The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection
Open accessThe DOI matches its Crossref record; 395 of the 397 references it cites were found in a registry or an index.
Abstract
Where am I? This is one of the most critical questions that any intelligent system should answer to decide whether it navigates to a previously visited area. This problem has long been acknowledged for its challenging nature in simultaneous localization and mapping (SLAM), wherein the robot needs to correctly associate the incoming sensory data to the database allowing consistent map generation. The significant advances in computer vision achieved over the last 20 years, the increased computational power, and the growing demand for long-term exploration contributed to efficiently performing such a complex task with inexpensive perception sensors. In this article, visual loop closure detection, which formulates a solution based solely on appearance input data, is surveyed. We start by briefly introducing place recognition and SLAM concepts in robotics. Then, we describe a loop closure detection system’s structure, covering an extensive collection of topics, including the feature extraction, the environment representation, the decision-making step, and the evaluation process. We conclude by discussing open and new research challenges, particularly concerning the robustness in dynamic environments, the computational complexity, and scalability in long-term operations. The article aims to serve as a tutorial and a position paper for newcomers to visual loop closure detection.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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 4×
“combination of advances in GPU computational capabilities and large labeled datasets [217].”
BackgroundInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“CNN is a concept introduced by LeCun et al. in the late ’80s [207], [208].”
MethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 6×
“6b), inspired by SIFT, proposes a faster extraction version using an approximation of the determinant of Hessian blob detector for identifying regions-of-interest and the sum of the Haar wavelet response around each point for feature description.”
MethodInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · cited 2×
“, AlexNet [217], VGG [238], ResNet [239], Inception [240], DenseNet [241], and MobileNet [242].”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1×
“However, subsequent studies showed that the utilization of intermediate representations with and without the CNN’s fully connected layers could offer high performances [153], [155] and rich semantic information [234], [235].”
BackgroundFischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893
(1967) · Cited by 23,719
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Hanley, J. A., & McNeil, B. J. (1982) · Radiology · doi:10.1148/radiology.143.1.7063747 · Cited by 21,856 · cited 3×
“The area under the precision-recall curve (AUC) [284] is another straightforward metric for indicating the performance [156], [164].”
BackgroundMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 2×
“, AlexNet [217], VGG [238], ResNet [239], Inception [240], DenseNet [241], and MobileNet [242].”
BackgroundVisualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“recent contributions provided helpful insights for better understanding the complex relationship between network layers and their features visualization [236], [237].”
BackgroundSURF: 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
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 1×
“CNN is a concept introduced by LeCun et al. in the late ’80s [207], [208].”
MethodBaeza-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
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 5×
“0 km X KITTI (course 05) [277] Stereo, Gray, frontal Outdoor, urban, dynamic 1241 × 376, 10 Hz 2761 ∼7.”
BackgroundInfluentialBeyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · cited 1×
“More specifically, data structures, such as pyramid matching [401], [402], were used to detect loop closures when high dimensional image descriptors were adopted [367], [397].”
MethodFundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680
Multidimensional binary search trees used for associative searching
Bentley, J. L. (1975) · Communications of the ACM · doi:10.1145/361002.361007 · Cited by 7,520 · cited 1×
“, k-d trees [395], randomized k-d forests [396], [397], Chow Liu trees [398], decision trees [399], BK tree [400].”
MethodORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 2×
“Lastly, the robot’s map is rectified extensively at both sides of the loop event (with permission from [3]).”
BackgroundError bounds for convolutional codes and an asymptotically optimum decoding algorithm
Viterbi, A. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1054010 · Cited by 6,759
Cognitive maps in rats and men
Tolman, E. C. (1948) · Psychological Review · doi:10.1037/h0061626 · Cited by 6,641 · cited 1×
“Relying on a higher representation level than metric ones, topological maps mimic the humans’ and animals’ internal maps [53]– [55].”
BackgroundThe relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559 · cited 1×
“whether or not the precision reaches 100% at any recall value [291].”
BackgroundVideo Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1×
“In particular, this model, which was initially developed for language processing and information retrieval tasks [188], allows the images’ description as an aggregation of quantized local features, i.e., “visual words” [189].”
MethodModeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Oliva, A., & Torralba, A. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011139631724 · Cited by 6,319 · cited 4×
“1) Global Features: Oliva and Torralba proposed the most recognized global descriptor, widely known as Gist [179]–[181], inspiring several loop closure detection pipelines [97]–[100].”
BackgroundInfluentialThe hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat
O'Keefe, J., & Dostrovsky, J. (1971) · Brain Research · doi:10.1016/0006-8993(71)90358-1 · Cited by 6,151 · cited 1×
“Relying on a higher representation level than metric ones, topological maps mimic the humans’ and animals’ internal maps [53]– [55].”
BackgroundEvaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
Powers, D. M. W. (2020) · arXiv · doi:10.48550/arxiv.2010.16061 · Cited by 5,440
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 2×
“, AlexNet [217], VGG [238], ResNet [239], Inception [240], DenseNet [241], and MobileNet [242].”
BackgroundA STATISTICAL INTERPRETATION OF TERM SPECIFICITY AND ITS APPLICATION IN RETRIEVAL
SPARCK JONES, K. (1972) · Journal of Documentation · doi:10.1108/eb026526 · Cited by 4,505 · cited 1×
“inverse-document-frequency (TF-IDF) scheme [191] has been adopted to weight each database element.”
MethodParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346 · cited 1×
“1) Key-frame selection: is based on the detection of scenes’ visual changes by utilizing methods developed for video compression [341].”
MethodMicrostructure of a spatial map in the entorhinal cortex
Hafting, T., Fyhn, M., Molden, S., Moser, M.-B., & Moser, E. I. (2005) · Nature · doi:10.1038/nature03721 · Cited by 4,068
Places: A 10 Million Image Database for Scene Recognition
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2723009 · Cited by 4,042 · cited 1×
“[403] database reduced the computational and memory costs [160].”
BackgroundMonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959 · cited 1×
“infeasible when large distances are dealt with [52].”
BackgroundComputer vision: algorithms and applications
(2011) · Choice Reviews Online · doi:10.5860/choice.48-5140 · Cited by 3,911
BRIEF: Binary Robust Independent Elementary Features
Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_56 · Cited by 3,597
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596 · cited 1×
“A robot’s capability to build a map (deriving the model of an unknown environment) and localizing (estimating its position) within that map is essential for intelligent autonomous operations and, during the last three decades, one of the most famous research topics [39].”
BackgroundScalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
BRISK: Binary Robust invariant scalable keypoints
Leutenegger, S., Chli, M., & Siegwart, R. Y. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126542 · Cited by 3,450 · cited 2×
“Most of them extended BRIEF, which uses simple intensity difference tests to describe regions-of-interest, by incorporating descriptiveness and invariance to scale and rotation variations, such as LDB, ORB [200], BRISK [201], FREAK [202], and M-LDB [203].”
