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 701–800 of 1,000
Visual SLAM Based on Lightweight SuperPoint Network
Liu, Y., & Li, Z. (2022) · IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · doi:10.1109/iccasit55263.2022.9987187 · Cited by 3
“In the SLAM system, the feature point method is the mainstream method in the frontend, and the relationship between points in the image is usually estimated by feature matching[1].”
MethodRobot Localization Using Situational Graphs (S-Graphs) and Building Architectural Plans
Shaheer, M., Bavle, H., Sánchez-López, J. L., & Voos, H. (2023) · Robotics · doi:10.3390/robotics12030065 · Cited by 12
“This is sometimes called the kidnapped robot prolem [3], re-localization [4], or place recognition [5].”
BackgroundNight-to-day thermal image translation for deep thermal place recognition
Lee, D.-G., Gil, H., Yun, S., Kim, J., & Kim, A. (2023) · Intelligent Service Robotics · doi:10.1007/s11370-023-00473-7 · Cited by 3
“1 Department of Mechanical Engineering, Seoul National University, 1 Gwanak-ro Gwanak-Gu, Seoul 08826, Republic of Korea rent location has been previously visited by the robot [2].”
BackgroundYe, M., & Kanji, T. (2023) · Applied Sciences · doi:10.3390/app13159040 · Cited by 3
Adaptive Soft Encoding: A General Unsupervised Feature Aggregation Method for Place Recognition
Gong, Y., Yuan, J., Sun, F., Sun, Q., Zhu, W., & Zhang, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3307752 · Cited by 3
“[6], and localization of mobile robots [7].”
Overview on Interest Point Detection Over 40 Year’s Development: A Review
Zhou, G., Li, H., & Gao, E. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3318756 · Cited by 3
“I NTEREST points usually include corner points, T-junctions, blobs, and points with significant texture changes [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14].”
BackgroundLearning to Find the Optimal Correspondence Between SAR and Optical Image Patches
Li, H., Xu, F., Yang, W. T., Yu, H., Xiang, Y., Zhang, H., & Xia, G.-S. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3324768 · Cited by 4
Sequential visual place recognition using semantically-enhanced features
Paturkar, V., Yadav, R., & Kala, R. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17404-4 · Cited by 3
“Lowry et al. [14] surveyed the visual place recognition landscape and the significant components of a place recognition system.”
3D Model-Free Visual Localization System From Essential Matrix Under Local Planar Motion
Jiao, Y., Zhang, B., Jiang, P., Wang, C., Lu, H., Xiong, R., & Wang, Y. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3374823 · Cited by 3
Predictive Data Acquisition for Lifelong Visual Teach, Repeat and Learn
Rouček, T., Rozsypálek, Z., Blaha, J., Ulrich, J., & Krajník, T. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3421193 · Cited by 5
“Another approach was to learn feature descriptors that are conditions invariant both indoors and outdoors [8], [9].”
BackgroundWang, Z., Zhang, Y., Zhao, X., Ning, J., Zou, D., & Pei, M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611102 · Cited by 3
“However, VPR remains challenging due to dynamic environmental changes[4][5][6] and annoying perceptual aliasing[7].”
BackgroundRegressing Transformers for Data-efficient Visual Place Recognition
Leyva-Vallina, M., Strisciuglio, N., & Petkov, N. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611288 · Cited by 3
“It is an important component of visual navigation [1], [2] for autonomous driving and robotics [3].”
BackgroundMatched Filtering Based LiDAR Place Recognition for Urban and Natural Environments
Joseph, T., Fischer, T., & Milford, M. J. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3533966 · Cited by 7
“This capability is crucial for several downstream tasks in Simultaneous Localisation and Mapping (SLAM), such as loop closure detection and localisation in GPS-denied environments [1], [2].”
BackgroundSelf-citationPan, T., He, J., Chen, C., Li, Y., & Feng, C. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128789 · Cited by 4
“It plays a pivotal role in tasks like providing loop closure in visual Simultaneous Localization and Mapping (SLAM) systems [1].”
