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 501–600 of 1,000
Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud
Ding, X., Xu, X., Lu, S., Jiao, Y., Tan, M., Xiong, R., Deng, H., Li, M., & Wang, Y. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811750 · Cited by 8
Robustness in bio‐inspired visually guided multi‐agent flight and the gain modulation hypothesis
Billah, M. A., & Faruque, I. (2022) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.6442 · Cited by 7
Place Recognition with Memorable and Stable Cues for Loop Closure of Visual SLAM Systems
Islam, R., & Habibullah, H. (2022) · Robotics · doi:10.3390/robotics11060142 · Cited by 9
Tree-based indexing for real-time ConvNet landmark-based visual place recognition
Hou, Y., Zhang, H., & Zhou, S. (2017) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881416686951 · Cited by 8
“Although these two descriptor categories have achieved tremendous success, each has its own disadvantages, as have been identified in the literature.(1,2) Thanks to the invariance properties of local descriptors, local descriptor-based approaches are usually more robust to occlusions and viewpoint change.”
BackgroundPlace Recognition in Gardens by Learning Visual Representations: Data Set and Benchmark Analysis
Leyva-Vallina, M., Strisciuglio, N., & Petkov, N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29888-3_26 · Cited by 11
Lee, S. J., & Hwang, S. S. (2019) · International Journal of Control Automation and Systems · doi:10.1007/s12555-018-0790-6 · Cited by 8
Communication constrained cloud-based long-term visual localization in real time
Ding, X., Wang, Y., Tang, L., Yin, H., & Xiong, R. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968550 · Cited by 8
“In [8, 21], they try to find the topological localization through place recognition and give satisfactory performance.”
BackgroundLocalising PMDs through CNN Based Perception of Urban Streets
Jayasuriya, M., Arukgoda, J., Ranasinghe, R., & Dissanayake, G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196639 · Cited by 6
“The visual processing front-end of most state of the art vision based techniques use feature detectors and descriptors such as FAST, SIFT, SURF, ORB and BRIEF [9][10].”
BackgroundMethodBeyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition
Schubert, S., Neubert, P., & Protzel, P. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561006 · Cited by 10
“A more detailed introduction and an overview over existing methods is given in a survey from 2016 [1].”
MethodA Semantically Aware Place Recognition System for Loop Closure of a Visual SLAM System
Islam, R., & Habibullah, H. (2021) · International Conference on Mechatronics, Robotics and Automation (ICMRA) · doi:10.1109/icmra53481.2021.9675715 · Cited by 8
Feature matching for texture-less endoscopy images via superpixel vector field consistency
Liu, S., Fan, J., Ai, D., Song, H., Fu, T., Wang, Y., & Yang, J. (2022) · Biomedical Optics Express · doi:10.1364/boe.450259 · Cited by 8
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationPreprint
Chancán, M., & Milford, M. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00667 · Cited by 10
“These two approaches often first require computing image descriptors using diverse hand-crafted- [64] or deep-learningbased models [65]–[67].”
BackgroundSelf-citationCamera-LiDAR Fusion With Latent Correlation for Cross-Scene Place Recognition
Pan, Y., Xie, J., Wu, J., & Zhou, B. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3440470 · Cited by 11
PRGS: Patch-to-Region Graph Search for Visual Place Recognition
Zuo, W., Liu, L., Li, Y., Shen, Y., Xiang, F., Xin, J., & Zheng, N. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111673 · Cited by 7
SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition
Lu, F., Jin, T., Lan, X., Zhang, L., Liu, Y., Wang, Y., & Yuan, C. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3629287 · Cited by 27
“The main challenges of the VPR task include condition (e.g., illumination and weather) changes, viewpoint changes, and perceptual aliasing [5] (hard to differentiate similar images from different places).”
State Observer Under Multi-Rate Sensing Environment and Its Design Using l2-Induced Norm
Okajima, H., Hosoe, Y., & Hagiwara, T. (2023) · IEEE Access · doi:10.1109/access.2023.3249187 · Cited by 8
“In recent years, autonomous robots and automatic driving have been actively studied, and precision of the simultaneous localization and mapping (SLAM) [8], [9] is essential for their realization.”