SuperPoint: Self-Supervised Interest Point Detection and Description
DeTone, D., Malisiewicz, T., & Rabinovich, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00060 · Cited by 3,355 · cited 4×
“SuperPoint [221] and D2net [233] were robust across various conditional changes.”
BackgroundInfluentialRefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
Lin, G., Milan, A., Shen, C., & Reid, I. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.549 · Cited by 3,287 · cited 1×
“tracted via RefineNet [330], multi-frame LoST-X [177] accomplished place recognition over opposing viewpoints.”
Background(1999) · Cited by 3,186
Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
Multiple view geometry in computer vision
Opower, H. (2002) · Optics and Lasers in Engineering · doi:10.1016/s0143-8166(01)00145-2 · Cited by 3,007
Aggregating local descriptors into a compact image representation
Jegou, H., Douze, M., Schmid, C., & Perez, P. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540039 · Cited by 2,692
FAST APPROXIMATE NEAREST NEIGHBORS WITH AUTOMATIC ALGORITHM CONFIGURATION
(2009) · Proceedings of the Fourth International Conference on Computer Vision Theory and Applications · doi:10.5220/0001787803310340 · Cited by 2,640 · cited 1×
“k-d forests [397], [398], Chow Liu trees [399], decision trees [400].”
BackgroundThe information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 1×
“Subsequent works were based on spatial data structures [394] and agglomerative clustering [359].”
BackgroundImproving the Fisher Kernel for Large-Scale Image Classification
Perronnin, F., Sánchez, J., & Mensink, T. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15561-1_11 · Cited by 2,588 · cited 1×
“Fisher Kernels [200], [201] refine the visual BoW model via fitting a Gaussian mixture over the database entries and the local features.”
MethodNetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.572 · Cited by 2,584 · cited 2×
“Inspired by the success of VLAD, NetVLAD [216] was proposed as a trainable and generalized layer that forms an image descriptor via combining features, while the spatial pyramid-enhanced VLAD (SPE-VLAD) layer improved VLAD features by exploiting the images’ spatial pyramid structure [149].”
Method(2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2,534
Method for registration of 3-D shapes:
Besl, P. J., & McKay, N. D. (1992) · SPIE Proceedings · doi:10.1117/12.57955 · Cited by 2,413
Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.352 · Cited by 2,338 · cited 1×
“Synthia [280] is a synthetically created dataset containing trajectories in city-like environments throughout spring and winter.”
BackgroundThe EuRoC micro aerial vehicle datasets
Burri, M., Nikolic, J., Gohl, P., Schneider, T., Rehder, J., Omari, S., Achtelik, M. W., & Siegwart, R. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915620033 · Cited by 2,066 · cited 2×
“2km X EuRoC Machine Hall 05 [281] Stereo, gray, frontal Indoor, static 752 × 480, 20 Hz 2273 ∼ 0.”
BackgroundAn efficient solution to the five-point relative pose problem
Nister, D. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.17 · Cited by 2,009 · cited 1×
“Moreover, a minimum number of RANSAC inliers has to be satisfied for a loop to be confirmed [275].”
BackgroundPlace Cells, Grid Cells, and the Brain's Spatial Representation System
Moser, E. I., Kropff, E., & Moser, M.-B. (2008) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.31.061307.090723 · Cited by 1,934 · cited 1×
“This fact highlights the impact of appearance cues in localization tasks [29]–[32].”
BackgroundBags of Binary Words for Fast Place Recognition in Image Sequences
Galvez-López, D., & Tardos, J. D. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2197158 · Cited by 1,913 · cited 5×
“Aiming to prevent the system from detecting false-positives, these locations are rejected based on a sliding window defined either by a timing constant [134], [137], [142], [176], [255] or environmental semantic changes [50], [97], [128], [144], [148], [150].”
BackgroundMethodInfluentialUnderstanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Alahi, A., Ortiz, R., & Vandergheynst, P. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247715 · Cited by 1,775 · cited 2×
“Most of them extended BRIEF, which uses simple intensity difference tests to describe regions-of-interest, by incorporating descriptiveness and invariance to scale and rotation variations, such as LDB, ORB [200], BRISK [201], FREAK [202], and M-LDB [203].”
Keyframe-based visual–inertial odometry using nonlinear optimization
Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R., & Furgale, P. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364914554813 · Cited by 1,723 · cited 1×
“[90]–[94] can improve performance, especially in changing environmental conditions [95], such a setup requires expensive hardware and additional calibration than camera-only ones [96].”
BackgroundApproximating discrete probability distributions with dependence trees
Chow, C., & Liu, C. (1968) · IEEE Transactions on Information Theory · doi:10.1109/tit.1968.1054142 · Cited by 1,720 · cited 1×
“k-d forests [397], [398], Chow Liu trees [399], decision trees [400].”
BackgroundFisher Kernels on Visual Vocabularies for Image Categorization
Perronnin, F., & Dance, C. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383266 · Cited by 1,641 · cited 2×
“Fisher Kernels [193], [194] refine the visual BoW model via fitting a Gaussian mixture over the database entries and the local features.”
Method1 year, 1000 km: The Oxford RobotCar dataset
Maddern, W., Pascoe, G., Linegar, C., & Newman, P. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364916679498 · Cited by 1,632 · cited 4×
“Over 100 traverses with various weather ( e.g., direct sun, overcast) and illumination ( e.g., day, night) conditions are provided in Oxford RobotCar [279].”
BackgroundMethodInfluentialAggregating Local Image Descriptors into Compact Codes
Jegou, H., Perronnin, F., Douze, M., Sanchez, J., Perez, P., & Schmid, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.235 · Cited by 1,503
The pyramid match kernel: discriminative classification with sets of image features
Grauman, K., & Darrell, T. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.239 · Cited by 1,481 · cited 1×
“More specifically, data structures, such as pyramid matching [401], [402], were used to detect loop closures when high dimensional image descriptors were adopted [367], [397].”
MethodFAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
Cummins, M., & Newman, P. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364908090961 · Cited by 1,472 · cited 14×
“5 km X City Centre [113] Stereo, color, lateral Outdoor, urban, dynamic 1024 × 768, 7 Hz 1237 ∼1.”
