Machine Learning for High-Speed Corner Detection
The DOI matches its Crossref record; 32 of the 33 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Moreover, the efficiency of HF-net2 was tested and compared with several wellknown handcrafted algorithms for keypoint detection and description including Harris [4], FAST [6], SIFT [9] and ORB [8].”
From Keypoint Detection and Description through Deep Learning in Unstructured Environments (2023) · cites this paper as [6]
In the citing paper
“As the mission distance increase, the planetary rovers increasingly require safer, more real-time, and more accurate navigation systems [29,86,87].”
From Semantic Terrain Segmentation in the Navigation Vision of Planetary Rovers—A Systematic Literature Review (2022) · cites this paper as [86]
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Rosten and Drummond 2006
Citations
Cites
Distinctive 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 1×
“Lowe [12] obtains scale invariance by convolving the image with a Difference of Gaussians (DoG) kernel at multiple scales, retaining locations which are optima in scale as well as space.”
MethodQuinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439 · cited 1×
“Stage 2 employs the algorithm used in ID3[31] and begins by selecting the x which yields the most information about whether the candidate pixel is a corner, measured by the entropy of Kp.”
MethodA 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 2×
“A number of suggestion have [5,7,8,9] been made for how to compute the corner strength from H and these have been all shown [10] to be equivalent to various matrix norms of H Zheng et al.”
MethodResultShi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 5×
“Based on the assumption of affine image deformation, a mathematical analysis led Shi and Tomasi[7] conclude that it is better to use the smallest eigen value of H as the corner strength function: C = min (λ1, λ2).”
BackgroundMethodResultInfluentialHaralock, R. M., & Shapiro, L. G. (1991) · Addison-Wesley Longman Publishing Co., Inc. eBooks · Cited by 3,933
SUSAN—a new approach to low level image processing
Smith, S. M., & Brady, J. M. (1997) · International Journal of Computer Vision · doi:10.1023/a:1007963824710 · Cited by 3,333 · cited 2×
“Smith and Brady[27] claim that the SUSAN corner detector performs well in the presence of noise since it does not compute image derivatives, and hence, does not amplify noise.”
BackgroundMethodEvaluation of Interest Point Detectors
Schmid, C., Mohr, R., & Bauckhage, C. (2000) · International Journal of Computer Vision · doi:10.1023/a:1008199403446 · Cited by 1,484 · cited 4×
“When measuring reliability, what is important is if the same real-world features are detected from multiple views [1] This is the definition which will be used here.”
BackgroundMethodInfluentialAn Affine Invariant Interest Point Detector
Mikolajczyk, K., & Schmid, C. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-47969-4_9 · Cited by 1,325 · cited 2×
“Recently, scale invariance has been extended to consider features which are invariant to affine transformations [14,16,17].”
BackgroundFusing points and lines for high performance tracking
Rosten, E., & Drummond, T. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.104 · Cited by 1,119 · cited 2×
“In addition, the approach allows the detector to be generalised, producing a suite of high-speed detectors which we currently use for real-time tracking [2] and AR label placement [3].”
BackgroundSelf-citationIndexing based on scale invariant interest points
Mikolajczyk, K., & Schmid, C. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937561 · Cited by 1,101 · cited 3×
“Scale-space techniques have also been combined with the Harris approach in [15] which computes Harris corners at multiple scales and retains only those which are also optima of the LoG response across scales.”
Method
Research works printed but not linked: 3
- Noble, A.: Descriptions of image surfaces. PhD thesis, Department of Engineering Science, University of Oxford (1989)
- James, L., Crowley, O.R.: Fast computation of characteristic scale using a half octave pyramid. In: Scale Space 2003: 4th International Conference on Scale-Space theories in Computer Vision, Isle of Skye, Scotland (2003)
- Performenace Evaluation of Corner Detection Algorithms under Affine and Similarity Transforms. In: Cootes, T.F., Taylor, C. (eds.) 12th British Machine Vision Conference, Manchester, British Machine Vision Assosciation (2001)
Cited by
Items 101–200 of 1,007
Fast Event-based Corner Detection
Mueggler, E., Bartolozzi, C., & Scaramuzza, D. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.33 · Cited by 194
S-PTAM: Stereo Parallel Tracking and Mapping
Pire, T., Fischer, T., Castro, G., De Cristóforis, P., Civera, J., & Jacobo Berlles, J. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.019 · Cited by 192
“In [63] the FAST/BRIEF extractor is recommended in the same context as the experiments conducted in the present work.”