BackgroundInfluentialEvaluation of Global Descriptor Methods for Appearance-Based Visual Place Recognition
Li, K., Ma, Y., Wang, X., Ji, L., & Geng, N. (2023) · Journal of Robotics · doi:10.1155/2023/9150357 · Cited by 9
NeoSLAM: Long-Term SLAM Using Computational Models of the Brain
Pizzino, C. A. P., Costa, R. R., Mitchell, D., & Vargas, P. A. (2024) · Sensors · doi:10.3390/s24041143 · Cited by 7
“By definition, a VPR system must be able to recognize a previously visited place via visual information [9].”
BackgroundXu, H., Liu, H., Meng, S., & Sun, Y. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421887 · Cited by 7
“I. 2) Metrics: We adopt three metrics for evaluation, namely precision-recall curve [1], maximum F 1 score [25] and recall@ N [7].”
BackgroundMethodShape BoW: Generalized Bag of Words for Appearance-Based Loop Closure Detection in Bathymetric SLAM
Zhang, Q., & Kim, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3426370 · Cited by 7
“While such methods are prevalent in visual SLAM (detailed in [16], [17]), their successful adaptation to bathymetric SLAM remains limited.”
MethodMS-NetVLAD: Multi-Scale NetVLAD for Visual Place Recognition
Uggi, A., & Channappayya, S. S. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3425279 · Cited by 7
“VPR has gained widespread attention from the vision community, particularly in robotics [1], [2], [3], [4].”
BackgroundExplicit Interaction for Fusion-Based Place Recognition
Xu, J., Ma, J., Wu, Q., Zhou, Z., Wang, Y., Chen, X., Yu, W., & Pei, L. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802665 · Cited by 7
“The rapid development of place recognition have been comprehensively documented in surveys over the years [23]– [25].”
TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments
Hossain, J., Faridee, A. Z. M., Roy, N., Freeman, J., Gregory, T., & Trout, T. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802380 · Cited by 15
“They often struggle to adapt to dynamic and unstructured environments, where the appearance of landmarks may change significantly over time.”
Shen, Y., Zhou, S., Fu, J., Wang, R., Chen, S., & Zheng, N. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3556859 · Cited by 13
Experimental evaluation of visual place recognition algorithms for personal indoor localization
Nowicki, M., Wietrzykowski, J., & Skrzypczyński, P. (2016) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2016.7743649 · Cited by 7
“Another class of vision-based navigation algorithms are those that, given an image of a place, can tell whether or not this image is of a place that was already seen by the system [13].”
BackgroundPHROG: A Multimodal Feature for Place Recognition
Bonardi, F., Aïnouz, S., Boutteau, R., Dupuis, Y., Savatier, X., & Vasseur, P. (2017) · Sensors · doi:10.3390/s17051167 · Cited by 7
“The survey [2] gives details on maps and decision processes used in SLAM.”
BackgroundMethodA Node-Based Method for SLAM Navigation in Self-Similar Underwater Environments: A Case Study
Trabes, E., & Jordán, M. A. (2017) · Robotics · doi:10.3390/robotics6040029 · Cited by 7
MASAT: A fast and robust algorithm for pose-graph initialization
Harsányi, K., Kiss, A., Szirányi, T., & Majdik, A. L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.11.010 · Cited by 7
“The measurements can originate either from ego-motion estimation odometry or from detecting loop-closure situations whenever the robot returns to a previously visited place [4] .”
Towards Simulating Semantic Onboard UAV Navigation
Mandel, N., Vanegas, F., Milford, M. J., & Gonzalez, F. (2020) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero47225.2020.9172771 · Cited by 7
“The algorithms hold the potential to be human-centric, robust, scalable and could impose fewer requirements on memory [13].”
BackgroundSelf-citationVisual Sequence Place Recognition with Improved Dynamic Time Warping
Lu, F. H., Chen, B., Guo, Z., & Zhou, X. (2019) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00145 · Cited by 7
“Second, it must return a belief about whether or not the current visual information is from a place already included in the map, and if so, which one [2].”