BackgroundMethodInfluentialChapter 2 Building the gist of a scene: the role of global image features in recognition
Oliva, A., & Torralba, A. (2006) · Progress in Brain Research · doi:10.1016/s0079-6123(06)55002-2 · Cited by 1,434
Representing shape with a spatial pyramid kernel
Bosch, A., Zisserman, A., & Munoz, X. (2007) · Proceedings of the 6th ACM international conference on Image and video retrieval · doi:10.1145/1282280.1282340 · Cited by 1,399
DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes
Bescos, B., Facil, J. M., Civera, J., & Neira, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2860039 · Cited by 1,263 · cited 1×
“as the vast majority of the approaches and datasets assume a static environment which limits the applicability of visual SLAM in many relevant cases, such as intelligent autonomous systems operating in populated real-world environments [305], [306].”
BackgroundSalakhutdinov, R., & Hinton, G. (2009) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2008.11.006 · Cited by 1,246 · cited 1×
“, locality sensitive hashing (LSH) [384] or semantic hashing [385].”
BackgroundLIFT: Learned Invariant Feature Transform
Yi, K. M., Trulls, E., Lepetit, V., & Fua, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_28 · Cited by 1,202
Neural Codes for Image Retrieval
Babenko, A., Slesarev, A., Chigorin, A., & Lempitsky, V. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_38 · Cited by 1,192
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., & Sattler, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00828 · Cited by 1,179 · cited 3×
“SuperPoint [221] and D2net [233] were robust across various conditional changes.”
BackgroundFast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces
Alcantarilla, P., Nuevo, J., & Bartoli, A. (2013) · Procedings of the British Machine Vision Conference 2013 · doi:10.5244/c.27.13 · Cited by 1,173 · cited 2×
“Most of them extended BRIEF, which uses simple intensity difference tests to describe regions-of-interest, by incorporating descriptiveness and invariance to scale and rotation variations, such as LDB, ORB [200], BRISK [201], FREAK [202], and M-LDB [203].”
MethodAlcantarilla, P. F., Bartoli, A., & Davison, A. J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33783-3_16 · Cited by 1,168 · cited 2×
“KAZE [199] detects and describes 2D features in a nonlinear scale space by means of nonlinear diffusion filtering, demonstrating improved feature quality.”
BackgroundVisual Place Recognition: A Survey
Lowry, S., Sünderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., & Milford, M. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2496823 · Cited by 1,079 · cited 2×
“Similar surveys can be found in the related literature, although they focus more on mapping techniques [4]–[6] or place recognition, relevant to robotics and other research areas, including computer vision, viz., Lowry et al. [7], Zhang et al. [8], Masone and Caputo [9], and Garg et al. [10].”
BackgroundMatching Local Self-Similarities across Images and Videos
Shechtman, E., & Irani, M. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383198 · Cited by 1,076 · cited 1×
“During navigation in a changing environment, the topological information about the robot’s relative movement becomes more important as noise from the sensory inputs is accumulated to an overwhelming degree [296], [297].”
BackgroundFrom Coarse to Fine: Robust Hierarchical Localization at Large Scale
Sarlin, P.-E., Cadena, C., Siegwart, R., & Dymczyk, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01300 · Cited by 1,044 · cited 5×
“feature network (HF-Net) [180], a compressed model trained”
BackgroundMethodInfluentialHippocampal place units in the freely moving rat: Why they fire where they fire
O'Keefe, J., & Conway, D. H. (1978) · Experimental Brain Research · doi:10.1007/bf00239813 · Cited by 999 · cited 1×
“This fact highlights the impact of appearance cues in localization tasks [29]–[32].”
BackgroundSeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights
Milford, M. J., & Wyeth, G. F. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224623 · Cited by 981 · cited 11×
“Each of the techniques mentioned above can be effi-ciently adopted in sequence-of-images-based methods ( e.g., SeqSLAM [111], HMM-SeqSLAM [250], ABLE-M [251], S-VWV [115], MCN [252]).”
BackgroundMethodInfluentialWang, J., Zhang, T., Song, J., Sebe, N., & Shen, H. T. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699960 · Cited by 971 · cited 1×
“adopted binary descriptors to improve computational efficiency [148] or encoded the high-dimensional vectors into compact codes, such as hashing [383].”
MethodDynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes
Bescos, B., Fácil, J. M., Civera, J., & Neira, J. (2018) · Zaguan (Universidad de Zaragoza) · Cited by 893
Context-based vision system for place and object recognition
Torralba, Murphy, Freeman, & Rubin (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238354 · Cited by 867
Large-Scale Image Retrieval with Attentive Deep Local Features
Noh, H., Araujo, A., Sim, J., Weyand, T., & Han, B. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.374 · Cited by 847 · cited 1×
“Deep local features (DELF) combined traditional local feature extraction with deep learning [225].”
BackgroundRGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments
Henry, P., Krainin, M., Herbst, E., Ren, X., & Fox, D. (2014) · Springer Tracts in Advanced Robotics · doi:10.1007/978-3-642-28572-1_33 · Cited by 809 · cited 1×
“Nevertheless, these issues could be addressed by adopting more complex setups, such as stereo or RGB-D cameras [91]–[94].”
BackgroundMeasurement and correction of systematic odometry errors in mobile robots
Borenstein, J., & Feng, L. (1996) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.544770 · Cited by 807
KUIPERS, B. (1978) · Cognitive Science · doi:10.1016/s0364-0213(78)80003-2 · Cited by 771 · cited 1×
“is constructed, which is further split into a set of metric submaps [61]–[66].”
BackgroundParticular object retrieval with integral max-pooling of CNN activations
Tolias, G., Sicre, R., & Jégou, H. (2015) · arXiv · doi:10.48550/arxiv.1511.05879 · Cited by 744 · cited 2×
“pooling on cropped areas of the convolutional layers’ feature maps to detect regions-of-interest [230].”
BackgroundArandjelovic, R., & Zisserman, A. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.207 · Cited by 713 · cited 1×
“At the same time, VLAD (VLAD stands for vector of locally aggregated descriptors [202], [203]) concatenated the distance vectors between each”
BackgroundThe entorhinal grid map is discretized
Stensola, H., Stensola, T., Solstad, T., Frøland, K., Moser, M.-B., & Moser, E. I. (2012) · Nature · doi:10.1038/nature11649 · Cited by 701 · cited 2×
“Hierarchies have also been found in the mammalian brain, both in the structure of grid cells in the Hippocampus [356] and the visual cortex’s pathway [357].”
BackgroundBenchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., et al. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00897 · Cited by 699
Optimised KD-trees for fast image descriptor matching
Silpa-Anan, C., & Hartley, R. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587638 · Cited by 677 · cited 2×
“More specifically, data structures, such as pyramid matching [401], [402], were used to detect loop closures when high dimensional image descriptors were adopted [367], [397].”
