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 601–700 of 1,000
Papapetros, I. T., Kansizoglou, I., Bampis, L., & Gasteratos, A. C. (2023) · Machines · doi:10.3390/machines11050558 · Cited by 6
GeoCluster: Enhancing Visual Place Recognition in Spatial Domain on Aerial Vehicle Platforms
Chen, C., He, M., Wang, J., & Meng, Z. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3363536 · Cited by 6
Patterns of approximated localised moments for visual loop closure detection
Erhan, C., Sarıyanidi, E., Şencan, O., & Temeltaş, H. (2017) · IET Computer Vision · doi:10.1049/iet-cvi.2016.0237 · Cited by 5
Fast and Consistent Matching for Landmark-Based Place Recognition
Liu, Q., & Duan, F. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-01108-9 · Cited by 5
Reliable Data Association for Feature-Based Vehicle Localization using Geometric Hashing Methods
Hofstetter, I., Sprunk, M., Ries, F., & Haueis, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196601 · Cited by 5
“The latter is also the case in visual place recognition, which is the solution to the problem of determining if an image can be associated to a place that has been seen before [13], [14].”
BackgroundProbabilistic Qualitative Localization and Mapping
Mor, R., & Indelman, V. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341269 · Cited by 7
“A survey of topological mapping and place detection approaches can be found in [19].”
BackgroundMethod of Robot Episode Cognition Based on Hippocampus Mechanism
Yuan, J., Guo, W. P., Zha, F., Li, M., & Sun, L. (2021) · IEEE Access · doi:10.1109/access.2021.3119530 · Cited by 6
“Cognitive map [3] [4] is a representation method that records the relationship between environmental landmarks.”
MethodYi, S., Worrall, S., & Nebot, E. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564875 · Cited by 6
Chen, S., Wu, J., Lu, Q., Wang, Y., & Lin, Z. (2021) · International Journal of Advanced Robotic Systems · doi:10.1177/17298814211050560 · Cited by 5
“LCD is to determine whether the robot has returned to a location that has been visited before, and it is, in essence, the same as global localization and place recognition.(19,20) So next we introduce these three aspects together.”
BackgroundEvaluation of Long-term LiDAR Place Recognition
Peltomäki, J., Alijani, F., Puura, J., Huttunen, H. J., Rahtu, E., & Kämäräinen, J. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636320 · Cited by 6
“Due to its importance place recognition is an important research topic in robotics and computer vision community for which Lowry et al. [1] and Zhang et al. [2] survey the past works.”
BackgroundMethodA Cross-Platform HD Dataset and a Two-Step Framework for Robust Aerial Image Matching
Shahid, M., Abhishek, B., & Channappayya, S. S. (2022) · IEEE Access · doi:10.1109/access.2022.3184328 · Cited by 5
“A comprehensive review of VPR and where is your place can be found in the literature [18], [19].”
BackgroundMethodInfluentialGlobal Data Association for SLAM with 3D Grassmannian Manifold Objects
Lusk, P. C., & How, J. P. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981075 · Cited by 11
“In the visual place recognition [4] setting, image features are commonly used in bag-of-words techniques [5] for loop candidate retrieval and geometric verification.”
MethodCondition-invariant and compact visual place description by convolutional autoencoder
Ye, H., Chen, W., Yu, J., He, L., Guan, Y., & Zhang, H. (2023) · Robotica · doi:10.1017/s0263574723000085 · Cited by 9
“Although these traditional methods have been widely used in SLAM (simultaneous localization and mapping) research, they still struggle in large-scale environments with severe appearance changes [4].”
BackgroundMethodInfluentialHausler, S., Garg, S., Chakravarty, P., Shrivastava, S., Vora, A., & Milford, M. J. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341550 · Cited by 4
“Localization can be divided into coarse localization using GPS or Visual Place Recognition (VPR) [3]–[5] and fine-grained 6-DoF metric localization using techniques based on 3D reconstruction [6] and local feature matching [7].”
MethodSelf-citationCollaborative indoor navigation for emergency services personnel
Morrison, A. J., Sokolova, N., Haavardsholm, T. V., Hagen, O. K., Opsahl, T. O., Ánonsen, K. B., & Eriksen, K. E. H. (2017) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2017.7943729 · Cited by 5
“By detecting loop-closures when revisiting areas using image recognition techniques [22], drift in both the global map and camera trajectories may be reduced, leading to a more consistent global map.”