Semantic Signatures for Urban Visual Localization
Weng, L., Soheilian, B., & Gouet-Brunet, V. (2018) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2018.8516492 · Cited by 3
“Visual localization [1], [2] is an alternative to conventional signal-based positioning solutions.”
BackgroundAvoiding to Face the Challenges of Visual Place Recognition
Mihankhah, E., & Wang, D. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01054-6_52 · Cited by 3
“However, mission planning requires general estimation of robot location in the studied environment, which is mostly addressed through place recognition techniques [2].”
BackgroundInfluentialSemantic Localization of a Robot in a Real Home
Cruz, E., Bauer, Z., Rangel, J. C., Cazorla, M., & Gomez‐Donoso, F. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-99885-5_1 · Cited by 3
Three level sequence-based Loop Closure Detection
Rodrigues, F., Neuland, R., Mantelli, M., Pittol, D., Maffei, R. D. Q., Prestes, E., & Kolberg, M. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103620 · Cited by 3
Traffic Intersection Re-Identification Using Monocular Camera Sensors
Xiong, L., Deng, Z., Huang, Y., Du, W., Zhao, X., Lu, C., & Tian, W. (2020) · Sensors · doi:10.3390/s20226515 · Cited by 3
“Compared to simultaneous localization and mapping (SLAM), visual place re-identification [1] is unobligated to save a vast amount of point clouds or visual feature points, and thus is suitable for sparse localization.”
BackgroundPlace recognition with deep superpixel features for brain-inspired navigation
Zhao, J. H., Tang, J., Zhao, D., Cao, H., Liu, X., Shen, C., Wang, C., & Liu, J. (2020) · Review of Scientific Instruments · doi:10.1063/5.0027767 · Cited by 3
Re-localization for Self-Driving Cars using Semantic Maps
Kenye, L., Palugulla, R., Arora, M., Bhat, B., Kala, R., & Nayak, A. (2020) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2020.00018 · Cited by 3
“The visual place recognition techniques [2] identify prominent places and use them to get the pose of the vehicle.”
BackgroundExperimental Analysis of Appearance Maps as Descriptor Manifolds Approximations
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89131-2_10 · Cited by 3
A probabilistic framework for global localization with segmented planes
Wietrzykowski, J., & Skrzypczyński, P. (2017) · European Conference on Mobile Robots · doi:10.1109/ecmr.2017.8098672 · Cited by 3
“In keyframe-based 3-D SLAM systems, large loop closures are detected using appearance-based place recognition techniques [6].”
MethodHHA-based CNN image features for indoor loop closure detection
Zhang, W., Liu, G., & Tian, G. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243597 · Cited by 3
“The visual simultaneous localization and mapping (SLAM) is considered as one of the most critical technologies in autonomous robot research fields, which has been investigated extensively in the past 10 years [1, 2].”
BackgroundEdge-Based Loop Closure Detection in Visual SLAM
Mendieta, D. F., Capua, F. R., Tarrio, J., & Moreyra, M. L. (2018) · Argentine Conference on Automatic Control (AADECA) · doi:10.23919/aadeca.2018.8577273 · Cited by 3
“La variedad de caracterı́sticas para representar una imagen pueden clasificarse en caracterı́sticas locales [12] y globales [13].”
BackgroundOutlier Detection using Hierarchical Spatial Verification for Visual Place Recognition
Yuan, M., Li, Z. G., Wan, K.-W., & Yau, W. (2018) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2018.8581070 · Cited by 3
“In robotics, visual place recognition is an important but challenging task, as the appearance of navigating environments may change drastically [1], [2], [3], [4].”
BackgroundLost Robot Self-Recovery via Exploration Using Hybrid Topological-Metric Maps
Yuan, M., Yau, W., & Li, Z. G. (2018) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2018.8650236 · Cited by 3
“Motivated by the localization and navigation capability of humans or animals, visual information provides appearance cues to re-localize a lost robot [14], [15], [16], [17], [18], [19].”