BackgroundCao, W., Huang, X., & Shu, F. (2020) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/0954407020957768 · Cited by 7
CityLearn: Diverse Real-World Environments for Sample-Efficient Navigation Policy Learning
Chancán, M., & Milford, M. J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197336 · Cited by 8
Self-citationVisual Place Recognition From Eye Reflection
Ohshima, Y., Maeda, K., Edamoto, Y., & Nakazawa, A. (2021) · IEEE Access · doi:10.1109/access.2021.3071406 · Cited by 9
“Place recognition from an image is a task to find the location similar to the query image from a dataset of place images [21], [22].”
BackgroundSuperPlane: 3D Plane Detection and Description from a Single Image
Ye, W., Li, H., Zhang, T., Zhou, X., Bao, H., & Zhang, G. (2021) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr50410.2021.00042 · Cited by 7
“Finding the correspondence between different views is a key problem in 3D vision tasks such as augmented reality (AR) applications [2–4, 38] and image-based localization (IBL) task [7, 22, 31, 32, 34].”
BackgroundA Bio-Inspired Multi-Sensor System for Robust Orientation and Position Estimation
Xie, J., He, X., Mao, J., Zhang, L., Guo-liang, H., Zhou, W., & Hu, X. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635932 · Cited by 7
“Place recognition [25] is used to identify the scene that has been visited which is the basis of closed-loop or map fusion.”
BackgroundCarson, H., Ford, J., & Milford, M. J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160679 · Cited by 7
“This match however can be incorrect due to visual aliasing, changes in the environment, dynamic agents, lighting differences and shadows, and many other issues that cause images taken at the same place to look different, and different places to look the same [1].”
BackgroundInfluentialSelf-citationSequential appearance-based Global Localization using an ensemble of kNN-DTW classifiers
Forechi, A., Souza, A. F. D., Badue, C. S., & Oliveira-Santos, T. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727550 · Cited by 7
“update an internal representation of these places, and (iii) predict their locations based on upcoming images and, optionally, some temporal information [6].”
BackgroundCheng, H.-M., Song, D., Angert, A., Li, B., & Yi, J. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2891488 · Cited by 7
Shin, D.-W., Ho, Y., & Kim, E.-S. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.1.013014 · Cited by 8
“When we describe place images in terms of the place recognition problem, there are two main categories: local feature-based method and whole image descriptor-based method.(11) The local feature descriptorbased method represents the image by collecting local image features using scale invariant feature transform (SIFT)…”
MethodCompressed Holistic Convolutional Neural Network-based Descriptors for Scene Recognition
Wang, S., Lv, X., Ye, D., & Li, B. (2019) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae48301.2019.9043837 · Cited by 7
“As one of the most important parts of the SLAM simultaneous localization and mapping (SLAM) system, scene recognition aims to determine whether a mobile robot has returned to previously visited places [1].”
BackgroundResolving Place Recognition Inconsistencies Using Intra-Set Similarities
Neubert, P., Schubert, S., & Protzel, P. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3060729 · Cited by 8
“Place recognition is a well studied problem, please refer to [10] for an overview.”
BackgroundJaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2021) · Sensors · doi:10.3390/s21072483 · Cited by 8
“In addition, these descriptors have proven to more sensitively reflect pose fluctuations than local features [26], which is described, for example, by the equivariance property [27,28].”
BackgroundA Flexible and Efficient Loop Closure Detection Based on Motion Knowledge
Liu, B., Tang, F., Fu, Y., Yang, Y., & Wu, Y. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561126 · Cited by 7
“Visual loop closure detection (LCD) is a recognized solution to this problem, which can be considered as an on-line image retrieval problem that matches the scene in the current location with previously visited locations [4].”
BackgroundTowards accurate building recognition using convolutional neural networks
Farfan, J., Enciso-Rodas, L., & Vargas-Muñoz, J. E. (2017) · IEEE International Conference on Electronics, Electrical Engineering and Computing (INTERCON) · doi:10.1109/intercon.2017.8079686 · Cited by 7
“Other methods use the bag-of-words technique (BOW) to obtain a middle-level representation of the image and afterward perform classification [5], [3].”