BackgroundMethodInfluentialGeorgiou, T., Liu, Y., Chen, W., & Lew, M. (2020) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-019-00183-w · Cited by 187
“Yu et al. [325] developed a generalization of the FAST [223] detector to the spatiotemporal case, which they call V-FAST.”
BackgroundSURFTrac: Efficient tracking and continuous object recognition using local feature descriptors
Ta, D.-N., Chen, W.-C., Gelfand, N., & Pulli, K. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206831 · Cited by 192
“Alternatively, one can imagine a hybrid algorithm where motion estimation is done through lightweight features such as FAST corners [19, 20] or Harris corners [9] and object recognition is done through robust features.”
BackgroundA learned feature descriptor for object recognition in RGB-D data
Blum, M., Springenberg, J. T., Wulfing, J., & Riedmiller, M. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6225188 · Cited by 189
“Approaches to detect interest points traditionally comprise methods such as SIFT [3], SURF [4] and FAST [15] which”
MethodUnsupervised learning to detect loops using deep neural networks for visual SLAM system
Gao, X., & Zhang, T. (2017) · Autonomous Robots · doi:10.1007/s10514-015-9516-2 · Cited by 186
“There are numerous types of features and the quantity of them is still growing as the proposing of new features and improving of the traditional ones (Rosten and Drummond 2006; Rublee et al. 2011; Wang and Lin 2014).”
BackgroundAccurate Calibration of LiDAR-Camera Systems Using Ordinary Boxes
Pusztai, Z., & Hajder, L. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.53 · Cited by 177
OnePose: One-Shot Object Pose Estimation without CAD Models
Sun, J., Wang, Z., Zhang, S., He, X., Zhao, H., Zhang, G., & Zhou, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00670 · Cited by 177
“Traditionally, the localization problem is solved by finding 2D-3D correspondences between input RGB images and a 3D model from SfM with hand-crafted local features like SIFT [20], FAST [29] and ORB [30].”
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
Lindenberger, P., Sarlin, P.-E., Larsson, V., & Pollefeys, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00593 · Cited by 172
Vision-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
“Harris [73] Corners X (X) (X) Shi and Tomasi [74] Corners X SUSAN [75] Corners X FAST [76] Corners X (X) FAST-ER [77] Corners X (X) ORB [78] Corners X X AGAST [79] Corners X (X) BRISK [80] Corners X X SIFT [81] Blobs X X SURF [82] Blobs X X CenSure [63] Blobs X X Star [83] Blobs X X SUSurE [84] Blobs X X KAZE [85] Blo…”
BackgroundYan, C., Xie, H., Liu, S., Yin, J., Zhang, Y., & Dai, Q. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2749977 · Cited by 176
Raza, A., Bardhan, S., Xu, L., Yamijala, S. S. R. K. C., Lian, C., Kwon, H., & Wong, B. M. (2019) · Environmental Science & Technology Letters · doi:10.1021/acs.estlett.9b00476 · Cited by 173
Wu, K. J., Guo, C. X., Georgiou, G., & Roumeliotis, S. I. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989603 · Cited by 174
“Around 200 FAST corners [18] are extracted from each image and tracked using the Kanade-Lucas-Tomasi (KLT) algorithm [19] at a frequency of 15 Hz.”
MethodYe, Y., Zhu, B., Tang, T., Yang, C., Xu, Q., & Zhang, G. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.04.011 · Cited by 166
Learning Universal Adversarial Perturbations with Generative Models
Hayes, J., & Danezis, G. (2018) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00015 · Cited by 187
Keyframe-based monocular SLAM: design, survey, and future directions
Younes, G., Asmar, D., Shammas, E., & Zelek, J. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.09.010 · Cited by 191
“Feature detector examples include Hessian corner detector (Beaudet, 1978), Harris detector (Harris and Stephens, 1988), Shi-Tomasi corners (Shi and Tomasi, 1994), Laplacian of Gaussian detector (Lindeberg, 1998), MSER (Matas et al, 2002), Difference of Gaussian (Lowe, 2004) and the accelerated segment test family of d…”
MethodInfluential6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
Wang, C., Martin-Martin, R., Xu, D., Lv, J., Lu, C., Fei-Fei, L., Savarese, S., & Zhu, Y. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9196679 · Cited by 164
“Classical methods detect and match keypoints based on hand-designed local features [4, 7, 30, 37, 38].”
