006 · Cited by 92
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not.Preprint
Tai, L., & Liu, M. (2016) · arXiv (Cornell University) · Cited by 70
Image features for visual teach-and-repeat navigation in changing environments
Krajník, T., Cristóforis, P. D., Kusumam, K., Neubert, P., & Duckett, T. (2016) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2016.11.011 · Cited by 64
“Although the problem of long-term autonomy in changing environments has received considerable attention during the last few years [7], the main e ff orts were aimed at place recognition [8] and metric local-Accepted ization [9].”
BackgroundFast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
Hosseinzadeh, S., Shakeri, M., & Zhang, H. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594050 · Cited by 61
A Hybrid Compact Neural Architecture for Visual Place Recognition
Chancan, M., Hernandez-Nunez, L., Narendra, A., Barron, A. B., & Milford, M. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2967324 · Cited by 74
“multiple places may look similar) [1].”
Self-citationEnvironmental Context Prediction for Lower Limb Prostheses With Uncertainty Quantification
Zhong, B., da Silva, R. L., Li, M., Huang, H., & Lobaton, E. J. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.2993399 · Cited by 67
“Deep learning has shown promising potential in various vision applications, such as semantic segmentation [14] and site recognition [15].”
BackgroundTextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts
Hong, Z., Pétillot, Y., Lane, D. M., Miao, Y., & Wang, S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00295 · Cited by 74
“Similar to most of the visual place recognition work, we use precision and recall (PR) as the main performance measurement for evaluation [15].”
BackgroundMethodFast and incremental loop closure detection with deep features and proximity graphs
An, S., Zhu, H., Wei, D., Tsintotas, K. A., & Gasteratos, A. C. (2022) · Journal of Field Robotics · doi:10.1002/rob.22060 · Cited by 61
“, the ability to recognize previously visited locations, plays a primary role in the generation of a valid map [4].”
BackgroundSaha, M., Fiannaca, A. J., Kneisel, M., Cutrell, E., & Morris, M. R. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353776 · Cited by 56
“Prior work in robotics has looked into using deep learning approaches [11,41,53] and traditional”
LiDAR-Based Place Recognition For Autonomous Driving: A Survey
Zhang, Y., Shi, P., & Li, J. (2024) · ACM Computing Surveys · doi:10.1145/3707446 · Cited by 95
“To facilitate and encourage further research, scholars have engaged in method classification [36], performance evaluation [37],”
A survey of autonomous robots and multi-robot navigation: Perception, planning and collaboration
Chen, W., Chi, W., Ji, S., Ye, H., Liu, J., Jia, Y., Yu, J., & Cheng, J. (2024) · Biomimetic Intelligence and Robotics · doi:10.1016/j.birob.2024.100203 · Cited by 116
Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning
Kulhánek, J., Derner, E., & Babuška, R. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3068106 · Cited by 79
Long-Term 3D Localization and Pose from Semantic Labellings
Toft, C., Olsson, C., & Kahl, F. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.83 · Cited by 61
“This is in contrast to approaches working in the image domain only, solving the problem of ”visual place recognition”, see [23] for a survey.”
ResultHyperdimensional computing as a framework for systematic aggregation of image descriptors
Neubert, P., & Schubert, S. (2021) · 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/cvpr46437.2021.01666 · Cited by 72
“Visual place recognition [35] is a basic problem in mobile robotics, e.”
BackgroundPrior Guided Dropout for Robust Visual Localization in Dynamic Environments
Huang, Z., Xu, Y., Shi, J., Zhou, X., Bao, H., & Zhang, G. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00288 · Cited by 66
“Topological localization, which is also called place recognition, aims to find whether the place or location where the query image is taken has been visited before [30].”
BackgroundAccurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
Shi, Y., Yu, X., Liu, L., Campbell, D., Koniusz, P., & Li, H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3189702 · Cited by 101
“tion [26], [27], [28], [29], [30], [31], [32], [33], [34], and loop-”
Feature-based visual simultaneous localization and mapping: a survey
Azzam, R., Taha, T., Huang, S., & Zweiri, Y. (2020) · SN Applied Sciences · doi:10.1007/s42452-020-2001-3 · Cited by 63
HBST: A Hamming Distance Embedding Binary Search Tree for Feature-Based Visual Place Recognition
Schlegel, D., & Grisetti, G. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2856542 · Cited by 60
“Based on the reported image matches and on the provided ground truth we then can compute Precision-Recall curves and F1 score [1].”