MethodSelf-Supervised Visual Place Recognition Learning in Mobile RobotsPreprint
Pillai, S., & Leonard, J. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04453 · Cited by 7
“Place recognition for mobile robots is a long-studied topic [23] due to the far-reaching impact it will have in enabling fully-autonomous systems in the near future.”
BackgroundMethodSelf-citationArshad, S., & Park, T.-H. (2024) · Sensors · doi:10.3390/s24030906 · Cited by 6
“The primary objective of VPR is to ascertain whether the visual data currently captured by the robot correspond to a place it has visited before, and if so, to precisely identify which place it is [1].”
BackgroundAdaptive Route Memory Sequences for Insect-Inspired Visual Route Navigation
Kagioulis, E., Knight, J. C., Graham, P., Nowotny, T., & Philippides, A. O. (2024) · Biomimetics · doi:10.3390/biomimetics9120731 · Cited by 6
Localization Meets Uncertainty: Uncertainty-Aware Multi-Modal Localization
Won, H.-M., Lee, J., & Oh, J. (2025) · Technologies · doi:10.3390/technologies13090386 · Cited by 6
Research on 6-DOF robot inverse kinematics based on blended optimization algorithm of ELM- SSA-SCA
Li, G., Cui, Y., Wang, L., & Meng, L. (2022) · Advances in Mechanical Engineering · doi:10.1177/16878132221113419 · Cited by 6
“Ten point locations within the accessible spaces of industrial robots were selected randomly, and the geodetic coordinate system was used as the standard to record the Cartesian coordinates corresponding to these point locations.(17) The blended optimization algorithm (ELM-SSA-SCA) proposed in this study was used to c…”
MethodXu, S., Zuo, Z., Liang, X., & Huaidong, Z. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14796-1 · Cited by 7
“This kind of skill is not provided by the geometric metric map [14, 37].”
BackgroundRostkowska, M., & Skrzypczyński, P. (2023) · Sensors · doi:10.3390/s23146485 · Cited by 7
“Although appearance-based localization does not provide an accurate metric position of the robot in a global reference system, the ability to tell if the robot is close to one of the known locations is often sufficient for indoor navigation [10].”
BackgroundMethodInfluentialSun, Y., Ma, Z., Zhou, M., & Cao, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3326167 · Cited by 8
“Its use can also reduce the burden of storing much map data and improve the efficiency of navigation [7], [8].”
BackgroundIS-CAT: Intensity–Spatial Cross-Attention Transformer for LiDAR-Based Place Recognition
Joo, H.-J., & Kim, J. (2024) · Sensors · doi:10.3390/s24020582 · Cited by 7
“Camera-based visual place recognition methods [1–4] are advantageous due to their ability to utilize detailed visual information for specific place recognition and cost-effective implementation.”
BackgroundSurvey of Deep Learning-Based Methods for FMCW Radar Odometry and Ego-Localization
Brune, M., Meisen, T., & Pomp, A. (2024) · Applied Sciences · doi:10.3390/app14062267 · Cited by 9
Chen, C., Cheng, Z., Liu, X., Li, Y., Ding, L., Wang, R., & Feng, C. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3495584 · Cited by 12
“VPR evaluation: There are several evaluation metrics for visual place recognition, e.g. , the popular AUC-PR [44] provides a good overview of precision and recall performance but is less indicative in the cases when ground truth match could take multiple values.”
Hierarchically self-organizing visual place memory
Erkent, Ö., Karaoğuz, H., & Bozma, H. I. (2017) · Advanced Robotics · doi:10.1080/01691864.2017.1356746 · Cited by 7
“…places and appearances is not perfect in either direction due to indiscriminate boundaries, appearance variability and perceptual aliasing – as addressed extensively by the excellent work on visual place recognition where a variety of representation and learning schemes have been developed [4,5].”
BackgroundAn adaptive localization system for image storage and localization latency requirements
Mao, J., Hu, X., & Milford, M. J. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.06.007 · Cited by 6
“Vision-based or visual place recognition techniques require a geo-referenced image database described by visual features [17].”
BackgroundSelf-citationRamtoula, B., de Azambuja, R., & Beltrame, G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197270 · Cited by 6
“A major part of a visual place recognition module is the description of a place [12].”