BackgroundCity-scale continuous visual localization
López-Antequera, M., Petkov, N., & González-Jiménez, J. (2017) · European Conference on Mobile Robots · doi:10.1109/ecmr.2017.8098692 · Cited by 5
“Since it is a thriving research topic, many advances have been made recently [1], however, there are still limitations when dealing with:”
BackgroundVisual place recognition with CNNs: From global to partial
Xin, Z., Cui, X., Zhang, J., Yang, Y., & Wang, Y. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310121 · Cited by 6
“Visual place recognition is the process of identifying images that belong to the same location [18].”
BackgroundInfluentialEfficient construction of topological semantic map with 3D information
Wang, P., Cheng, J. S., & Feng, W. (2018) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-169656 · Cited by 5
“They are both effective cues that might enhance the robustness and reduce the computational complexities for a more intelligent and versatile SLAM algorithm [3, 4].”
Adding Cues to Binary Feature Descriptors for Visual Place Recognition
Schlegel, D., & Grisetti, G. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793753 · Cited by 5
Salient Feature Selection for CNN-Based Visual Place Recognition
Chen, Y., Wenyan, G. A. N., Jiao, S., Xu, Y.-W., & Feng, Y. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edp7175 · Cited by 5
“Visual place recognition is an active research field in the robotic navigation and localization, especially in simultaneous localization and mapping (SLAM), which means the ability to recognize whether current place was visited before by using vision sensors [1].”
BackgroundRobust ConvNet Landmark-Based Visual Place Recognition by Optimizing Landmark Matching
Kong, Y., Liu, W., & Chen, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2901984 · Cited by 7
“For instance, in the loop closure detection of simultaneous localization and mapping [2], additional exact loops will contribute to generate an exact map.”
Bio-inspired multi-scale fusion
Hausler, S., Chen, Z., Hasselmo, M. E., & Milford, M. J. (2020) · Biological Cybernetics · doi:10.1007/s00422-020-00831-z · Cited by 8
“…2012), Gist (Oliva and Torralba 2006), and NetVLAD (Arandjelovic et al. 2018), which collectively span the range of technique types used in the field of robotics (Lowry et al. 2016): a direct image-based approach (SAD), a hand-crafted feature detector (Gist) and a learnt feature detector (NetVLAD).”
BackgroundSelf-citationBrain networks involved in place recognition based on personal and spatial semantics
Beldzik, E., Domagalik, A., Fąfrowicz, M., Ogińska, H., & Marek, T. (2020) · Behavioural Brain Research · doi:10.1016/j.bbr.2020.112976 · Cited by 5
Geocaching-Inspired Navigation for Micro Aerial Vehicles with Fallible Place Recognition
Barbeau, M., García-Alfaro, J., & Evangelos Kranakis, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61746-2_5 · Cited by 5
GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition
Yang, Y., Ma, B., Liu, X., Zhao, L., & Huang, S. (2021) · Remote Sensing · doi:10.3390/rs13081467 · Cited by 7
“There are two main challenges to perform visual place recognition based on the differences of scenes: one is the appearance change caused by illumination condition and seasonal changes, and the other is the viewpoint change caused by revisiting one place from different viewpoints [1].”
BackgroundA Lightweight sequence-based Unsupervised Loop Closure Detection
Xiong, F., Ding, Y., Yu, M., Zhao, W., Zheng, N., & Ren, P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534180 · Cited by 6
“Loop closure detection (LCD) can correct the accumulated errors of SLAM system [1], [2], which makes fast and accurate LCD play an important role in real-time SLAM systems.”
BackgroundLocNet: Global localization in 3D point clouds for mobile robots.Preprint
Yin, H., Wang, Y., Tang, L., Ding, X., & Xiong, R. (2017) · arXiv (Cornell University) · Cited by 8
On Machine Learning and Structure for Mobile RobotsPreprint
Wulfmeier, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.06003 · Cited by 7
“Finally, appearance change in our environment continues to be one of the most challenging aspects for learning as well as geometric approaches [117].”
BackgroundKernel learning for visual perception
Wang, C. (2019) · doi:10.32657/10220/47835 · Cited by 11
Dense Semantic 3D Map Based Long-Term Visual Localization with Hybrid FeaturesPreprint
Shi, T., Cui, H., Song, Z., & Shen, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.10766 · Cited by 11
“This type of approaches [1,26,39,54] solve visual localization as an image retrieval problem.”