BackgroundMethodVector-based navigation using grid-like representations in artificial agents
Banino, A., Barry, C., Uria, B., Blundell, C., Lillicrap, T., Mirowski, P., Pritzel, A., Chadwick, M. J., Degris, T., Modayil, J., et al. (2018) · Nature · doi:10.1038/s41586-018-0102-6 · Cited by 677 · cited 1×
“In robot navigation, unlike large-scale image retrieval or classification tasks, where images are disorganized, sensory measurements are captured sequentially and without time gaps [269], [270].”
BackgroundSimilarity estimation techniques from rounding algorithms
Charikar, M. (2002) · doi:10.1145/509961.509965 · Cited by 659
(2020) · doi:10.1109/icra40945.2020.9196885 · Cited by 633 · cited 1×
“Loop closure detection belongs to the front-end, as it is required to create constraints among locations once the robot returns to an earlier visited area [3], while outlier ( i.e., false-positive loop closures) rejection is assigned to the back-end of SLAM [41]–[43].”
BackgroundCity-Scale Location Recognition
Schindler, G., Brown, M., & Szeliski, R. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383150 · Cited by 626
Choset, H., & Nagatani, K. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.928558 · Cited by 624
CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching
Agrawal, M., Konolige, K., & Blas, M. R. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88693-8_8 · Cited by 613 · cited 1×
“CenSurE [205], a lightweight equivalent of SURF, detects regions-of-interest using center-surrounded”
BackgroundAppearance-only SLAM at large scale with FAB-MAP 2.0
Cummins, M., & Newman, P. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364910385483 · Cited by 609 · cited 5×
“Aiming to prevent the system from detecting false-positives, these locations are rejected based on a sliding window defined either by a timing constant [134], [137], [142], [176], [255] or environmental semantic changes [50], [97], [128], [144], [148], [150].”
BackgroundMethodInfluentialMa, J., Zhao, J., Jiang, J., Zhou, H., & Guo, X. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-018-1117-z · Cited by 601
GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence
Bian, J., Lin, W.-Y., Matsushita, Y., Yeung, S.-K., Nguyen, T.-D., & Cheng, M.-M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.302 · Cited by 594
Potter, M. C. (1975) · Science · doi:10.1126/science.1145183 · Cited by 589 · cited 1×
“information or “gist” of a scene [184], [185].”
Hahnel, D., Burgard, W., Fox, D., & Thrun, S. (2004) · Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453) · doi:10.1109/iros.2003.1250629 · Cited by 572 · cited 1×
“Although successful mapping techniques based on range-finders are implemented [73]–[75], these types of sensors tend to be”
MethodCNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
Radenović, F., Tolias, G., & Chum, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_1 · Cited by 551 · cited 2×
“However, efforts to reduce their complexity do exist [220].”
BackgroundOn the performance of ConvNet features for place recognition
Sunderhauf, N., Shirazi, S., Dayoub, F., Upcroft, B., & Milford, M. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353986 · Cited by 544 · cited 1×
“However, subsequent studies showed that the utilization of intermediate representations with and without the CNN’s fully connected layers could offer high performances [153], [155] and rich semantic information [234], [235].”
BackgroundFrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping
Konolige, K., & Agrawal, M. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004832 · Cited by 532 · cited 1×
“Although successful mapping techniques based on range-finders are implemented [67]–[69], these types of sensors tend to be associated with, or replaced by, single cameras [70]–[76] or stereo camera rigs [77]–[82].”
BackgroundFast and Incremental Method for Loop-Closure Detection Using Bags of Visual Words
Angeli, A., Filliat, D., Doncieux, S., & Meyer, J.-A. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004514 · Cited by 514 · cited 9×
“Aiming to prevent the system from detecting false-positives, these locations are rejected based on a sliding window defined either by a timing constant [134], [137], [142], [176], [255] or environmental semantic changes [50], [97], [128], [144], [148], [150].”
BackgroundInfluentialAn active testing model for tracking roads in satellite images
Geman, D., & Jedynak, B. (1996) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.476006 · Cited by 498 · cited 1×
“k-d forests [397], [398], Chow Liu trees [399], decision trees [400].”
BackgroundNear Duplicate Image Detection: min-Hash and tf-idf Weighting
Chum, O., Philbin, J., & Zisserman, A. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.50 · Cited by 460 · cited 1×
“hashing methods [247], [371], [372] have been explored, apart from data structure-based retrieval techniques, e.”
MethodLearning deep representations for ground-to-aerial geolocalization
Lin, T.-Y., Cui, Y., Belongie, S., & Hays, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299135 · Cited by 401
City-scale landmark identification on mobile devices
Chen, D. M., Baatz, G., Koser, K., Tsai, S. S., Vedantham, R., Pylvanainen, T., Roimela, K., Chen, X., Bach, J., Pollefeys, M., et al. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995610 · Cited by 400
RatSLAM: a hippocampal model for simultaneous localization and mapping
Milford, M. J., Wyeth, G. F., & Prasser, D. (2004) · IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 · doi:10.1109/robot.2004.1307183 · Cited by 399 · cited 3×
“temporal models [76], [163], or transition-based sub-mapping, e.”
BackgroundMethodReal Time Localization and 3D Reconstruction
Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., & Sayd, P. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) · doi:10.1109/cvpr.2006.236 · Cited by 396 · cited 1×
“Representative examples include the distance and angle between observations in space [86], [99], [271], [342], specific time intervals [272], [343], and a minimum number of tracked landmarks [130], [141], [344]–[346].”
BackgroundThe design and analysis of spatial data structures
Kovouras, M. (1991) · Computers & Geosciences · doi:10.1016/0098-3004(91)90117-v · Cited by 394
Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free
Suenderhauf, N., Shirazi, S., Jacobson, A., Dayoub, F., Pepperell, E., Upcroft, B., & Milford, M. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.022 · Cited by 379
Temporal frequency of subthreshold oscillations scales with entorhinal grid cell field spacing
Giocomo, L. M., Zilli, E. A., Fransén, E., & Hasselmo, M. E. (2007) · Science · doi:10.1126/science.1139207 · Cited by 377
An Investigation of Practical Approximate Nearest Neighbor Algorithms
Liu, T., Moore, A., Yang, K., & Gray, A. (2004) · Cited by 375
Online global loop closure detection for large-scale multi-session graph-based SLAM
Labbe, M., & Michaud, F. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6942926 · Cited by 373
Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation
Labbe, M., & Michaud, F. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2242375 · Cited by 372 · cited 7×
“Aiming to prevent the system from detecting false-positives, these locations are rejected based on a sliding window defined either by a timing constant [134], [137], [142], [176], [255] or environmental semantic changes [50], [97], [128], [144], [148], [150].”