BackgroundLPD-AE: Latent Space Representation of Large-Scale 3D Point Cloud
Suo, C., Liu, Z., Mo, L., & Liu, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2999727 · Cited by 6
“Given a query pictures or point clouds, the best match is retrieved in the database according to the descriptor generated by place recognition methods [3], [4], [39]–[41].”
MethodTwo-Stage vSLAM Loop Closure Detection Based on Sequence Node Matching and Semi-Semantic Autoencoder
Wang, Z., Peng, Z., Guan, Y. L., & Wu, L. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01302-0 · Cited by 7
Variational Bayesian Approach to Condition-Invariant Feature Extraction for Visual Place Recognition
Oh, J., & Eoh, G. (2021) · Applied Sciences · doi:10.3390/app11198976 · Cited by 6
“Compared to local features such as SIFT [5] and SURF [6], global descriptors are not only robust to illumination changes, but also require less computation since they do not require a keypoint detection phase [1].”
BackgroundMethodDeep Embeddings-based Place Recognition Robust to Motion Blur
Woźniak, P., & Kwolek, B. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00203 · Cited by 7
“Visual Place Recognition (VPR) refers to capability of recalling a previously visited place using visual input, under changing viewpoint, varying illumination conditions, while requiring as less as possible computational power and memory storage [17].”
BackgroundHighly-Efficient Binary Neural Networks for Visual Place Recognition
Ferrarini, B., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981978 · Cited by 12
“The rapid improvements in vision sensing capabilities made cameras the primary source of information for many robotics platforms motivating the interest in addressing place recognition with visual information [1], [2].”
Self-citationLocality-constrained continuous place recognition for SLAM in extreme conditions
Yadav, R., Pani, V., Mishra, A., Tiwari, N., & Kala, R. (2023) · Applied Intelligence · doi:10.1007/s10489-022-04415-1 · Cited by 5
“Place recognition algorithms [5, 20] take an image as input and detect the place from which the image is captured.”
BackgroundCoPR: Toward Accurate Visual Localization With Continuous Place-Descriptor Regression
Zaffar, M., Nan, L., & Kooij, J. F. P. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3262106 · Cited by 9
“However improving their performance remains an ongoing research challenge [6] [7].”
BackgroundPerformance Comparison of Visual Teach and Repeat Systems for Mobile Robots
Simon, M., Broughton, G., Rouček, T., Rozsypálek, Z., & Krajník, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31268-7_1 · Cited by 5
Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space
He, Y., Fang, I., Li, Y., Shah, R., & Feng, C. (2023) · Robotics: Science and Systems · doi:10.15607/rss.2023.xix.099 · Cited by 14
Robust Depth-Aided Visual-Inertial-Wheel Odometry for Mobile Robots
Zhao, X., Li, Q., Wang, C., Dou, H., & Liu, B. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3323731 · Cited by 10
“Simultaneously,visualplace recognitionprovidespotentialcandidatesfortheloopclosure modulewhentherobotrevisitsknownregions[6].”
Zhu, B., Fan, X., Gao, X., Xu, G., & Xie, J. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104619 · Cited by 7
Zhao, H., Zhao, Y., Tomko, M., & Khoshelham, K. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3388965 · Cited by 6
“Existing relocalization methods can be divided into two categories: geometry-based methods and learning-based meth-ods [4], [13], [20].”
MethodRING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning
Lu, S., Xu, X., Zhang, D., Wu, Y., Lu, H., Chen, X., Xiong, R., & Wang, Y. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3543267 · Cited by 14
“Traditional global localization approaches, originating from early visual methods [3], [6], [7], typically follow a paradigm: first place recognition (PR) then pose estimation (PE).”
Automated Map Reading: Image Based Localisation in 2-D Maps Using Binary Semantic Descriptors
Panphattarasap, P., & Calway, A. D. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594253 · Cited by 25
Cross-season vehicle localization using bag of local 3D features
Takahashi, Y., Kanji, T., & Fang, Y. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317606 · Cited by 6
“Much work has been conducted on self-localization, resulting in many interesting and effective algorithms being proposed [2].”