BackgroundLocalization of Autonomous Vehicles: Proof of Concept for A Computer Vision ApproachPreprint
Zahedian, S., Sadabadi, K. F., & Nohekhan, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02785 · Cited by 6
“Xk = FkXk−1 + Bkuk + wk−1 (3) yk = HkXk + vk (4)”
BackgroundMethodMulti-Domain Indoor Dataset for Visual Place Recognition and Anomaly Detection by Mobile Robots
Woźniak, P., Krzeszowski, T., & Kwolek, B. (2025) · Scientific Data · doi:10.1038/s41597-025-05124-3 · Cited by 9
Ensemble-Based Event Camera Place Recognition Under Varying Illumination
Joseph, T., Fischer, T., & Milford, M. J. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3641119 · Cited by 5
“Place recognition matches a query to a reference database via feature extraction and similarity search, enabling global re-localisation and loop closure [15], [16], [17], [18], [19], [24].”
Self-citationEfficient Visual Place Recognition Through Multimodal Semantic Knowledge Integration
Zhang, S., Mao, H., Chen, Q., & Kim, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00531 · Cited by 4
“Most early works on VPR employed handcrafted features for matching queries against references in the database [26].”
ZeroSCD: Zero-Shot Street Scene Change Detection
Kannan, S. S., & Min, B.-C. (2024) · IEEE International Conference on Robotics and Automation · doi:10.1109/icra55743.2025.11128082 · Cited by 18
“Detecting these changes related to the roundabout and signs is essential to ensure the map is updated for the safe navigation of autonomous vehicles.”
Sonar-based place recognition using joint sparse coding method
Xiangmei, Z., Liu, H., Sun, F., Gao, M., Li, J., & Zhang, Q. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727701 · Cited by 4
“Although passive vision sensors are very powerful and widely used in mobile robot navigation[3] [15], they cannot work in a dark environment.”
An Approach for Construct Semantic Map with Scene Classification and Object Semantic Segmentation
Wang, P., Cheng, J. T., & Feng, W. (2018) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar.2018.8621769 · Cited by 4
“They are both effective cues that might enhance the robustness and reduce the computational complexities for a more intelligent and versatile SLAM algorithm [3, 4].”
BackgroundTomită, M.-A., Zaffar, M., Ferrarini, B., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2022) · IEEE Access · doi:10.1109/access.2022.3196389 · Cited by 6
“Early techniques used in the field of VPR were based on handcrafted feature descriptors [39], [40] which can be categorised into either local or global feature descriptors depending on how they extract the information from an image [38].”
MethodSelf-citationOkajima, H., Arinaga, K., & Hayashida, A. (2023) · IEEE Access · doi:10.1109/access.2023.3329117 · Cited by 4
“Meanwhile, autonomous robots and self-driving cars have been actively researched, and accurate simultaneous localization and mapping (SLAM) [2], [3], [4] is crucial for their implementation.”
BackgroundNie, J., Xue, D., Pan, F., Ning, Z., Liu, W., da Hu, J., & Cheng, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3399591 · Cited by 6
“Visual Place Recognition (VPR) has emerged as a dynamic field of study, with numerous approaches being developed [15], [34], [35].”
BackgroundHIPer: A Human-Inspired Scene Perception Model for Multifunctional Mobile Robots
Graf, F., Lindermayr, J., Graf, B., Kraus, W., & Huber, M. F. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3420799 · Cited by 4
“Specialized networks also exist for tasks like human skeleton detection, providing joint information [20], [21], or (re)detecting specific places [22].”
BackgroundTS-LCD: Two-Stage Loop-Closure Detection Based on Heterogeneous Data Fusion
Jiang, F., Wang, W., You, H., Jiang, S., Meng, X., Kim, J., & Wang, S. (2024) · Sensors · doi:10.3390/s24123702 · Cited by 4
“References [12–14] offer diverse algorithms for loop detection and location identification, each boasting unique strengths in efficiency, precision, and versatility.”