BackgroundMethodInfluentialHierarchical SLAM: real-time accurate mapping of large environments
Estrada, C., Neira, J., & Tardos, J. D. (2005) · IEEE Transactions on Robotics · doi:10.1109/tro.2005.844673 · Cited by 368 · cited 1×
“Techniques that fall into this category map the environment hierarchically [347]–[351] and tackle scalability through the formulation of image groups,”
BackgroundUnifying Deep Local and Global Features for Image Search
Cao, B., Araujo, A., & Sim, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58565-5_43 · Cited by 366 · cited 5×
“features: Aiming to bridge the gap between robustness and efficiency, an emerging trend in the line of learned features combines the advances in the aforementioned fields to jointly estimate global and local features [180], [181].”
BackgroundMethodInfluentialDeep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?
Kruger, N., Janssen, P., Kalkan, S., Lappe, M., Leonardis, A., Piater, J., Rodriguez-Sanchez, A. J., & Wiskott, L. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.272 · Cited by 362
Ford Campus vision and lidar data set
Pandey, G., McBride, J. R., & Eustice, R. M. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364911400640 · Cited by 360 · cited 2×
“Campus is another collection of several panoramic images [279].”
BackgroundSpatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition
Yu, J., Zhu, C., Zhang, J., Huang, Q., & Tao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2908982 · Cited by 352 · cited 3×
“posed as a trainable and generalized layer that forms an image descriptor via combining features, while the spatial pyramidenhanced VLAD (SPE-VLAD) layer improved VLAD features by exploiting the images’ spatial pyramid structure [156].”
BackgroundYang, H., Antonante, P., Tzoumas, V., & Carlone, L. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2965893 · Cited by 325
Road Detection Based on Illuminant Invariance
Alvarez, J. M. Á., & Lopez, A. M. (2011) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2010.2076349 · Cited by 321 · cited 1×
“was based on illumination-invariant image conversions [218], [302], [317], and shadow removal [318]–[320].”
Outdoor SLAM using visual appearance and laser ranging
Newman, P., Cole, D., & Ho, K. (2006) · Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006. · doi:10.1109/robot.2006.1641869 · Cited by 316 · cited 1×
“In contrast, methods that do not follow this model implement an exhaustive search on the database descriptors’ space [77], [126], [137], [141], [144], [146].”
MethodThe New College Vision and Laser Data Set
Smith, M., Baldwin, I., Churchill, W., Paul, R., & Newman, P. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909103911 · Cited by 311 · cited 2×
“Another widely used version of the New College dataset was later presented in [2].”
BackgroundMethodCASENet: Deep Category-Aware Semantic Edge Detection
Yu, Z., Feng, C., Liu, M.-Y., & Ramalingam, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.191 · Cited by 300
Fast Matching of Binary Features
Muja, M., & Lowe, D. G. (2012) · 2012 Ninth Conference on Computer and Robot Vision · doi:10.1109/crv.2012.60 · Cited by 297 · cited 1×
“Nevertheless, with a view to avoid data collision and achieve unique mapping, visual information is embedded in continuous instead of discrete lower-dimensional spaces [391].”
BackgroundDouble window optimisation for constant time visual SLAM
Strasdat, H., Davison, A. J., Montiel, J. M. M., & Konolige, K. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126517 · Cited by 296
Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
Tian, Y., Chang, Y., Herrera Arias, F., Nieto-Granda, C., How, J. P., & Carlone, L. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3137751 · Cited by 288 · cited 1×
“, falsepositive loop closures) rejection is assigned to the back-end of SLAM [41]–[47].”
BackgroundPersistent Navigation and Mapping using a Biologically Inspired SLAM System
Milford, M., & Wyeth, G. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364909340592 · Cited by 286 · cited 1×
“To limit the number of database instances, clustering [137], [247], [254], [358]–[360] or pruning [361] methods can be”
MethodA comparison of loop closing techniques in monocular SLAM
Williams, B., Cummins, M., Neira, J., Newman, P., Reid, I., & Tardós, J. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.06.010 · Cited by 283 · cited 2×
“fidence [4]; the first one is image-to-image, and the second is sequence-to-sequence.”
BackgroundHighly scalable appearance-only SLAM - FAB-MAP 2.0
Cummins, M., & Newman, P. (2009) · Robotics: Science and Systems V · doi:10.15607/rss.2009.v.039 · Cited by 282
Schonberger, J. L., Pollefeys, M., Geiger, A., & Sattler, T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00721 · Cited by 267 · cited 1×
“, objects detected with CNN [152], [158], [168], [169], [173], [225], [228], [331], [332] or hand-crafted rules [231], [333]) showed that seman-”
Fast relocalisation and loop closing in keyframe-based SLAM
Mur-Artal, R., & Tardos, J. D. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906953 · Cited by 264
Visual place recognition: A survey from deep learning perspective
Zhang, X., Wang, L., & Su, Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107760 · Cited by 261 · cited 1×
“[8], Masone and Caputo [9], and Garg et al.”
BackgroundRobust monocular SLAM in dynamic environments
Tan, W., Liu, H., Dong, Z., Zhang, G., & Bao, H. (2013) · 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2013.6671781 · Cited by 249 · cited 2×
“[82], [86], [97], [117], [126], [375] were shown to perform better than a single k-d [76] or a Chow Liu tree [113].”
BackgroundMethodMapping Large Loops with a Single Hand-Held Camera
Clemente, L., Davison, A., Reid, I., Neira, J., & Tardos, J. (2007) · Robotics: Science and Systems III · doi:10.15607/rss.2007.iii.038 · Cited by 248 · cited 1×
“thus reducing the database’s search space [64], [65], [79], [142], [352]–[355].”
BackgroundObject recognition using multidimensional receptive field histograms
Schiele, B., & Crowley, J. L. (1996) · Lecture Notes in Computer Science · doi:10.1007/bfb0015571 · Cited by 243 · cited 9×
“HOG [175], which is the most frequently used technique, calculates every pixel’s gradient and creates a histogram based on the results (see Fig.”
MethodInfluentialAre We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four Seasons
Suenderhauf, N., Neubert, P., & Protzel, P. (2013) · QUT ePrints (Queensland University of Technology) · Cited by 241
Rejecting Mismatches by Correspondence Function
Li, X., & Hu, Z. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0318-x · Cited by 238 · cited 1×
“A correspondence function to model the bidirectional transformation, estimated by a support-vector regression technique, was designed by the authors in [328] to reject mismatches.”
MethodDOOR-SLAM: Distributed, Online, and Outlier Resilient SLAM for Robotic Teams
Lajoie, P.-Y., Ramtoula, B., Chang, Y., Carlone, L., & Beltrame, G. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2967681 · Cited by 236
Turcot, P., & Lowe, D. G. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457541 · Cited by 235 · cited 2×
“Different loop closure detection pipelines partially reduce their quantity by selecting the most informative ones [124], [143], or utilizing binary descriptors to avoid such cases [126], [136].”