BackgroundHan, F., Siva, S., & Zhang, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-21565-1_4 · Cited by 3
SIR-Net: Scene-Independent End-to-End Trainable Visual Relocalizer
Nakashima, R., & Seki, A. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00059 · Cited by 3
“In these methods, images similar to the query are first retrieved using global descriptors [2, 10, 20] (image retrieval task), then 2D keypoints in the query image are matched against 3D points visible in the retrieved images using local descriptors.”
MethodFast Loop Closure Detection via Binary Content
Wang, H., Li, J., Ran, M., & Xie, L. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899937 · Cited by 3
“In the back-end, loop closure partially resets localization to minimize transitional measurement error by matching current frame with historical data [2].”
MethodDesign of Obstacle Avoidance Algorithm for Submarine Intelligent Robot
Lu, X., & Liu, D. (2019) · Journal of Coastal Research · doi:10.2112/si97-023.1 · Cited by 3
Niu, J., & Qian, K. (2020) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881420966966 · Cited by 3
“13 Both viewpoint and appearance robustness havebeen demonstrated when CNNs are used for a wide variety of vision jobs like object recognition, 14 object detection, 15 and scene recognition.”
BackgroundSegment-based Cross-domain Localization between Aerial and Ground Robots
Wu, J., Yang, S., & Zhang, Y. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327579 · Cited by 3
“Lowry et al. [2] and Piasco et al. [3] give comprehensive overviews of vision-based place recognition and localization.”
BackgroundWaheed, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981722 · Cited by 12
“Efficiently performing the visual place recognition task is a major challenge in the field of robotics [1].”
BackgroundSelf-citationCNN Feature boosted SeqSLAM for Real-Time Loop Closure DetectionPreprint
Bai, D., Wang, C., Zhang, B., Yi, X., & Yang, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.05016 · Cited by 3
“Recently, convolutional neural networks (CNN) has been achieved great success[4][5] and received much interest in applying CNN features to robotic fields[6][7][8][9].”
BackgroundSparse Optimization for Robust and Efficient Loop ClosingPreprint
Latif, Y., Huang, G. P., Leonard, J. J., & Neira, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.08921 · Cited by 3
“, see [30, 13, 21]), a vast majority of existing algorithms typically require the offline training of visual words (dictionary) from a priori images that are acquired previously in visually similar environments.”
BackgroundSelf-citationKhaliq, A., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.08153 · Cited by 11
“Under significant visual changes experienced in day-night and summer-winter transitions, successful VPR employing image retrieval techniques quite hard to achieve [1].”
Self-citationSequential Place Learning: Heuristic-Free High-Performance Long-Term Place RecognitionPreprint
Chancán, M., & Milford, M. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02074 · Cited by 6
“The success of these multi-frame filtering methods primarily rely on leveraging temporal information— explicitly found in image sequences recorded from large outdoor real environments—for reducing high false-positive rates typically found in sequence-based place recognition tasks due to perceptual aliasing and environ…”
Self-citationMining Minimal Map-Segments for Visual Place ClassifiersPreprint
Kanji, T. (2019) · doi:10.31224/osf.io/v74eq · Cited by 3
Bredu, J. A. (2022) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.11495 · Cited by 3
Sensors and Data in Mobile Robotics for Localisation
Hodge, J. (2023) · IGI Global eBooks · doi:10.4018/978-1-7998-9220-5.ch133 · Cited by 3
VoxelPlane-Reloc: an indoor scene voxel plane relocalization algorithm
Suo, L., Wang, B., Huang, L., Xu, Y., Zhang, Q., & Ma, Y. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01357-8 · Cited by 2
“Relocalization, also referred to as scene recognition, is a vital component in simultaneous localization and mapping(SLAM) [1, 2].”