BackgroundMobile robot localization method based on point-line feature visual-inertial SLAM algorithm
Xu, J., Fang, Y., Gao, W., Liu, X., Shi, J., & Yang, H. (2024) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-08-2024-0381 · Cited by 4
Neighborhood Consensus Guided Matching Based Place Recognition with Spatial-Channel Embedding
Li, K., Zhang, Y., Ning, J., Zhao, X., Wang, G., & Liu, W. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801802 · Cited by 4
“In general, visual place recognition is usually regarded as an image retrieval problem [1][2], that is, given a query image, it needs to find the most similar image from the database for matching.”
BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues
Ge, F., Zhang, Y., Shen, S., Hu, W., Wang, Y., & Gao, J. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802401 · Cited by 5
“Visual Place Recognition (VPR) plays a crucial role in robotics and autonomous driving, typically framed as an image retrieval task [1], [2], [3].”
Unified Depth-Guided Feature Fusion and Reranking for Hierarchical Place Recognition
Li, K., Ou, Y., Ning, J., Kong, F., Cai, H., & Li, H. (2025) · Sensors · doi:10.3390/s25134056 · Cited by 6
“As a fundamental capability for autonomous driving systems, Visual Place Recognition (VPR) has become an increasingly important research focus in recent years [1,2].”
Simultaneous place learning and recognition for real-time appearance-based mapping
Kazmi, S. M. A. M., & Mertsching, B. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759719 · Cited by 4
“A comprehensive survey of place recognition techniques, ranging from purely appearance-based mapping to their integration with geometric information, is provided in [8], [9].”
BackgroundLearning-based scene recognition with monocular camera for light-rail system
Yao, M., Siu, W.-C., & Jia, K. (2018) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses.2018.8349879 · Cited by 4
“Nowadays, visual information plays an important role in localization system and is widely used on vehicles and mobile robots [1-3].”
BackgroundAn improved bag of words method for appearance based visual loop closure detection
Zhu, H., Xie, L., Yu, H., & Liujun, W. (2018) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2018.8408123 · Cited by 5
Bayesian place recognition based on bag of objects for intelligent vehicle localisation
Wang, X., Hu, Z., Tao, Q., Huang, G., & Mu, M. (2019) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5431 · Cited by 4
Visual Place Recognition by DTW-based sequence alignment
Hafez, A. H. A., Tello, A., & Alqaraleh, S. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806363 · Cited by 4
“As shown in [1], the main components of the visual place recognition system are:”
BackgroundMethodInfluentialA sequence-based visual place recognition method for aerial mobile robots
Yang, M., Mao, J., He, X., Zhang, L., & Hu, X. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1654/1/012080 · Cited by 4
“Introduction Visual place recognition (VPR) [1-2] determines whether a query image is taken at a known place in the database; it is widely used in mobile robotics for autonomous positioning.”
BackgroundMOZARD: Multi-Modal Localization for Autonomous Vehicles in Urban Outdoor Environments
Schaupp, L., Pfreundschuh, P., Bürki, M., Cadena, C., Siegwart, R., & Nieto, J. I. (2020) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros45743.2020.9341400 · Cited by 2
“Appearance changes in urban environments challenge visual localization approaches [2].”
BackgroundSequence-based visual place recognition: a scale-space approach for boundary detection
Bampis, L., & Gasteratos, A. C. (2021) · Autonomous Robots · doi:10.1007/s10514-021-09984-7 · Cited by 4
“In this section we provide a brief summary of existing literature regarding vPR, though for an extensive analysis, the reader can refer to the works of Garcia-Fidalgo and Ortiz (2015) and Lowry et al. (2015).”
BackgroundMethodVisual Place Recognition via Local Affine Preserving Matching
Ye, X., & Ma, J. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561709 · Cited by 5
“Although these methods combine CNNs with regional features, they still do not consider the spatial relationship between local features, which is beneficial to improve the robustness of place matching [1].”
BackgroundMethodConvolution-Based Encoding of Depth Images for Transfer Learning in RGB-D Scene Classification
Gopalapillai, R., Gupta, D., Zakariah, M., & Alotaibi, Y. A. (2021) · Sensors · doi:10.3390/s21237950 · Cited by 6
“These features are broadly divided into two categories [14]: local feature descriptors that represent relevant parts of the image and global descriptors that represent the whole image.”