BackgroundThe Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth
Ramezani, M., Wang, Y., Camurri, M., Wisth, D., Mattamala, M., & Fallon, M. (2020) · 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340849 · Cited by 235 · cited 1×
“The Newer College dataset [281] contains challenging image-sequences with aggressive shaking, fast motion, textureless surface, and rapid lighting change through a stereo camera system in New College, Oxford.”
MethodA visual bag of words method for interactive qualitative localization and mapping
Filliat, D. (2007) · Proceedings 2007 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2007.364080 · Cited by 230 · cited 2×
“This concept was introduced by Filliat [127], assuming an initial vocabulary that was gradually increased as new visual features were acquired.”
BackgroundExperience-based navigation for long-term localisation
Churchill, W., & Newman, P. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913499193 · Cited by 225 · cited 2×
“The authors in [307] learned how the appearance of a location changes gradually, while Neubert et al.”
BackgroundFANNG: Fast Approximate Nearest Neighbour Graphs
Harwood, B., & Drummond, T. W. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.616 · Cited by 222
SLAM-Loop Closing with Visually Salient Features
Newman, P., & Ho, K. (2006) · Proceedings of the 2005 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2005.1570189 · Cited by 215 · cited 1×
“point changes, local features were often selected for loop closure detection pipelines [16].”
BackgroundDetecting Loop Closure with Scene Sequences
Ho, K. L., & Newman, P. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-0020-1 · Cited by 213 · cited 2×
“On the contrary, sequence-to-sequence is typically based on the comparison of sub-maps [147]–[151].”
BackgroundFAB-MAP + RatSLAM: Appearance-based SLAM for multiple times of day
Glover, A. J., Maddern, W. P., Milford, M. J., & Wyeth, G. F. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509547 · Cited by 213 · cited 4×
“Lucia [285] Mono, color, frontal Outdoor, slightly changing, dynamic 640 × 480, 15 Hz X Oxford RobotCar [286] Trinocular stereo, color, frontal Outdoor, changing, highly dynamic 1280 × 960, 16 Hz X Nordland [249] Mono, color, frontal Outdoor, changing, static 1920 × 1080, 25 Hz X Mapillary [225] User submitted Outdoor…”
BackgroundInfluentialZaffar, M., Garg, S., Milford, M. J., Kooij, J. F. P., Flynn, D., McDonald-Maier, K. D., & Ehsan, S. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01469-5 · Cited by 212 · cited 1×
“the ground truth information, and the evaluation metrics [38].”
BackgroundRandomized algorithms and NLP: using locality sensitive hash function for high speed noun clustering
Ravichandran, D., Pantel, P., & Hovy, E. (2005) · Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05 · doi:10.3115/1219840.1219917 · Cited by 208 · cited 1×
“processing or off-line procedures [247], [372], [386]–[389], its discrete feature representations suffer from data collisions when their size is large [390].”
BackgroundOn the evaluation of illumination compensation algorithms
Vonikakis, V., Kouskouridas, R., & Gasteratos, A. C. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4783-x · Cited by 204 · cited 1×
“During navigation in a changing environment, the topological information about the robot’s relative movement becomes more important as noise from the sensory inputs is accumulated to an overwhelming degree [296], [297].”
BackgroundSelf-citationTopological mapping, localization and navigation using image collections
Fraundorfer, F., Engels, C., & Nister, D. (2007) · 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2007.4399123 · Cited by 202 · cited 1×
“often implemented based on the spatial information provided in local features, either hand-crafted or learned ones, by computing a fundamental/essential matrix or other epipolar constraints [78], [85], [89], [91], [113], [126], [137], [142]– [144], [148], [244], [271]–[273].”
BackgroundPairwise Consistent Measurement Set Maximization for Robust Multi-Robot Map Merging
Mangelson, J. G., Dominic, D., Eustice, R. M., & Vasudevan, R. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460217 · Cited by 202 · cited 1×
“, via robust pose-graph optimization [289]–[292].”
Convolutional Neural Network-based Place Recognition
Chen, Z., Lam, O., Jacobson, A., & Milford, M. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.1509 · Cited by 201 · cited 15×
“Deep learning has revolutionized many research areas [17], [18], with convolutional neural networks (CNNs) being used for various classification tasks as they can inherently learn high-level visual features.”
BackgroundInfluentialHierarchical optimization on manifolds for online 2D and 3D mapping
Grisetti, G., Kummerle, R., Stachniss, C., Frese, U., & Hertzberg, C. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509407 · Cited by 199
A Survey on Deep Visual Place Recognition
Masone, C., & Caputo, B. (2021) · IEEE Access · doi:10.1109/access.2021.3054937 · Cited by 192 · cited 2×
“Similar surveys can be found in the related literature, although they focus more on mapping techniques [4]–[6] or place recognition, relevant to robotics and other research areas, including computer vision, viz., Lowry et al. [7], Zhang et al. [8], Masone and Caputo [9], and Garg et al. [10].”
Babenko, A., & Lempitsky, V. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2361319 · Cited by 190
A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots
Thrun, S., Burgard, W., & Fox, D. (1998) · Autonomous Robots · doi:10.1023/a:1008806205438 · Cited by 189 · cited 1×
“Therefore, the robot’s motion estimation degenerates as the explored environment size grows, specifically with the traversed cycles’ size therein [40].”
BackgroundLearning View Graphs for Robot Navigation
Franz, M. O., Schölkopf, B., Mallot, H. A., & Bülthoff, H. H. (1998) · Autonomous Robots · doi:10.1023/a:1008821210922 · Cited by 187 · cited 1×
“becomes progressively less accurate, these approaches attempt to detect loops only upon the similarity between sensory measurements [57]–[59].”
BackgroundA probabilistic justification for using tf×idf term weighting in information retrieval
Hiemstra, D. (2000) · International Journal on Digital Libraries · doi:10.1007/s007999900025 · Cited by 187 · cited 1×
“Then, every image is represented via a vector of all its TF-IDF word values [192].”
MethodRobust Visual Robot Localization Across Seasons Using Network Flows
Naseer, T., Spinello, L., Burgard, W., & Stachniss, C. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.9057 · Cited by 186 · cited 4×
“[118], [285] or to predict and negate the effect of appearance variations [218], [250], [301]–[303].”
BackgroundInfluentialBRIEF-Gist - closing the loop by simple means
Sunderhauf, N., & Protzel, P. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6094921 · Cited by 184 · cited 1×
“[108], a global model of BRIEF (BRIEF stands for binary robust independent elementary features [189]) local descriptor to represent the entire image.”