MethodBachrach, A., Prentice, S., He, R., Henry, P., Huang, A. S., Krainin, M., Maturana, D., Fox, D., & Roy, N. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364912455256 · Cited by 162
“Specifically, the visual odometry uses the FAST feature detector developed by Rosten and Drummond (2006), the rotation estimation described by Mei et al. (2009), feature matching described by Nistér et al. (2004), and the inlier detection described by Howard (2008).”
BackgroundMethodInfluentialMODS: Fast and robust method for two-view matching
Mishkin, D., Matas, J., & Perdoch, M. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.08.005 · Cited by 158
“Fast detectors [12], [14] and binary descriptors [15], [16], [17] have been proposed to make matching significantly faster at the cost of decreasing tolerance to the scale, rotation and affine changes.”
BackgroundVast-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
“We use FAST features (Rosten and Drummond 2006) extracted at different levels of a scale-space pyramid for robustness to image blur.”
MethodAsynchronous, Photometric Feature Tracking Using Events and Frames
Gehrig, D., Rebecq, H., Gallego, G., & Scaramuzza, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01258-8_46 · Cited by 179
A state-of-the-art review on mobile robotics tasks using artificial intelligence and visual data
Cebollada, S., Payá, L., Flores, M., Peidró, A., & Reinoso, O. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114195 · Cited by 151
Robust Vehicle Detection and Distance Estimation Under Challenging Lighting Conditions
Rezaei, M., Terauchi, M., & Klette, R. (2015) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2015.2421482 · Cited by 153
“Among developed feature point detectors such as FAST [51], ORB [52], or FREAK [53], we obtained the best performance with the Shi–Tomasi method [54] for detecting “appropriate” corner points in our road scene application context.”
MethodVisual and Visual‐Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking
Servières, M., Renaudin, V., Dupuis, A., & Antigny, N. (2021) · Journal of Sensors · doi:10.1155/2021/2054828 · Cited by 181
Robust Real-Time Visual Odometry with a Single Camera and an IMU
Kneip, L., Chli, M., & Siegwart, R. (2011) · Procedings of the British Machine Vision Conference 2011 · doi:10.5244/c.25.16 · Cited by 149
“As shown in Figure 10, only the FAST or AGAST based solutions are able to run in real-time.”
MethodInfluentialJoint Representation Learning and Keypoint Detection for Cross-View Geo-Localization
Lin, J., Zheng, Z., Zhong, Z., Luo, Z., Li, S., Yang, Y., & Sebe, N. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3175601 · Cited by 198
“To speed up keypoint retrieval, FAST [57] counts the number of brighter or darker pixels around a point followed by a decision tree to improve performance and efficiency.”
BackgroundZaffar, 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
“FAST (Rosten and Drummond (2006)) which is a popular high-speed corner detector has been used in combination with the SIFT descriptor for SLAM by Mei et al. (2009).”
MethodMapping and localization from planar markers
Muñoz‐Salinas, R., Marín-Jiménez, M. J., Yeguas-Bolívar, E., & Medina-Carnicer, R. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.08.010 · Cited by 169
LNIFT: Locally Normalized Image for Rotation Invariant Multimodal Feature Matching
Li, J., Xu, W., Shi, P., Zhang, Y., & Hu, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3165940 · Cited by 193
“ORB improves the FAST [31] detector to achieve rotation invariance.”
BackgroundMethodHierarchical registration of unordered TLS point clouds based on binary shape context descriptor
Dong, Z., Yang, B., Liang, F., Huang, R., & Scherer, S. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.06.018 · Cited by 163
VDO-SLAM: A Visual Dynamic Object-aware SLAM SystemPreprint
Zhang, J., Henein, M., Mahony, R. E., & Ila, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11052 · Cited by 235
Rodríguez-Canosa, G. R., Thomas, S., del Cerro, J., Barrientos, A., & MacDonald, B. A. (2012) · Remote Sensing · doi:10.3390/rs4041090 · Cited by 148
“As shown in Figure 2(b), the second approach consists of applying the 9 point FAST feature detection developed by Rosten et al. in [24].”