BackgroundMethodInfluentialMultiRes-NetVLAD: Augmenting Place Recognition Training With Low-Resolution Imagery
Khaliq, A., Milford, M. J., & Garg, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3147257 · Cited by 57
“VPR is challenging due to uncontrollable environmental factors such as illumination, viewpoint, and seasonal transitions [1], [2], [9].”
BackgroundSelf-citationGraph-Based Place Recognition in Image Sequences with CNN Features
Zhang, X., Wang, L., Zhao, Y. C., & Su, Y. L. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0917-2 · Cited by 56
“Given the image of a place, the aim of visual place recognition is to determine whether this place has been visited by a mobile robot before [28], and it is also known as loop closure detection (LCD).”
BackgroundProbabilistic Appearance-Based Place Recognition Through Bag of Tracked Words
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2897151 · Cited by 50
“[4].”
A Neurologically Inspired Sequence Processing Model for Mobile Robot Place Recognition
Neubert, P., Schubert, S., & Protzel, P. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2927096 · Cited by 54
Modest-vocabulary loop-closure detection with incremental bag of tracked words
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103782 · Cited by 53
Visual place recognition with probabilistic voting
Gehrig, M., Stumm, E. S., Hinzmann, T., & Siegwart, R. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989362 · Cited by 51
“The resulting task, typically referred to as place recognition or loop closure, is frequently solved on the basis of appearance due to the almost universal presence of cameras on mobile platforms and the rich information they provide [1].”
BackgroundA survey of visual navigation: From geometry to embodied AI
Zhang, T., Hu, X., Xiao, J., & Zhang, G. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105036 · Cited by 68
A systematic literature review on long‐term localization and mapping for mobile robots
Sousa, R. B., Sobreira, H., & Moreira, A. P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22170 · Cited by 68
Autonomous UAV Cinematography: A Tutorial and a Formalized Shot-Type Taxonomy
Mademlis, I., Nikolaidis, N., Tefas, A., Pitas, I., Wagner, T., & Messina, A. (2019) · ACM Computing Surveys · doi:10.1145/3347713 · Cited by 58
“Visual SLAM performs an incremental 3D scene reconstruction based on the camera feed, using a real-time, on-line variant of Structure-from-Motion algorithms [49], augmented by visual place recognition [40], graph-based map modeling [23] and loop closure [1] modules.”
MethodSelf-powered bionic antenna based on triboelectric nanogenerator for micro-robotic tactile sensing
Zhu, D., Lu, J., Zheng, M., Wang, D., Wang, J., Liu, Y., Wang, X., & Zhang, M. (2023) · Nano Energy · doi:10.1016/j.nanoen.2023.108644 · Cited by 50
Data-Efficient Large Scale Place Recognition with Graded Similarity Supervision
Leyva-Vallina, M., Strisciuglio, N., & Petkov, N. (2023) · 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/cvpr52729.2023.02249 · Cited by 75
“Visual place recognition (VPR) is an important task of computer vision, and a fundamental building block of navigation systems for autonomous vehicles [24, 52].”
Kong, D., Li, X., Xu, Q., Hu, Y., & Ni, P. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3364511 · Cited by 50
“Image-based PR research has been well explored over the past decade with encouraging results [6], [7], [8], [9].”
Topological local-metric framework for mobile robots navigation: a long term perspective
Tang, L., Wang, Y., Ding, X., Yin, H., Xiong, R., & Huang, S. (2018) · Autonomous Robots · doi:10.1007/s10514-018-9724-7 · Cited by 53
“The other is to find the topological localization through place recognition (Lowry et al. 2016; Churchill and Newman 2013; Milford and Wyeth 2012; Cummins and Newman 2008).”
BackgroundAutonomous Navigation Framework for Intelligent Robots Based on a Semantic Environment Modeling
Joo, S.-H., Manzoor, S., Rocha, Y. G., Bae, S.-H., Lee, K.-H., Kuc, T., & Kim, M. (2020) · Applied Sciences · doi:10.3390/app10093219 · Cited by 59
“Visual place recognition (VPR) plays a vital role in achieving long term autonomy for mobile robotic applications [1].”