BackgroundSV-Loop:Semantic-Visual Loop Closure Detection with Panoptic Segmentation
Yuan, Z., Xu, K., Deng, B., Zhou, X., Chen, P., & Ma, Y. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688756 · Cited by 4
“Although these algorithms achieve high efficiency and stability in a stable environment, variations of complex senses can cause false judgement [2].”
BackgroundFastFusion: Real-Time Indoor Scene Reconstruction with Fast Sensor Motion
Zhu, Z., Xu, Z., Chen, R., Wang, T., Wang, C., Yan, C. C., & Xu, F. (2022) · Remote Sensing · doi:10.3390/rs14153551 · Cited by 5
Loop-Closure Detection with 3D LiDAR Data for Extreme Viewpoint Changes
Alexiou, D., Tsiakas, K., Kostavelis, I., Giakoumis, D., Gasteratos, A. C., & Tzovaras, D. K. (2022) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar55195.2022.9874344 · Cited by 4
“The first stage in local descriptors-based approach includes the evocation of salient keypoints in the point cloud [27].”
BackgroundMethodChia, T., Zhang, J., Li, H., Peng, G., Wen, M., Kee, D., & Senarathne, P. G. C. N. (2022) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv57592.2022.10004346 · Cited by 4
“note the power of visual place recognition for robot localization, but also describe the many challenges visual cameras face [14], [15].”
BackgroundLi, Y., Wu, W., & Zhu, H. (2023) · Applied Sciences · doi:10.3390/app13116481 · Cited by 4
5G Edge Vision: Wearable Assistive Technology for People with Blindness and Low Vision
Azzino, T., Mezzavilla, M., Rangan, S., Wang, Y., & Rizzo, J. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10570607 · Cited by 5
“UNav relies on visual place recognition [11] where the features of the query image are compared against a library of pre-stored features to locate the user.”
BackgroundConvolutional Autoencoder aided loop closure detection for monocular SLAM
Leonardi, M., & Stahl, A. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.09.486 · Cited by 5
Wang, X., Şekercioğlu, Y. A., Drummond, T. W., Frémont, V., Natalizio, E., & Fantoni, I. (2018) · Sensors · doi:10.3390/s18082430 · Cited by 4
“In these approaches, the location and orientation of the camera sensors are used to establish clusters, and a variety of existing feature detection algorithms [30], [31] or place recognition approaches [15], [32] are used to determine the”
MethodBTEL: A Binary Tree Encoding Approach for Visual Localization
Le, H., Hoang, T., & Milford, M. J. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2932580 · Cited by 5
“In recent years, the use of visual similarity search algorithms has proven to be of significant impact to a large number of works on visual localization for robotics navigation [4] and autonomous driving [2].”
BackgroundSelf-citationDeep learning based glance of real world scenes through decision tree
Pawar, P. A., Devendran, V., & Singh, S. (2019) · International Conference on Advanced Informatics for Computing Research (ICAICR) · doi:10.1145/3339311.3339360 · Cited by 4
“Scenes are composed in multiple parts of objects and objects are intrinsic components of scenes, provides knowledge about both scenes and objects at different scales and also help to improve recognition accuracy [21].”
BackgroundDeep Learning for Visual Indonesian Place Classification with Convolutional Neural Networks
Chowanda, A., & Sutoyo, R. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.08.236 · Cited by 5
SPRINT: Subgraph Place Recognition for INtelligent Transportation
Latif, Y., Doan, A.-D., Chin, T.-J., & Reid, I. D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196522 · Cited by 4
“Place recognition is the problem of localizing a mobile agent using an on-board camera as the sole sensor [2, 12].”
BackgroundReview of Place Recognition Approaches: Traditional and Deep Learning Methods
Taha, M. A., Şah, M., & Direkoğlu, C. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-64058-3_22 · Cited by 4
Interval Inspired Approach Based on Temporal Sequence Constraints to Place Recognition
Neuland, R., Rodrigues, F., Pittol, D., Jaulin, L., Maffei, R. D. Q., Kolberg, M., & Prestes, E. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-021-01375-5 · Cited by 4
“The most common ways to represent a scene are using either a set of local features or the whole image information [18].”
BackgroundInfluentialDeep Next-Best-View Planner for Cross-Season Visual Route Classification
Kurauchi, K., & Kanji, T. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412043 · Cited by 5
“The task of VPR is to classify ego-centric view images into predefined place classes [1].”