MethodX-View: Graph-Based Semantic Multi-View Localization
Gawel, A., Don, C. D., Siegwart, R., Nieto, J., & Cadena, C. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2801879 · Cited by 183 · cited 3×
“On the contrary, representations provided by deep learning techniques show promising results on applications with challenging conditional and viewpoint changes [169], [224], [231], [299], [300].”
BackgroundKhaliq, A., Ehsan, S., Chen, Z., Milford, M. J., & McDonald-Maier, K. D. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2956352 · Cited by 182 · cited 4×
“, objects detected with CNN [152], [158], [168], [169], [173], [225], [228], [331], [332] or hand-crafted rules [231], [333]) showed that seman-”
MethodInfluentialDOOR-SLAM: Distributed, Online, and Outlier Resilient SLAM for Robotic TeamsPreprint
Lajoie, P., Ramtoula, B., Chang, Y., Carlone, L., & Beltrame, G. (2020) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 180
Robust Feature Matching Using Spatial Clustering With Heavy Outliers
Jiang, X., Ma, J., Jiang, J., & Guo, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2934572 · Cited by 179 · cited 1×
“processing or off-line procedures [247], [372], [386]–[389], its discrete feature representations suffer from data collisions when their size is large [390].”
BackgroundScalable k-NN graph construction for visual descriptors
Wang, J., Wang, J., Zeng, G., Tu, Z., Gan, R., & Li, S. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247790 · Cited by 178
Real-time topometric localization
Badino, H., Huber, D., & Kanade, T. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224716 · Cited by 175 · cited 2×
“[90]–[94] can improve performance, especially in changing environmental conditions [95], such a setup requires expensive hardware and additional calibration than camera-only ones [96].”
BackgroundMethodVision-based topological mapping and localization methods: A survey
Garcia-Fidalgo, E., & Ortiz, A. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.11.009 · Cited by 175 · cited 1×
“An extensive review regarding topological mapping is provided by the authors in [5].”
BackgroundLong-Term Recording from Single Neurons in Brain of Unrestrained Mammals
Strumwasser, F. (1958) · Science · doi:10.1126/science.127.3296.469 · Cited by 175
Only look once, mining distinctive landmarks from ConvNet for visual place recognition
Chen, Z., Maffra, F., Sa, I., & Chli, M. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202131 · Cited by 172 · cited 5×
“Finally, although impressive outcomes have been achieved by utilizing deep learning, such approaches are yet computationally costly [171].”
BackgroundInfluentialConvolutional neural network-based image representation for visual loop closure detection
Hou, Y., Zhang, H., & Zhou, S. (2015) · 2015 IEEE International Conference on Information and Automation · doi:10.1109/icinfa.2015.7279659 · Cited by 171 · cited 2×
“On the other hand, techniques which are built upon learned features typically demand an extensive labeled training set [170], [171], [221], [233], [292], [310]; however, there exist some exceptions that do not require environment-specific”
BackgroundPlace recognition using keypoint voting in large 3D lidar datasets
Bosse, M., & Zlot, R. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630945 · Cited by 171 · cited 1×
“Within the last years, since 3D maps [70] became more popular over traditional 2D [71], light detection and ranging (LiDAR) is established as the primary sensor for large-scale 3D geometric reconstructions [72].”
BackgroundLightweight Unsupervised Deep Loop Closure
Merrill, N., & Huang, G. P. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.032 · Cited by 171 · cited 1×
“exceptions that do not require environment-specific learning samples [156], [309].”
BackgroundA collection of outdoor robotic datasets with centimeter-accuracy ground truth
Blanco, J.-L., Moreno, F.-A., & Gonzalez, J. (2009) · Autonomous Robots · doi:10.1007/s10514-009-9138-7 · Cited by 168 · cited 2×
“Malaga 2009 Parking 6L [280] was recorded at an outdoor university campus parking lot via the stereo vision system of an electric buggy-typed vehicle.”
MethodProbabilistic Appearance Based Navigation and Loop Closing
Cummins, M., & Newman, P. (2007) · Proceedings 2007 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2007.363622 · Cited by 167 · cited 1×
“Similar to the Bayes approach discussed in [11], [15], later works followed the Bayesian filtering scheme to evaluate loop closure hypotheses [50], [97], [107], [113],”
MethodLocal Difference Binary for Ultrafast and Distinctive Feature Description
Yang, X., & Cheng, K.-T. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.150 · Cited by 164 · cited 1×
“showed that when applying disparity information on the local difference binary (LDB) descriptor [109], [110], failures due to perceptual aliasing could be reduced.”
BackgroundVisual SLAM for autonomous ground vehicles
Lategahn, H., Geiger, A., & Kitt, B. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5979711 · Cited by 159
Vast-scale Outdoor Navigation Using Adaptive Relative Bundle Adjustment
Sibley, G., Mei, C., Reid, I., & Newman, P. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364910369268 · Cited by 156 · cited 1×
“However, many challenges emerge when splitting the map into sub-maps, such as optimal size, sub-map overlapping throughout database searching, and uniform semantic map definition [87].”
BackgroundUnified Loop Closing and Recovery for Real Time Monocular SLAM
Eade, E. D., & Drummond, T. W. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.6 · Cited by 153 · cited 2×
“and a corresponding node while the current node rectifying this way the accumulated mapping error [60] (see Fig.”
BackgroundNavigation using an appearance based topological map
Booij, O., Terwijn, B., Živković, Z., & Kröse, B. (2007) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2007.364081 · Cited by 150
LDB: An ultra-fast feature for scalable Augmented Reality on mobile devices
Yang, X., & Cheng, K.-T. T. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402537 · Cited by 148 · cited 1×
“showed that when applying disparity information on the local difference binary (LDB) descriptor [109], [110], failures due to perceptual aliasing could be reduced.”
BackgroundDetect-To-Retrieve: Efficient Regional Aggregation for Image Search
Teichmann, M., Araújo, A. D. M., Zhu, M., & Sim, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00525 · Cited by 148
Where Is Your Place, Visual Place Recognition?
Garg, S., Fischer, T., & Milford, M. J. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/603 · Cited by 147 · cited 1×
“[10] gives a broader discussion about the differences between visual place recognition in the computer vision and robotics communities.”
BackgroundEfficient estimation of accurate maximum likelihood maps in 3D
Grisetti, G., Grzonka, S., Stachniss, C., Pfaff, P., & Burgard, W. (2007) · 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2007.4399030 · Cited by 145 · cited 1×
“, trees [373]–[377] and graphs [142], [378]–[381].”
ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes
Liu, D., Long, C., Zhang, H., Yu, H., Dong, X., & Xiao, C. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00816 · Cited by 142 · cited 1×
“Historically, visual place recognition depicts a related task, studied intensively by the researchers in computer vision society within a broad spectrum of applications [33], including 3D reconstruction [34], map fusion [35], augmented reality [36], and structure-frommotion [37].”