MethodIntervention AUVs: The next challenge
Ridao, P., Carreras, M., Ribas, D., Sanz, P. J., & Oliver, G. (2015) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2015.09.015 · Cited by 159
Learning to Detect Objects with a 1 Megapixel Event CameraPreprint
Perot, E., de Tournemire, P., Nitti, D., Masci, J., & Sironi, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.13436 · Cited by 382
“For the RGB stream, we simply extract FAST [72] points.”
MethodKonolige, K., & Bowman, J. (2009) · 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2009.5354121 · Cited by 138
“VO uses FAST features [22] and SAD correlation, continuously matching the current frame of the video stream against the last keyframe, until a given distance has transpired or the match becomes too weak.”
MethodA Comprehensive Review of Vision-Based 3D Reconstruction Methods
Zhou, L., Wu, G., Zuo, Y., Chen, X., & Hu, H. (2024) · Sensors · doi:10.3390/s24072314 · Cited by 190
Advances in Human Action Recognition: A SurveyPreprint
Cheng, G., Wan, Y., Saudagar, A. N., Namuduri, K. R., & Buckles, B. P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.05964 · Cited by 169
“The FAST detector [65] was extended to V-FAST for video interest point detection.”
MethodToward Geometric Deep SLAMPreprint
DeTone, D., Malisiewicz, T., & Rabinovich, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.07410 · Cited by 194
“We evaluate the MagicPoint component of our system against traditional corner detection baselines like the FAST [20] corner detector, the Harris [15] corner detector, and the “Good Features to Track” or Shi [21] corner detector.”
MethodAutomated Low-Cost Smartphone-Based Lateral Flow Saliva Test Reader for Drugs-of-Abuse Detection
Carrio, A., Sampedro, C., Sánchez-López, J. L., Pimienta, M., & Campoy, P. (2015) · Sensors · doi:10.3390/s151129569 · Cited by 152
“ORB uses the well-known FAST keypoints [17,18] with a circular radius of nine (FAST-9) and introduces orientation to the keypoint by measuring the intensity centroid (oFAST).”
MethodIdentifying the Contributions of Multi-Source Data for Winter Wheat Yield Prediction in China
Cao, J., Zhang, Z., Tao, F., Zhang, L., Luo, Y., Han, J., & Li, Z. (2020) · Remote Sensing · doi:10.3390/rs12050750 · Cited by 147
Integrating the physical environment into mobile remote collaboration
Gauglitz, S., Lee, C., Turk, M., & Höllerer, T. (2012) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/2371574.2371610 · Cited by 147
“On each level, keypoints are detected with the FAST corner detector [32], and a subset”
MethodComputer Vision, Machine Learning, and the Promise of Phenomics in Ecology and Evolutionary Biology
Lürig, M., Donoughe, S., SVENSSON, E. I., Porto, A., & Tsuboi, M. (2021) · Frontiers in Ecology and Evolution · doi:10.3389/fevo.2021.642774 · Cited by 158
Real-time loop detection with bags of binary words
Gálvez‐López, D., & Tardós, J. D. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094885 · Cited by 158
“2) Matches against images gathered close in time are grouped together as a single match.”
BackgroundCombining Harris interest points and the SIFT descriptor for fast scale-invariant object recognition
Azad, P., Asfour, T., & Dillmann, R. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354611 · Cited by 135
“In parallel, Wagner et al. have developed a similar approach based on the same idea, using a combination of the SIFT descriptor and Ferns descriptor [19] together with the FAST detector [20], as presented in [21].”
MethodInvolvement of Machine Learning for Breast Cancer Image Classification: A Survey
Nahid, A.-A., & Kong, Y. (2017) · Computational and Mathematical Methods in Medicine · doi:10.1155/2017/3781951 · Cited by 154
Semantics lead all: Towards unified image registration and fusion from a semantic perspective
Xie, H., Zhang, Y., Qiu, J., Zhai, X., Liu, X., Yang, Y., Zhao, S., Luo, Y., & Zhong, J. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101835 · Cited by 146
Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features
Gabriel Takacs, A., Chandrasekhar, V., Tsai, S. S., Chen, D. M., Grzeszczuk, R., & Girod, B. (2010) · 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.2010.5540116 · Cited by 133
“First, we apply the FAST [20] interest point detector on each level of an image pyramid.”