BackgroundGeometric Consistency for Self-Supervised End-to-End Visual Odometry
Iyer, G., Jatavallabhula, K. M., Gupta, G., Krishna, K. M., & Paull, L. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00064 · Cited by 58
The Halting problem: Video analysis of self-driving cars in traffic
Brown, B. A. T., Broth, M., & Vinkhuyzen, E. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581045 · Cited by 67
“It is important to note that while there has been impressive progress [48], signi cant challenges remain on basic tasks–such as using vision to locate a car [9].”
BackgroundSRAL: Shared Representative Appearance Learning for Long-Term Visual Place Recognition
Han, F., Yang, X., Deng, Y., Rentschler, M. E., Yang, D., & Zhang, H. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2662061 · Cited by 45
“Methods based on pairwise similarity scores calculate a similarity score of the current scene image and each template based on a certain distance metric and select the template image that has the maximum score [20], [21].”
MethodLLOAM: LiDAR Odometry and Mapping with Loop-closure Detection Based Correction
Ji, X., Zuo, L., Zhang, C., & Liu, Y. (2019) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2019.8816388 · Cited by 45
“Moreover, 3D LiDAR based SLAM is stable and accurate as LiDAR does not suffer from the failures caused by illumination changes and can provide high frequency range measurements where errors are relatively constant irrespective of the distance measured [4], [5].”
BackgroundVisual Cross-View Metric Localization with Dense Uncertainty Estimates
Xia, Z., Booij, O., Manfredi, M., & Kooij, J. F. P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19842-7_6 · Cited by 84
SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation
Lentsch, T., Xia, Z., Caesar, H., & Kooij, J. F. P. (2023) · 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/cvpr52729.2023.01652 · Cited by 91
“, Global Navigation Satellite Systems (GNSS), image retrieval [19], or dead reckoning [13].”
BackgroundInvestigating the Role of Image Retrieval for Visual Localization: An Exhaustive Benchmark
Humenberger, M., Cabon, Y., Pion, N., Weinzaepfel, P., Lee, D., Guérin, N., Sattler, T., & Csurka, G. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01615-7 · Cited by 66
“For more details on aspects of visual localization, please see recent survey papers (Brejcha and Čadík 2017; GarciaFidalgo andOrtiz 2015; Lowry et al. 2016; Piasco et al. 2018; Zamir et al. 2016) and benchmarks (Sattler et al.”
VLASE: Vehicle Localization by Aggregating Semantic Edges
Yu, X., Chaturvedi, S., Feng, C., Taguchi, Y., Lee, T., Fernandes, C., & Ramalingam, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594358 · Cited by 47
Jiang, B., & Shen, S. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160337 · Cited by 43
“Much research has been devoted to vision-based loop detection [2], [3], but their methods often suffer from visual feature variation due to illumination, view point or seasonal changes.”
BackgroundCondition-Invariant Multi-View Place RecognitionPreprint
Fácil, J. M., Olid, D., Montesano, L., & Civera, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09516 · Cited by 54
“Given a dataset of images taken at different places, visual place recognition [1], [2], [3] aims to identify the place of a new query image by associating it to one or several images of the dataset taken in the same location.”
BackgroundWang, K., Wang, Y., Liu, B., & Chen, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3256459 · Cited by 63
“Therefore, it has been widely applied in all levels of the ICV field, including planning and decision-making [10], [11], [12], [13], perception [14], [15], [16], [17], [18], [19], map and positioning [20], [21], [22], [23], and so on.”
MethodImproving Visual Localization Accuracy in Dynamic Environments Based on Dynamic Region Removal
Cheng, J., Zhang, H., & Meng, M. Q. ‐. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.2964938 · Cited by 42
“However, the vision-based methods are vulnerable to uncontrolled environmental conditions such as moving objects [23] or changes in illumination [24], which can adversely affect localization accuracy.”