Backgroundvan Eden, B., & Rosman, B. (2019) · Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) · doi:10.1109/robomech.2019.8704781 · Cited by 8
“[46] on place recognition and a visual place recognition survey [47] that provide insight into this topic.”
BackgroundA Robust Image-Sequence-Based Framework for Visual Place Recognition in Changing Environments
Wang, Y., Xue, T., & Li, Q. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2977128 · Cited by 8
“2977128 two factors: 1) viewpoint variations and 2) environmental condition variations [1].”
BackgroundInfluentialGeo-localization using Ridgeline Features Extracted from 360-degree Images of Sand Dunes
Fukuda, S., Nakatani, S., Nishiyama, M., & Iwai, Y. (2020) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0008914306210627 · Cited by 6
“In the second type (Kim et al., 2017; Brejcha and Čadı́k, 2017; Lowry et al., 2016), the geo-location is estimated using texture patterns in the images acquired from a camera.”
A SPATIO-TEMPORAL WEB APPLICATION FOR THE UNDERSTANDING OF THE FORMATION OF THE PARISIAN METROPOLIS
Blettery, E., Lecat, P., Devaux, A., Gouet-Brunet, V., Saly-Giocanti, F., Brédif, M., Delavoipière, L., Conord, S., & Moret, F. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-vi-4-w1-2020-45-2020 · Cited by 8
“This estimation is a core problem that can be tackled by a large panel of approaches (Lowry et al., 2016) (Garcia-Fidalgo, Ortiz, 2015) (Brejcha, Cadik, 2017) (Piasco et al., 2018).”
BackgroundTomită, M.-A., Zaffar, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2020) · ePrints Soton (University of Southampton) · doi:10.48550/arxiv.2009.13454 · Cited by 6
“descriptors cannot handle viewpoint variation [2].”
BackgroundInfluentialSelf-citationSelf-Supervised Map-Segmentation by Mining Minimal-Map-Segments
Kanji, T. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304724 · Cited by 6
Vehicle-to-Vehicle Collaborative Graph-Based Proprioceptive Localization
Cheng, H.-M., Chou, C., & Song, D. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3056032 · Cited by 6
Garcia‐Fidalgo, E., & Ortiz, A. (2022) · Autonomous Robots · doi:10.1007/s10514-021-10032-7 · Cited by 6
“The BoW model [50], Nister and Stewenius (2006), used along with an inverted file, is the most used indexing scheme for appearance-based LCD (Garcia-Fidalgo and Ortiz 2015; Lowry et al. 2016).”
MethodVisual and Location Information Fusion for Hierarchical Place Recognition
Hettiarachchi, D., & Kamijo, S. (2022) · International Conference on Consumer Electronics · doi:10.1109/icce53296.2022.9730537 · Cited by 6
Woźniak, P., & Ożóg, D. (2023) · Sensors · doi:10.3390/s23136134 · Cited by 7
“Depending on the environment and assumptions, conditions, such as the point of view, lighting conditions, or observed equipment, change, which requires additional handling mechanisms that are computationally expensive [3].”
BackgroundLinear Features Observation Model for Autonomous Vehicle Localization
Shipitko, O., Kibalov, V., & Abramov, M. V. (2020) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv50220.2020.9305434 · Cited by 7
“Throughout many years it is still one of the core topics in robotics [1], [2], [3].”
BackgroundLiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure DetectionPreprint
Company-Corcoles, J. P., Garcia‐Fidalgo, E., & Ortiz, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09897 · Cited by 6
“The Bag of Words (BoW) model [29, 34], in combination with an inverted file, is arguably the most used indexing scheme for appearance-based loop closure detection [14, 25].”