Liu, S., Huang, C., & Huang, H. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3582814 · Cited by 5
“Scene recognition (SR), which involves labeling scenes, has thus become a major research focus in both computer vision [9], [10] and robotics [11], [12], [13], [14], [15].”
Local Maps Are All You Need: A Review of Topometric Teach and Repeat Navigation
Krawciw, A., & Barfoot, T. D. (2025) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-032724-020548 · Cited by 2
MM-Geo: Multi-Scale and Multi-Positive UAV-View Geo-Localization
Ai, P., Zhang, X., Cheng, S., Huang, P., Liu, J., Zhai, F., Mao, Y., & Huang, G. P. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11245896 · Cited by 2
Spatial Graph Attentional Network Based Place Recognition with Visual Mamba Embedding
Li, K., Ou, Y., Cai, H., Ning, J., & Qi, M. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247468 · Cited by 2
“In most implementations, VPR is formulated as an image retrieval problem [1][2][3], where the system must retrieve the most relevant database image corresponding to a query input.”
Visual SLAM in the era of heterogeneous intelligence coexistence: A survey
Su, S., He, X., Meng, X., Zhang, Y., Yin, W., Mo, L., & Yu, F. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132458 · Cited by 4
Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes
Chen, C., Dang, N., Zhang, J., Sun, W., Zheng, P., He, X., Ye, Y., Zhang, J., Srinivas, T., & Feng, C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00504 · Cited by 3
Hwang, H., Yang, S., Monon, J. S., Giudice, N. A., Lee, S. I., Biswas, J., & Kim, D. (2026) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3757279.3785625 · Cited by 8
“To improve robustness, we follow prior work [7, 66] by using visual place recognition (VPR) embeddings [1, 48] instead of raw pixel matching [13].”
InfluentialEfficiently closing loops in LiDAR-based SLAM using point cloud density maps
Gupta, S., Guadagnino, T., Mersch, B., Trekel, N., Malladi, M. V. R., & Stachniss, C. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261449269 · Cited by 7
“Performance across all baselines is comparable in less challenging urban scenarios, such as the KAIST01 and River-side01 sequences from the MulRan dataset.”
Environment characterization using Laplace eigenvalues
Mihankhah, E., & Wang, D. (2016) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2016.7838769 · Cited by 2
“Knowing the type of objects in a scene can limit the guesses for the place (finding a car can eliminate possibility of robot being in the kitchen), and knowing the place can limit the expected objects in the environment [5] (knowing the robot is in the kitchen, car is not expected to be found).”
Non-metric Constraints in the Graph-Based Optimization for Personal Indoor Localization
Nowicki, M. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00571 · Cited by 2
“The non-metric information is also obtained from loop closure systems that determine the similar localization using the appearance of RGB images [8].”
MethodBoosting the Performance of Scene Recognition via Offline Feature-Shifts and Search Window Weights
Li, C.-T., Siu, W.-C., & Lun, D. P.-K. (2018) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2018.8631883 · Cited by 2
“In conventional feature-based matching procedures [5, 18], we match a feature in a query frame by building a search window and search for the location which gives the highest similarity between features.”
MethodDevelopment of a semantic scene conversion model for image-based localization at night
Kim, D., Shin, S., Park, J., & Shin, S. Y. (2019) · ACM Conference on Research in Adaptive and Convergent Systems (RACS) · doi:10.1145/3338840.3355676 · Cited by 2
Visual Topological Mapping Using an Appearance-Based Location Selection Method
Khan, M. A., & Labrosse, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63486-5_12 · Cited by 2
Yan, Y., Yang, H., Hu, T., Yu, H., & Lai, F. (2021) · SAE International Journal of Advances and Current Practices in Mobility · doi:10.4271/2021-01-0077 · Cited by 2
A Semantic-Based Loop Closure Detection of 3D Point Cloud
Fan, Y., Yuan, H., Zhu, S., Zhou, G., Du, R., & Gu, J. J. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739592 · Cited by 2
Lousada, S. (2020) · IntechOpen eBooks · doi:10.5772/intechopen.83282 · Cited by 2
An efficient loop closure detection method based on spatially constrained feature matching
Zhang, H., Zhao, T., Zhong, Y., Yin, Y., Yuan, H., & Dian, S. (2022) · Intelligent Service Robotics · doi:10.1007/s11370-022-00423-9 · Cited by 2
“For example, in the matching of streetlights on different roads at night, there should be an obvious spatial position relationship between different streetlights in the images taken normally [16], but they may be mistaken as the same feature owing to their great similarity, leading to perceptual aliasing.”