Background3D point cloud-based place recognition: a survey
Luo, K., Yu, H., Chen, X., Yang, Z., Wang, J., Cheng, P., & Mian, A. S. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10713-6 · Cited by 53
“Lowry (Lowry et al. 2015) defined the “place” concept in their survey and discussed how VPR solutions can implicitly or explicitly account for changes in the environment’s appearance.”
Robust Multimodal Sequence-Based Loop Closure Detection via Structured Sparsity
Zhang, H., Han, F., & Wang, H. (2016) · Robotics: Science and Systems · doi:10.15607/rss.2016.xii.043 · Cited by 39
“Loop closure detection is an integrated component of all visual SLAM techniques, which uses visual features to recognize revisited locations [25].”
Lin, S., Cheng, R., Wang, K., & Yang, K. (2018) · Sensors · doi:10.3390/s18082476 · Cited by 44
“However, it is possible that the visual information of a location varies substantially between query and database from multiple environmental variations, which is a challenging issue for achieving robust visual localization [3].”
BackgroundMerrill, N., & Huang, G. P. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968159 · Cited by 40
“Many systems have come forth [7], each with their own benefits, in terms of accuracy, efficiency, storage requirements, or a mix of the three.”
BackgroundOneShot Global Localization: Instant LiDAR-Visual Pose Estimation
Ratz, S., Dymczyk, M., Siegwart, R., & Dubé, R. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197458 · Cited by 46
“ill-lighted conditions or in situations where illumination undergoes strong changes over time [2].”
BackgroundHou, Y., Zhang, H., & Zhou, S. (2017) · Autonomous Robots · doi:10.1007/s10514-017-9684-3 · Cited by 43
“We used two metrics to evaluate the performance in terms of recognition accuracy and matching efficiency: (a) precision– recall curve , which is commonly used criterion in the VPR community (Lowry et al. 2016), and (b) average matching time per query .”
BackgroundMethodInfluentialZaffar, M., Khaliq, A., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.09107 · Cited by 50
“been the prime focus of all VPR techniques, latter has been discussed only recently. A detailed survey of the challenges, developments and future directions in VPR has been performed by Lowry et al. [3]. The early techniques employed for image matching in VPR consisted of handcrafted feature descriptors [15] [16]. The…”
BackgroundMethodSelf-citationGeneral Place Recognition Survey: Toward Real-World Autonomy
Yin, P., Jiao, J., Zhao, S., Xu, L., Huang, G. P., Choset, H., Scherer, S., & Han, J. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3550771 · Cited by 71
“Effective algorithms must strike a balance between accuracy and computational efficiency.”
Gottipati, S. K., Seo, K., Bhatt, D., Mai, V., Jatavallabhula, K. M., & Paull, L. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2932575 · Cited by 40
“We refer the interested reader to [19] for an excellent survey.”
BackgroundAutoMerge: A Framework for Map Assembling and Smoothing in City-Scale Environments
Yin, P., Zhao, S., Lai, H., Ge, R., Zhang, J., Choset, H., & Scherer, S. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3290448 · Cited by 54
Sequence searching with CNN features for robust and fast visual place recognition
Bai, D., Wang, C., Zhang, B., Yi, X., & Yang, X. (2017) · Computers & Graphics · doi:10.1016/j.cag.2017.07.019 · Cited by 38
Fast and Effective Loop Closure Detection to Improve SLAM Performance
Güçlü, O., & Can, A. B. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0718-z · Cited by 44
“Besides the inherent difficulties of place recognition, another important challenge is the expansion of the search space by movement of the robot [23].”
BackgroundExploring Performance Bounds of Visual Place Recognition Using Extended Precision
Ferrarini, B., Waheed, M., Waheed, S., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2969197 · Cited by 45
“VPR is a fundamental task in many endeavours in the field of robotics and hence has been subject to great advancements in recent times in regard to both existing algorithms and new techniques [27].”
MethodSelf-citationAugmenting Visual Place Recognition With Structural Cues
Oertel, A., Cieslewski, T., & Scaramuzza, D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3009077 · Cited by 50
“See [12] for a survey of handcrafted visual place recognition methods.”