MethodLocal map descriptor for compressive change retrieval
Kanji, T. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866648 · Cited by 4
BdFusion: Bi-directional visual-LiDAR fusion for resilient place recognition
Liang, A., Chen, Z., Xiong, W., Meng, F., Yin, Y., Zhang, D., & Li, Q. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.07.022 · Cited by 3
DSFormer: A Dual-Scale Cross-Learning Transformer for Visual Place Recognition
Jiang, H., Piao, S., Gao, C., Yu, L., & Chen, L. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3604761 · Cited by 3
“, viewpoint changes, and perceptual aliasing [1] (where distinct locations exhibit repetitive or structurally similar patterns.)”
Scale, Don’t Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time*
Cheng, J., Li, W., Luo, J., Tang, X., He, Z., Wu, J., Zou, Y., & Zhang, W. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.12.458 · Cited by 10
Lost in the Woods? Place Recognition for Navigation in Difficult Forest Environments
Garforth, J., & Webb, B. H. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.541770 · Cited by 5
“Deep Learning and Place Recognition Image matching is a popular domain for Deep Neural Networks, and when the images being matched against represent locations the task is known as place recognition (Lowry et al., 2015).”
BackgroundPedram, A. R., Funada, R., & Tanaka, T. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683570 · Cited by 3
“We assume that the relative angles between landmarks and the robot are obtained through the computer vision techniques [21] and well-known camera model [22].”
MethodLong-term Visual Place Recognition
Alijani, F., Peltomäki, J., Puura, J., Huttunen, H. J., Kämäräinen, J., & Rahtu, E. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956392 · Cited by 4
“Describing the whole image using a holistic feature, a global descriptor, is more robust against appearance changes than local descriptors [1].”
A Hierarchical Utilization of Semantic Gradients and Scene Structure for Visual Place Recognition
Bao, Y., Pan, Y., Yang, Z., & Huan, R. (2023) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2023.3281870 · Cited by 3
“The research focus has been transferred from local features-based Bag-of-Words [24] and global features-based sequence searching [25] to deep learnt-based robust representations [1], [26].”
BackgroundThe First Experimental Study of Monocular Visual Localization for Train using Deep Learning Method
Wang, Y., Xie, J., Zhang, J., Li, S., Fan, K. B., & Zhang, M. (2023) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis59572.2023.10262972 · Cited by 3
“The problem of localization and mapping has been studied for decades, and various complex models and algorithms are being developed, such as odometry estimation (including visual odometers [2], [3], [4], visual-inertial odometers [5], [6], [7], [8], [9] and LiDAR odometers), image based positioning [10], [11], positio…”
MethodSynthetic Images for Georeferencing Camera Images in Mobile Mapping Point-clouds
Jones, K., Lichti, D. D., & Radovanovic, R. (2024) · Canadian Journal of Remote Sensing · doi:10.1080/07038992.2023.2300328 · Cited by 3
“Lowry et al. (2016) suggests that updating or complementing maps with image sequences may fill map gaps by recognizing the changes from the image sequence, but a single image or image pair is currently unable to fill a map gap.”
Self-Supervised Learning for Place Representation Generalization across Appearance Changes
Musallam, M. A., Gaudillière, V., & Aouada, D. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00728 · Cited by 8
Semantic-focused Patch Tokenizer with Multi-branch Mixer for Visual Place Recognition
Xu, Z., Ren, Z., Zhang, Q., Lou, J., Tao, D., & Cheng, J. S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610372 · Cited by 3
“Based on the geographic labels associated with the best match, the system determines the current position and realizes accurate re-localization [2].”
BackgroundNuRF: Nudging the Particle Filter in Radiance Fields for Robot Visual Localization
Meng, W., Wu, T., Yin, H., & Zhang, F. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3553261 · Cited by 3
“On the other hand, learning-based approaches such as visual place recognition (VPR) [4], [5], [6] can regress or retrieve poses through trained networks from scratch.”
Liang, J., Das, D., Song, D., Shuvo, M. N. H., Durrani, M., Taranath, K., Penskiy, I., Manocha, D., & Xiao, X. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128193 · Cited by 22
“Map-based approaches rely on a comprehensive cost map for path planning [43], [44] and precise robot localization [45], [46] to ensure accurate path execution.”