BackgroundInfluentialA Object-augmented Semantic Mapping System for Indoor Mobile Robots
Song, X., Liang, X., Zuo, Z., & Huaidong, Z. (2022) · IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) · doi:10.1109/seai55746.2022.9832075 · Cited by 2
Visual and Positioning Information Fusion Towards Urban Place Recognition
Hettiarachchi, D., & Kamijo, S. (2022) · SN Computer Science · doi:10.1007/s42979-022-01472-8 · Cited by 2
“2 Proposed system is defined according to the schematic VPR system architecture [21].”
BackgroundMethodInfluentialWang, X., Zhu, X., Yan, Z., Ye, Z., Jiangyi, D., Guo, F., Xu, Z., Liu, C., & Mao, C. (2023) · The Visual Computer · doi:10.1007/s00371-023-02838-6 · Cited by 2
“Therefore, visual-based place recognition is widely used in underground parking lots [13].”
Toward Precise Ambiguity-Aware Cross-Modality Global Self-Localization
Stannartz, N., Schütte, S., Kühn, M., & Bertram, T. (2023) · IEEE Access · doi:10.1109/access.2023.3286310 · Cited by 2
“nition (PR) [9], [10], [11] and precise local pose track-”
BackgroundDonadi, I., Olivastri, E., Fusaro, D., Li, W., Evangelista, D., & Pretto, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44137-0_28 · Cited by 2
Active Semantic Localization with Graph Neural Embedding
Yoshida, M., Tanaka, K., Yamamoto, R., & Iwata, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47634-1_17 · Cited by 2
Semantic-based visual vocabulary for loop closure detection
Papapetros, I. T., Oikonomou, K. M., Kansizoglou, I., Tsintotas, K. A., & Gasteratos, A. C. (2023) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist59124.2023.10355694 · Cited by 2
“Finding associations among two observations in not a trivial task [14].”
BackgroundSimultaneous Localization and Mapping of a Mobile Robot With Stereo Camera Using ORB Features
Raoui, Y., & Amraoui, M. (2024) · Journal of Automation Mobile Robotics & Intelligent Systems · doi:10.14313/jamris/2-2024/14 · Cited by 2
“The survey in [14] [13] presented several meth‐ ods for Visual Place Recognition (VPR) and how it is shaped by the recent advances in deep learning.”
BackgroundVDNA-PR: Using General Dataset Representations for Robust Sequential Visual Place Recognition
Ramtoula, B., Martini, D. D., Gadd, M., & Newman, P. M. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611379 · Cited by 2
“VPR is classically set as an image retrieval problem; given a query image and a reference database, its closeness in geometric space to any image in the database is directly related to a similarity measure in an embedding space [1], extracted either from local or global features within the image.”
BackgroundSelf-citationAutomatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor
Huang, Y., Hassan, M. A., He, J., HIGGINS, J. A., McCrory, M. A., Eicher‐Miller, H. A., Thomas, J. G., Sazonov, E. E., & Zhu, F. M. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00372 · Cited by 3
“Multiple computer vision/early deep learning algorithms re-lated to environment recognition were reviewed in [38].”
BackgroundLubanco, D. L. S., Hashem, A., Pichler, M., Schlechter, T., Feger, R., & Stelzer, A. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3517880 · Cited by 2
“Place recognition algorithms are usually evaluated by observing their performance in terms of precision, recall and balanced f-score [37], the latter denoted by f 1 score .”
LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition
Akcal, M. U., Raikov, I., Gribkova, E., Choudhuri, A., Kim, S. H., Gazzola, M., Gillette, R., Soltész, I., & Chowdhary, G. V. (2025) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1490267 · Cited by 2
“Yet, still the global descriptors are reported to be more effective in the case of varying lighting conditions[44].”
NeRF-Supervised Feature Point Detection and Description
Youssef, A., & Vasconcelos, F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91989-3_7 · Cited by 2
Robust visual place recognition with adaptive deformable token aggregation
Wang, C., Li, Y., Min, S., & Chen, X. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104342 · Cited by 2
RE-TRIP: Reflectivity Instance Augmented Triangle Descriptor for 3D Place Recognition
Park, Y., Pak, G., & Kim, E. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128417 · Cited by 2
“Traditionally, visual sensors have been primarily used to solve this problem [7], [8], [9], [10].”
A Robust Approach for Monocular Visual Odometry in Underwater Environments
Jordán, M. A., Trabes, E., & Delrieux, C. A. (2019) · Conicet · Cited by 2
SEER: Unsupervised and sample-efficient environment specialization of image descriptors
Neubert, P., & Schubert, S. (2022) · Robotics: Science and Systems · doi:10.15607/rss.2022.xviii.006 · Cited by 3
“An overview of existing methods was given by Lowry et al. [21] in 2016.”
MethodFrequency map enhancement: introducing dynamics into static environment models
Krajník, T., Fentanes, J. P., Santos, J. P. S. S., & Duckett, T. (2016) · Lincoln Repository (University of Lincoln) · Cited by 4
Visual place recognition techniques for pose estimation in changing environments
Lowry, S. M., & Andreasson, H. (2016) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 2
Self-citationA Two-Layered Pipeline for Topological Place Recognition Based on Topic Model
Dong, X., Yuan, J., Sun, F., & Huang, Y. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7305-2_37 · Cited by 2
Region-Based Epipolar and Planar Geometry Estimation in Low─Textured Environments
Gaudillière, V., Simon, G., & Berger, M. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451244 · Cited by 2
“Indeed, appropriatelydesigned descriptors of subimages can offer the advantage of being robust to both viewpoint changes (as local descriptors) and condition changes (as global descriptors) [18].”
Visual Localization in Changing Environments using Place Recognition Techniques
Xin, Z., Cai, Y., Cai, S., Zhang, J., Yang, Y., & Wang, Y. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545833 · Cited by 2
“However, matching based on low-level features is not robust against appearance changes [11].”
BackgroundTransforming multiple visual surveys of a natural environment into time-lapses
Griffith, S., Dellaert, F., & Pradalier, C. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919881205 · Cited by 2
“Methods towards robust visual data association in outdoor environments have overcome variation in appearance in many ways (Lowry et al. 2016).”
BackgroundSpatial Pyramid Pooling based Convolutional Autoencoder Network for Loop Closure Detection
Xiang, R., Liu, Y., Zhang, Q., & Cheng, J. T. (2019) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar47638.2019.9044155 · Cited by 2
“Loop closure detection is a crucial module in SLAM, which has been studied extensively in the past ten years [1], [2].”
BackgroundMulti-granularity environment perception based on octree occupancy grid
ZHANG, G., Wu, B., Xu, Y., & Ye, Y.-D. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09302-w · Cited by 2
“It only accepts adding up new points but not deleting expired points and provides no means of fusing multiple measurements [18].”
BackgroundWietrzykowski, J., & Skrzypczyński, P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197215 · Cited by 2
“On the other hand, visual place recognition (VPR), which is commonly used for mobile robots [11], is less demanding as to the computer power, especially if the efficient binary-feature-based encoding is used for images [12] or their sequences [13].”