BackgroundRecent advances in evolutionary and bio-inspired adaptive robotics: Exploiting embodied dynamics
Husbands, P., Shim, Y., Garvie, M., Dewar, A., Domcsek, N., Graham, P., Knight, J. C., Nowotny, T., & Philippides, A. O. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02275-9 · Cited by 47
Addressing Challenging Place Recognition Tasks Using Generative Adversarial Networks
Latif, Y., Garg, R., Milford, M. J., & Reid, I. D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461081 · Cited by 36
Self-citationOptimized Self-Localization for SLAM in Dynamic Scenes Using Probability Hypothesis Density Filters
Evers, C., & Naylor, P. A. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2775590 · Cited by 39
“Global descriptors [18] process the image without a detection phase, and are hence particularly suitable for place recognition.”
BackgroundIndoor Localization for Augmented Reality Devices Using BIM, Point Clouds, and Template Matching
Herbers, P., & König, M. (2019) · Applied Sciences · doi:10.3390/app9204260 · Cited by 40
Visual Place Recognition by spatial matching of high-level CNN features
Camara, L. G., & Přeučil, L. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103625 · Cited by 47
“Specifically, mobile robots whose main sensors are cameras typically solve loop closure by Visual Place Recognition (VPR) [11], a fundamental and still open problem in computer vision and also the main subject of this paper.”
BackgroundLocalization for Autonomous Driving
Woo, A., Fidan, B., & Melek, W. (2018) · Wiley eBooks · doi:10.1002/9781119434610.ch29 · Cited by 51
Topometric Localization with Deep Learning
Oliveira, G. L., Radwan, N., Burgard, W., & Brox, T. (2019) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-28619-4_38 · Cited by 39
Multi-sensor three-dimensional Monte Carlo localization for long-term aerial robot navigation
Pérez-Grau, F. J., Caballero, F., Viguria, A., & Ollero, A. (2017) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881417732757 · Cited by 36
“Some of them perform well even in long trajectories when we revisit the same areas, which allows for loop closing in order to reduce the localization uncertainty.(23,24) However, the problem of loop closing in order to distinguish places in the environment is usually framed as a classification task rather than a robot…”
BackgroundYou Are Here: Geolocation by Embedding Maps and Images
Samano, N., Zhou, M., & Calway, A. D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58592-1_30 · Cited by 53
Fast and Robust Bio-inspired Teach and Repeat Navigation
Dall’Osto, D., Fischer, T., & Milford, M. J. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636334 · Cited by 38
“The feature based approach to teach and repeat approach has recently been extended with work from the visual place recognition field (see [32] for a survey), where more detailed image descriptors are used to uniquely identify images in the world.”
BackgroundSelf-citationA Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition
Keetha, N., Milford, M. J., & Garg, S. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3096751 · Cited by 42
“surveys [12]–[14] have reviewed the many representations used to describe images for VPR, ranging from hand-crafted fea-”
BackgroundSelf-citationXu, Y., Huang, J., Wang, J., Wang, Y., Qin, H., & Nan, K. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3094228 · Cited by 41
“LCD which can also be regarded as place recognition [2] is an essential component in the VSLAM system.”
BackgroundVisual Place Recognition Using Landmark Distribution Descriptors
Panphattarasap, P., & Calway, A. D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54190-7_30 · Cited by 35
“As pointed out in [2], the two categories above tend to address complementary issues: local features provide a degree of invariance to viewing position and direction, whilst global descriptors provide better invariance to changes in viewing conditions.”
BackgroundMethodInfluentialUnsupervised semantic clustering and localization for mobile robotics tasks
Balaska, V. E., Bampis, L., Boudourides, M. A., & Gasteratos, A. C. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103567 · Cited by 37
Lamb wave-based mapping of plate structures via frontier exploration
Miranda, A., Hook, J. V., & Schaal, C. (2020) · Ultrasonics · doi:10.1016/j.ultras.2020.106282 · Cited by 34
“Practical applications often use occupancy grid representations [24], as in this work, and modern techniques are quite robust [25].”
MethodRobust Place Recognition and Loop Closing in Laser-Based SLAM for UGVs in Urban Environments
Cao, F., Zhuang, Y., Zhang, H., & Wang, W. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2815956 · Cited by 34
“Visual place recognition [4] has been studied extensively in recent years and most of the approaches are image-toimage or appearance-based such as FAB-MAP [5].”