MethodVision-Based Detection and Distance Estimation of Micro Unmanned Aerial Vehicles
Gökçe, F., Üçoluk, G., Şahin, E., & Kalkan, S. (2015) · Sensors · doi:10.3390/s150923805 · Cited by 150
“Popular examples of keypoint detectors include fast corner detection (FAST) [14,15], Harris corner detection (HARRIS) [16], maximally stable extremal region extractor (MSER) [17] and good features to track (GFTT) [18] (see [19] for a survey of local keypoint detectors).”
BackgroundA Review of Body Measurement Using 3D Scanning
Bartol, K., Bojanic, D., Petković, T., & Pribanić, T. (2021) · IEEE Access · doi:10.1109/access.2021.3076595 · Cited by 163
“First, the keypoints are detected [10], [104], [138], [139] and matched between the images [36] to find the correspondences.”
BackgroundCvišić, I., Ćesić, J., Marković, I., & Petrović, I. (2018) · Journal of Field Robotics · doi:10.1002/rob.21762 · Cited by 133
A Comprehensive Review on Autonomous Navigation
Nahavandi, S., Alizadehsani, R., Nahavandi, D., Mohamed, S. M. K., Mohajer, N., Rokonuzzaman, M., & Hossain, I. (2025) · ACM Computing Surveys · doi:10.1145/3727642 · Cited by 189
“PTAM uses FAST-10 corner detector [246] for feature extraction.”
HPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Balntas, V., Lenc, K., Vedaldi, A., Tuytelaars, T., Matas, J., & Mikolajczyk, K. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2915233 · Cited by 132
“One of the first successful attempts was FAST [24] and FAST-ER [27], which mainly addressed the efficiency of feature extraction for real time applications.”
Learning Covariant Feature Detectors
Lenc, K., & Vedaldi, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49409-8_11 · Cited by 151
“Features DetNet-L DetNet-S DoG Harris FAST Fig.”
BackgroundMethodInfluentialEfficient online structured output learning for keypoint-based object tracking
Hare, S., Saffari, A., & Torr, P. H. 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.2012.6247889 · Cited by 130
“Recently, there has been significant interest in developing approaches suitable for low-powered mobile devices such as smartphones and tablets, which are becoming increasingly popular platforms for computer vision applications [3,10,14,15].”
BackgroundTriantafyllopoulos, G., Dimaratos, A. M., Ntziachristos, L. D., Bernard, Y., Dornoff, J., & Samaras, Z. C. (2019) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2019.02.144 · Cited by 133
Event-aided Direct Sparse Odometry
Hidalgo‐Carrió, J., Gallego, G., & Scaramuzza, D. (2022) · 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/cvpr52688.2022.00569 · Cited by 179
“Then FAST corners [54] are extracted and tracked separately on the event frames and the grayscale frames, and are passed to a state-of-the-art geometric feature-based back-end [55].”
MethodRolling shutter bundle adjustment
Hedborg, J., Forssen, P.-E., Felsberg, M., & Ringaby, E. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247831 · Cited by 129
Robust Model-Based Monocular Pose Initialization for Noncooperative Spacecraft Rendezvous
Sharma, S., Ventura, J., & D’Amico, S. (2018) · Journal of Spacecraft and Rockets · doi:10.2514/1.a34124 · Cited by 128
“accelerated segment test (FAST) [49]; or 3) using key-point detectors such as binary robust invariant scalable keypoints (BRISK) [50].”
BackgroundMethodInfluentialA review of monocular visual odometry
He, M., Zhu, C., Huang, Q., Ren, B., & Liu, J. (2019) · The Visual Computer · doi:10.1007/s00371-019-01714-6 · Cited by 140
“However, the popularity of some computable feature extraction/description algorithms, such as oriented FASTand rotatedBRIEF (ORB) [42] andBinaryRobust Invariant Scalable Keypoints (BRISK) [43], has gradually exceeded that of the Harris corner points or SIFT/SURF, which were not well tracked before, and the former grou…”
MethodGrauman, K., & Leibe, B. (2011) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.2200/s00332ed1v01y201103aim011 · Cited by 126
“Consequently, several approaches have been proposed in order to speed up the interest region extraction and/or description stages (N. Cornelis 2008, Bay et al. 2006, 2008, Rosten & Drummond 2008).”
MethodReal-time Action Recognition by Spatiotemporal Semantic and Structural Forests
Yu, T.-H., Kim, T., & Cipolla, R. (2010) · British Machine Vision Conference (BMVC) · doi:10.5244/c.24.52 · Cited by 141
“A novel spatiotemporal interest point detector, called VFAST, is designed based on the FAST 2D corners [18].”