Liu, Z. B., Li, Y., Hu, C., Kong, D., Jiang, J., & Fang, Z. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3682981 · Cited by 3
“To address these challenges, event cameras have been increasingly adopted in VPR due to their high temporal resolution, high dynamic range, and low latency [7], leading to event-based VPR (EVPR) [8], [9], [10], [11].”
Dynamic Transition Trajectory Planning of Three-DOF Cable-Suspended Parallel Robots
Jiang, X., & Gosselin, C. (2017) · Mechanisms and machine science · doi:10.1007/978-3-319-61431-1_20 · Cited by 3
Dynamic Environments Localization via Dimensions Reduction of Deep Learning Features
Zhang, H., Wang, X., Du, X., Liu, M., & Chen, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68345-4_22 · Cited by 5
“[17] pointed out that the map framework differs depending on visual sensors and what type of place recognition is being performed.”
BackgroundAn Incremental Episodic Memory Framework for Topological Map Building
Chin, W. H., Saputra, A. A., Toda, Y., & Kubota, N. (2018) · International Electronics Symposium (IES) · doi:10.1109/kcic.2018.8628468 · Cited by 3
“The cognitive map is formed by sets of important landmark and contains spatial relationships between generated landmarks in the environment [3], [4].”
Backgroundc-M2DP: A Fast Point Cloud Descriptor with Color Information to Perform Loop Closure Detection
Perdomo, L., Pittol, D., Mantelli, M., Maffei, R. D. Q., Kolberg, M., & Prestes, E. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8842896 · Cited by 3
“While there is a significant amount of visual based methods 16 (CUMMINS; NEWMAN, 2008; SÜNDERHAUF; PROTZEL, 2011; MILFORD; WYETH, 2012; LOWRY et al., 2016; NASEER et al., 2015) exploiting 2D camera features to accomplish loop closure detection, few approaches (BOSSE; ZLOT, 2013; RÖHLING; MACK;…”
BackgroundInfluentialDynamic Time Warping of Deep Features for Place Recognition in Visually Varying Conditions
Alqaraleh, S., Hafez, A. H. A., & Tello, A. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-020-05146-6 · Cited by 3
Modelling Software Architecture for Visual Simultaneous Localization and Mapping
Mishra, B., Griffin, R. J., & Sevil, H. E. (2021) · Automation · doi:10.3390/automation2020003 · Cited by 3
“This can be corrected by detecting constraints from instances of the system coming back to a previously observed location, also known as place recognition [48].”
BackgroundResearch on Loop Closure Detection Method Based on ResNet
Zhang, S., Wang, Z., & Zhu, Q. (2021) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs52002.2021.00055 · Cited by 3
3D solid robot animation design based on ADAMS
Yang, B., Deng, Y., Yue, X., & Teo, K. T. K. (2021) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-021-01280-y · Cited by 3
VGG-CAE: Unsupervised Visual Place Recognition Using VGG16-Based Convolutional Autoencoder
Xu, Z., Zhang, Q., Hao, F., Ren, Z., Kang, Y., & Cheng, J. S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88007-1_8 · Cited by 4
A UAV Visual Relocalization Method Using Semantic Object Features Based on Internet of Things
Wang, M., Wang, H., Wang, Z., & Li, Y. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7299309 · Cited by 3
Visual Place Recognition via Semantic and Geometric Descriptor for Automated Valet Parking
Yu, J., & Su, J. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739413 · Cited by 3
“For a standard AVP task, the intelligent vehicle needs visual place recognition (VPR) [2] to determine its absolute position, especially when it has just entered a parking lot.”
BackgroundApplication of Sparse-Channel Lidar Sensors on Viewpoint-Invariant Loop Closing Task
Cao, F., Wu, H., & Wu, C. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3178392 · Cited by 3
Deep Visual Place Recognition for Waterborne Domains
Thomas, L., Edwards, M., Capsey, A., Rahat, A., & Roach, M. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897962 · Cited by 4
“Place recognition allows autonomous systems to roughly identify locations from nearby landmarks [10].”
BackgroundSO-PFH: Semantic Object-based Point Feature Histogram for Global Localization in Parking Lot
Lv, J., Meng, C., Wang, Y., Sun, J., Xiong, R., & Pu, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981094 · Cited by 4
“Email: wangyue@iipc.zju.edu.cn, rxiong@zju.edu.cn localization methods [1] have been proposed in the past decades.”
Background
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.