BackgroundKonolige, K., & Bowman, J. (2009) · 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2009.5354121 · Cited by 138 · cited 1×
“To limit the number of database instances, clustering [137], [247], [254], [358]–[360] or pruning [361] methods can be”
MethodLoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics
Garg, S., Sünderhauf, N., & Milford, M. J. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.022 · Cited by 137 · cited 3×
“Using visual semantics, extracted via RefineNet [328], multi-frame LoST-X [170]”
MethodInfluentialSeqNet: Learning Descriptors for Sequence-Based Hierarchical Place Recognition
Garg, S., & Milford, M. J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3067633 · Cited by 137 · cited 2×
“or they describe each submap through sequential descriptors [151], [175], [178], [179].”
BackgroundNavigating, Recognizing and Describing Urban Spaces With Vision and Lasers
Newman, P., Sibley, G., Smith, M., Cummins, M., Harrison, A., Mei, C., Posner, I., Shade, R., Schroeter, D., Murphy, L., et al. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364909341483 · Cited by 134 · cited 1×
“often implemented based on the spatial information provided in local features, either hand-crafted or learned ones, by computing a fundamental/essential matrix or other epipolar constraints [78], [85], [89], [91], [113], [126], [137], [142]– [144], [148], [244], [271]–[273].”
BackgroundAppearance-based loop detection from 3D laser data using the normal distributions transform
Magnusson, M., Andreasson, H., Nüchter, A., & Lilienthal, A. J. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152712 · Cited by 133
Keypoint design and evaluation for place recognition in 2D lidar maps
Bosse, M. C., & Zlot, R. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.009 · Cited by 132 · cited 1×
“Within the last years, since 3D maps [70] became more popular over traditional 2D [71], light detection and ranging (LiDAR) is established as the primary sensor for large-scale 3D geometric reconstructions [72].”
BackgroundScene Signatures: Localised and Point-less Features for Localisation
McManus, C., Upcroft, B., & Newmann, P. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.023 · Cited by 131 · cited 10×
“More specifically, deep learning approaches can be utilized to either construct description features with increased robustness to perceptual changes [111],”
MethodInfluentialAll-environment visual place recognition with SMART
Pepperell, E., Corke, P., & Milford, M. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907067 · Cited by 131 · cited 1×
“and large-scale SLAM autonomy, previously visited locations in dynamic environments need to be recognized under different day periods and scenes with changeable illumination and seasonal conditions [93], [190], [258], [295].”
BackgroundRöwekämper, J., Sprunk, C., Tipaldi, G. D., Stachniss, C., Pfaff, P., & Burgard, W. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385988 · Cited by 131 · cited 1×
“Metric maps provide geometrically accurate representations of the robot’s surroundings, enabling centimeter-level accuracy for localization [51].”
Background
Research works printed but not linked: 16
- bruce, 2015, The SFU mountain dataset: Semi-structured woodland trails under changing environmental conditions, Proc IEEE Int Conf Robot Automat Workshop
- biederman, 1988, Aspects and extensions of a theory of human image understanding, Computational Processes in Human Vision An Interdisciplinary Perspective, 370
- garg, 2018, Don’t look back: Robustifying place categorization for viewpoint- and condition-invariant place recognition, Proc IEEE Int Conf Robot Automat (ICRA), 3645
- bowman, 2021, Robust and efficient semantic SLAM with semantic keypoints, Proc AAAI Nat Conf Artif Intell, 1
- maddern, 2014, Illumination invariant imaging: Applications in robust vision-based localisation, mapping and classification for autonomous vehicles, Proc IEEE Int Conf Robot Automat, 3
- rolet, 2012, Integrated recognition, localization and detection using convolutional networks, Proc Eur Conf Mach Learn, 1255
- ackerman, 2014, Dyson's robot vacuum has 360-degree camera tank treads cyclone suction
- goodfellow, 2016, Deep Learning, 1
- mactavish, 2014, Towards hierarchical place recognition for long-term autonomy, Proc IEEE Int Conf Robot Automat Workshop, 1
- gollub, 2017, A partitioned approach for efficient graph-based place recognition, Proc IEEE/RSJ Int Conf Intell Robots Syst /Workshop Planning Perception Navigat Intell Veh, 1
- 10.1207/s15516709cog0202_3 · doi:10.1207/s15516709cog0202_3 · Paper page
- kuipers, 1988, A robust qualitative method for spatial learning in unknown environments, Proc 7th AAAI Nat Conf Artif Intell, 774
- milford, 2015, Towards visual SLAM with event-based cameras, Proc Robot Sci Syst, 1
- finman, 2015, Toward object-based place recognition in dense RGB-D maps, Proc IEEE Int Conf Robot Automat, 76, 1
- 10.1177/0278364914551008 · DOI
- 10.1109/ICRA.2018.8462894 · DOI
Cited by
Review of simultaneous localization and mapping (SLAM) for construction robotics applications
Yarovoi, A., & Cho, Y. K. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105344 · Cited by 128
A review of visual SLAM for robotics: evolution, properties, and future applications
Al-Tawil, B., Hempel, T., Abdelrahman, A. A., & Al-Hamadi, A. K. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1347985 · Cited by 126
Konstantinidis, F. K., Myrillas, N., Tsintotas, K. A., Mouroutsos, S. G., & Gasteratos, A. C. (2023) · International Journal of Production Research · doi:10.1080/00207543.2023.2270588 · Cited by 77
Self-citationVisual Place Recognition: A Tutorial [Tutorial]
Schubert, S., Neubert, P., Garg, S., Milford, M. J., & Fischer, T. (2023) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2023.3310859 · Cited by 102
“In fact, one of the original drivers for VPR research was the generation of loop closures for SLAM systems, that is, recognizing a place when revisiting it (e.g., in a loop) and tying the current observation with that already in the map (i.e., closure) [8].”
BackgroundLiDAR, IMU, and camera fusion for simultaneous localization and mapping: a systematic review
Fan, Z., Zhang, L., Wang, X., Shen, Y., & Deng, F. Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11187-w · Cited by 107
Metadata
- Authors
- Tsintotas, K. A., Bampis, L., & Gasteratos, A.
- Affiliations
- Democritus University of Thrace (GR)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2022-11
- Volume
- 23
- Issue
- 11
- Pages
- 19929-19953
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W4225108957
- Cited by
- 175
- References
- 397
- Citations by year
- 2026: 28 · 2025: 44 · 2024: 51 · 2023: 40 · 2022: 12
- FWCI
- 16.35
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- SLAM, place recognition, feature extraction, environment representation, dynamic environments, robot navigation, map consistency
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.