BackgroundMethodA Monocular Vision Sensor-Based Efficient SLAM Method for Indoor Service Robots
Lee, T.-J., Kim, C.-H., & Cho, D. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2826471 · Cited by 129
“For corner detection, the algorithm [5] with the threshold 20 is used.”
MethodRecent developments and applications of simultaneous localization and mapping in agriculture
Ding, H., Zhang, B., Zhou, J. C., Yan, Y., Tian, G., & Gu, B. (2022) · Journal of Field Robotics · doi:10.1002/rob.22077 · Cited by 146
“Furthermore, a high‐speed corner detection method: Features from Accelerated Segment Test (FAST) also had a strong computation speed (Rosten & Drummond, 2006), but lost the orientation information.”
MethodReal-time panoramic mapping and tracking on mobile phones
Wagner, D., Mulloni, A., Langlotz, T., & Schmalstieg, D. (2010) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr.2010.5444786 · Cited by 124
“The tracker applies the FAST corner detector [10] on finished cells to extract keypoints.”
MethodVisual SLAM for robot navigation in healthcare facility
Fang, B., Mei, G., Yuan, X., Wang, L., Wang, Z., & Wang, J. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107822 · Cited by 137
MonoFusion: Real-time 3D reconstruction of small scenes with a single web camera
Pradeep, V., Rhemann, C., Izadi, S., Zach, C., Bleyer, M., & Bathiche, S. (2013) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2013.6671767 · Cited by 131
“For scale-invariant salient corner detection and matching, an input image Ii is first converted into a 3-level multi-scale Gaussian pyramid [16] and the FAST interest point detector [28] is applied over each level in the pyramid.”
MethodCopy-move forgery detection based on scaled ORB
Zhu, Y. H., Shen, X., & Chen, H. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2431-2 · Cited by 131
“Key points are extracted by using the simple and rapid algorithm, FAST (Features from Accelerated Segment Test) [18, 19].”
MethodStereo parallel tracking and mapping for robot localization
Pire, T., Fischer, T., Civera, J., Cristoforis, P. D., & Berlles, J. J. (2015) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros.2015.7353546 · Cited by 120
“Although the method performs slower than other state-of-the-art detection algorithms such as FAST [19], it enforces a “good” spatial distribution of the selected points over the image by means of non-maximum suppression, which significantly increases the robustness of the pose refinement during tracking.”
MethodLearning Discriminative and Transformation Covariant Local Feature Detectors
Zhang, X., Yu, F. X., Karaman, S., & Chang, S. (2017) · 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.2017.523 · Cited by 132
“[21] propose to learn a fast feature detector from the FAST detector aiming at speeding up the detection.”
BackgroundMethodResultInfluentialVision-Based Construction Worker Activity Analysis Informed by Body Posture
Roberts, D., Calderon, W. T., Tang, S., & Golparvar‐Fard, M. (2020) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000898 · Cited by 131
Asynchronous event-based corner detection and matching
Clady, X., Ieng, S.-H., & Benosman, R. B. (2015) · Neural Networks · doi:10.1016/j.neunet.2015.02.013 · Cited by 119
“…measure (Moravec, 1980) derived from mathematical analysis (e.g. con-tour’s local curvature Mokhtarian & Suomela, 1998, relying on an eigenvalue decomposition of a second-moment matrix Harris & Stephens, 1988) or selected as the output from a machine learning process (Rosten & Drummond, 2006).”
MethodImprovements to Target-Based 3D LiDAR to Camera Calibration
Huang, J.-K., & Grizzle, J. W. (2020) · IEEE Access · doi:10.1109/access.2020.3010734 · Cited by 122
“We assume that these have been obtained through the user’s preferred method, such as corner detection [23], [24], [25], edge detection [26], [27], [28], or even manual selection.”
MethodBoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
Cui, Y., Chen, X., Zhang, Y., Dong, J., Wu, Q., & Zhu, F. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3221336 · Cited by 140
“DBoW2 [4], used for the first time bag of binary words based on BRIEF descriptors [20] with the very efficient FAST feature detector [21], greatly improving the efficiency of loop retrieval.”