BackgroundA Multi-Domain Feature Learning Method for Visual Place Recognition
Yin, P., Xu, L., Li, X.-Q., Chen, Y., Li, Y., Srivatsan, R. A., Li, L., Ji, J., & He, Y. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793752 · Cited by 36
“Visual place recognition (VPR) [2] or loop closure detection (LCD) helps robots to find loop closure in SLAM framework and is an essential element for accurate mapping and localization.”
BackgroundLi, Z., Shang, T., Xu, P., & Deng, Z. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11367-8 · Cited by 50
“The contributions of this work lie fourfold: ● Compared to the previous survey of place recognition, such as Lowry et al. (2015), Zhang et al. ( 2021), Barros et al. (2021 ), Zhang et al. ( 2024a) and Luo et al. (2024), our overview is more comprehensive and in-depth.”
Enhancing Place Recognition Using Joint Intensity - Depth Analysis and Synthetic Data
Sizikova, E., Singh, V. K., Georgescu, B., Halber, M., Ma, K., & Chen, T. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49409-8_74 · Cited by 36
“Visual place recognition is a task of detecting when two images in an image sequence depict the same location, possibly under camera viewpoint or illumination-related appearance changes [14].”
BackgroundLearning Deep NBNN Representations for Robust Place Categorization
Mancini, M., Bulò, S. R., Ricci, E., & Barbara Caputo, B. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2705282 · Cited by 32
“In the last decade several works in the robotic community addressed the problem of developing robust place recognition [15], [16], [17], [8], [9] and semantic classification [4], [18], [7] approaches using visual data.”
BackgroundOpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions
Talbot, B., Garg, S., & Milford, M. J. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593761 · Cited by 34
Self-citationSchubert, S., Neubert, P., & Protzel, P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197044 · Cited by 33
“An overview of existing methods is given in [2].”
MethodProbabilistic Visual Place Recognition for Hierarchical Localization
Xu, M., Sünderhauf, N., & Milford, M. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3040134 · Cited by 49
“While there is an extensive literature around improving the invariance of place recognition systems to appearance change [5], [10]–[13], these systems are not designed to localize at tight error tolerances (e.g. ≤ 5 m) more suitable for hierarchical localization.”
BackgroundSelf-citationRadar-to-Lidar: Heterogeneous Place Recognition via Joint Learning
Yin, H., Xu, X., Wang, Y., & Xiong, R. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.661199 · Cited by 39
Semantic loop closure detection based on graph matching in multi-objects scenes
Qin, C., Zhang, Y., Liu, Y., & Lv, G. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103072 · Cited by 42
Season-Invariant and Viewpoint-Tolerant LiDAR Place Recognition in GPS-Denied Environments
Cao, F., Yan, F., Wang, S., Zhuang, Y., & Wang, W. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2962416 · Cited by 33
“Since cameras are inexpensive and smaller in size, vision-based place recognition has attracted significant interest in recent years [6].”
BackgroundKeroglou, C., Kansizoglou, I., Michailidis, P., Oikonomou, K. M., Papapetros, I. T., Dragkola, P., Michailidis, I., Gasteratos, A. C., Kosmatopoulos, E. B., & Sirakoulis, G. C. (2023) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2023.3261342 · Cited by 36
“On the other hand dynamic conditions such as different illumination states, weather conditions or moved objects between the mapping and the query observations can significantly affect the overall performance [57], [58], [59], [60], [61].”
BackgroundAugmenting Visual Place Recognition With Structural Cues
Oertel, A., Cieslewski, T., & Scaramuzza, D. (2020) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-197709 · Cited by 32
Visual Place Recognition using LiDAR Intensity Information
Giammarino, L. D., Aloise, I., Stachniss, C., & Grisetti, G. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636649 · Cited by 32
“Effective solutions are available to quickly find the potential matches in the database, see [23].”
BackgroundConvolutional Cross-View Pose Estimation
Xia, Z., Booij, O., & Kooij, J. F. P. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3346924 · Cited by 75
“Thus, other sensors [3], such as camera [4], [5], [6] and LiDAR [7], [8], [9], are used in combination with detailed HD maps [10], [11] to enhance the localization accuracy and robustness.”
Method
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.