BackgroundLandmark Segmentation and Selective Feature Extraction in Street-View Image
Vilera, R., Rachmadi, R. F., & Yuniarno, E. M. (2020) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim51130.2020.9298008 · Cited by 2
“One of the main group of techniques for describing places using visual data is based on local feature descriptors [6].”
MethodMetric learning with generator for closed loop detection in VSLAM
Chang, J., Dong, N., Li, D., Ip, W. H., & Yung, K. L. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-020-01067-7 · Cited by 2
Improved Visual Localization via Graph Filtering
Lassance, C., Latif, Y., Garg, R., Gripon, V., & Reid, I. D. (2021) · Journal of Imaging · doi:10.3390/jimaging7020020 · Cited by 7
“Related Work Visual localization is a well studied problem in the vision community and recent surveys can be found in [1,9].”
BackgroundCertainty Aware Global Localisation Using 3D Point Correspondences
Steiner, R., Cox, M., Borges, P., Bernreiter, L., & Nieto, J. I. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3114956 · Cited by 2
Region Recognition Based on HMM Using Primitive Motion Transitions
Neto, R. P. B., Ohno, K., Kojima, S., & Tadokoro, S. (2021) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc48978.2021.9564906 · Cited by 2
Visual place representation and recognition from depth images
Ibelaiden, F., & Larabi, S. (2022) · Optik · doi:10.1016/j.ijleo.2022.169109 · Cited by 2
“The permanent changes of scenes induce the scene descriptors modification and lead to a state of the art localization system failure [3].”
BackgroundLi, K., Wang, X., Shi, L., & Geng, N. (2023) · IEEE Access · doi:10.1109/access.2023.3246803 · Cited by 3
“The core need of an appearance-based VPR system is to describe places accurately and effectively, and this requirement has spawned many methods [2], [21], which can be generally categorized into local, global, and local-region-descriptor-based approaches.”
BackgroundOn the Study of Data Augmentation for Visual Place Recognition
Jang, S., & Kim, U.-H. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3301778 · Cited by 2
“These challenges stem primarily from the complexity of the scene and the ever-changing nature of the environment [13].”
BackgroundSequential Monte Carlo localization in topometric appearance maps
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231197723 · Cited by 4
“The most simplistic approach for addressing AbL is Visual Place Recognition (Lowry et al. 2015), a technique that, instead of estimating the query pose, assigns it the pose of the most similar element in the AM.”
BackgroundMethodEquilibrium Conformation of Concentric-Tube Robots Under Loads Based on the Minimum Energy Principle
Huang, L., He, C., Yang, Y., & Guang, C. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-2875-5_18 · Cited by 2
Pose Tracking in Augmented Reality of Cultural Heritage
Asmar, D. (2017) · International Journal of Computational Methods in Heritage Science · doi:10.4018/ijcmhs.2017010108 · Cited by 2
Visual Tilt Estimation for Planar-Motion Methods in Indoor Mobile Robots
Fleer, D. (2017) · Robotics · doi:10.3390/robotics6040032 · Cited by 2
“These include relative-pose estimation [1], visual odometry [2,3], place recognition [4], and simultaneous localization and mapping (SLAM) [5].”
BackgroundAppearance-Based Along-Route Localization for Planetary Missions
Grixa, I., Schulz, P., Stürzl, W., & Triebel, R. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594518 · Cited by 2
“recognition methods, see [15].”
How to add new knowledge to already trained deep learning models applied to semantic localization
Cruz, E., Rangel, J. C., Gomez‐Donoso, F., & Cazorla, M. (2019) · Applied Intelligence · doi:10.1007/s10489-019-01517-1 · Cited by 2
Metode Pengenalan Tempat Secara Visual Berbasis Fitur CNN untuk Navigasi Robot di Dalam Gedung
Afrisal, H. (2019) · Jurnal Teknologi dan Sistem Komputer · doi:10.14710/jtsiskom.7.2.2019.47-55 · Cited by 3
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.