Visual Place Recognition for Simultaneous Localization and Mapping
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Wiley eBooks · doi:10.1002/9781394152636.ch4 · Cited by 7
Monocular based 3D depth estimation and SLAM integration
El-Alfy, Y. E., & Baroudi, U. A. (2025) · Drone Systems and Applications · doi:10.1139/dsa-2024-0025 · Cited by 7
UltraVPR: Unsupervised Lightweight Rotation- Invariant Aerial Visual Place Recognition
Chen, C., Li, C., He, M., Wang, J., Xing, F., & Meng, Z. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3592075 · Cited by 5
SPOT: Point Cloud Based Stereo Visual Place Recognition for Similar and Opposing Viewpoints
Carmichael, S., Agrawal, R., Vasudevan, R., & Skinner, K. A. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610293 · Cited by 5
“Throughout the literature, VPR is often cast as pure image retrieval [3].”
BackgroundMethodInfluentialHardness-Aware Metric Learning With Cluster-Guided Attention for Visual Place Recognition
Guan, P., Cao, Z., Fan, S., Yang, Y., Yu, J., & Wang, S. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3465520 · Cited by 7
“It aims to determine the specific geographical location corresponding to the current image captured by a robot, given a set of database images annotated with geo-tags in an environment [1], [2].”
PRIOR-SLAM: Enabling Visual SLAM for Loop Closure Under Large Viewpoint Variations
Wang, Y., Bai, W., Zhang, Z., Wang, H., Sun, H. X., & Cao, Q. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3508193 · Cited by 6
“In this article, we address the lack of viewpoint invariance in both macroscopic place definition and microscopic feature descriptioninexistingLCDresearch,basedonthecrucialinsight thatgeometricinformationismoreviewpoint-invariantthan visualinformation[1].”
InfluentialLearning street view representations based on a spatiotemporal contrastive learning framework
Li, Y. H., Huang, Y., & Zhang, F. (2025) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2025.102393 · Cited by 11
“For instance, in place recognition tasks (Lowry et al., 2015), the features are expected to focus only on place-invariant information, such as buildings and roads, filtering out dynamic information like lighting conditions, pedestrians, vehicles, and vegetation.”
Zhang, L., Zhang, S., Li, Z., Sun, X., Hu, W., Kong, D., & Dong, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3583695 · Cited by 5
“Viewpoint changes, condition change, and perceptual aliasing [24] are three key challenges existing in VPR, and one crucial difficulty, in particular, is faced in viewpoint changes—dynamic target interference.”
Visual Localization by Place Recognition Based on Multifeature (D- λ LBP++HOG)
Qiao, Y., & Zhang, Z. (2017) · Journal of Sensors · doi:10.1155/2017/2157243 · Cited by 5
“With the wide use of cameras, varieties of approaches were proposed to address the challenges of place recognition based visual localization [1, 2].”
BackgroundA Sequence-Based Neuronal Model for Mobile Robot Localization
Neubert, P., Ahmad, S., & Protzel, P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00111-7_11 · Cited by 5
Jayasuriya, M., Dissanayake, G., Ranasinghe, R., & Gandhi, N. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917454 · Cited by 7
“Feature based systems employ feature detectors and descriptors such as FAST, SIFT, SURF, ORB and BRIEF [20], [21].”
MethodVision-based Indoor Positioning Method By Joint Using 2D Images and 3D Point Cloud Map
Ma, L., Jiang, H., Qin, D., & Tan, X. (2020) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc48107.2020.9148325 · Cited by 5
“Image retrieval has been studied for a long time so that there are lots of good methods available [9, [11].”
MethodImproving Road Segmentation in Challenging Domains Using Similar Place Priors
Malone, C., Garg, S., Xu, M., Peynot, T., & Milford, M. J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3146894 · Cited by 6
“Our proposed approach relies on the identification of similar reference images using Visual Place Recognition systems [24], warranting a brief overview.”
MethodSelf-citationUnsupervised Appearance Map Abstraction for Indoor Visual Place Recognition With Mobile Robots
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3186768 · Cited by 6
“Visual Place Recognition (VPR) [1], [2] aims to detect the most similar place to a certain query image, given a map consisting of a generally large database of georeferenced images.”
BackgroundUsman, M. T., Ali, A. N., Tahir, A., Rahman, M. Z. U., & Khan, A. M. (2022) · Sensors · doi:10.3390/s22239168 · Cited by 5
“Although comprehensively studied [12] and more accurate visual keypointbased place recognition techniques have their own set of difficulties regarding scalability, viewpoint, and slight variations.”
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.