MethodEye blink based fatigue detection for prevention of Computer Vision Syndrome
Divjak, M., & Bischof, H. (2009) · Machine Vision Applications · Cited by 117
Visual SLAM for underwater vehicles: A survey
Zhang, S., Zhao, S., An, D. U., Liu, J., Wang, H., Yu, F., Li, D., & Zhao, R. (2022) · Computer Science Review · doi:10.1016/j.cosrev.2022.100510 · Cited by 135
A survey on image and video stitching
Lyu, W., Zhou, Z., Chen, L., & Zhou, Y. (2019) · Virtual Reality & Intelligent Hardware · doi:10.3724/sp.j.2096-5796.2018.0008 · Cited by 134
Scene Signatures: Localised and Point-less Features for Localisation
McManus, C., Upcroft, B., & Newmann, P. (2014) · Robotics: Science and Systems X · doi:10.15607/rss.2014.x.023 · Cited by 117
“Rublee et al. [10] developed a new feature called ORB, which builds upon the FAST [15] detector and the BRIEF [9] descriptor.”
MethodBEBLID: Boosted efficient binary local image descriptor
Suárez, I., Sfeir, G., Buenaposada, J. M., & Baumela, L. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.04.005 · Cited by 128
“There is a plethora of very efficient detectors for various low level structures such as corners [20], segments [31], lines [25] and regions [14], that may be described by real valued [13, 5] or binary [7, 21, 2, 4, 11, 10] descriptors, being the binary ones the fastest to extract and match.”
BackgroundDiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Lan, S., Yu, Z., Choy, C., Radhakrishnan, S., Liu, G., Zhu, Y., Davis, L. S., & Anandkumar, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00339 · Cited by 145
“Over the past decade, the methods have evolved from hand-crafted ones [9–11] to learning-based ones using decision tree and deep neural networks [12–17] with extremely abundant literature.”
MethodGlobal pose estimation using multi-sensor fusion for outdoor Augmented Reality
Schall, G., Wagner, D., Reitmayr, G., Taichmann, E., Wieser, M., Schmalstieg, D., & Hofmann-Wellenhof, B. (2009) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2009.5336489 · Cited by 113
“The locations of the interest points are selected in the map using the FAST [18] corner detector in areas of the map that have already been finished.”
MethodLee, W., Lenferink, A. T. M., Otto, C., & Offerhaus, H. L. (2019) · Journal of Raman Spectroscopy · doi:10.1002/jrs.5770 · Cited by 123
OV$^{2}$SLAM: A Fully Online and Versatile Visual SLAM for Real-Time Applications
Ferrera, M., Eudes, A., Moras, J., Sanfourche, M., & Besnerais, G. L. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3058069 · Cited by 132
Robust and unobtrusive marker tracking on mobile phones
Wägner, D., Langlotz, T., & Schmalstieg, D. (2008) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2008.4637337 · Cited by 113
“Candidate feature detection is performed using the FAST corner detector [7], which turned out to deliver high performance rates on phones (~8ms at 320x240 on a 400Mhz ARM CPU).”
MethodIntervention AUVs: The Next Challenge
Ridao, P., Carreras, M., Ribas, D., Sanz, P. J., & Oliver, G. (2014) · IFAC Proceedings Volumes · doi:10.3182/20140824-6-za-1003.02819 · Cited by 116
Simultaneous State Initialization and Gyroscope Bias Calibration in Visual Inertial Aided Navigation
Kaiser, J., Martinelli, A., Fontana, F., & Scaramuzza, D. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2521413 · Cited by 129
“The feature extraction and matching is done via the FAST corners [21, 22].”
MethodObject recognition using local invariant features for robotic applications: A survey
Loncomilla, P., Ruíz-del-Solar, J., & Martínez, L. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.05.021 · Cited by 121
Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras
Manderscheid, J., Sironi, A., Bourdis, N., Migliore, D., & Lepetit, V. (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.2019.01049 · Cited by 141
“It has been used in [39] for corner detection, where the FAST algorithm [50] is adapted to the pattern of Time Surface of a moving corner.”
MethodAlmeida, S. G. M., Guimarães, F. G., & Ramírez, J. A. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.05.024 · Cited by 122
“Techniques to perform corner detection can be found in Harris and Stephens (1988), Shi and Tomasi (1994) and Rosten and Drummond (2006).”
MethodWang, Z., Kieu, H., Nguyen, H., & Le, M. (2014) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2014.04.002 · Cited by 114
“In addition to SIFT, SURF, and PCA-SIFT, there are a few other notable feature detection algorithms such as smallest univalue segment assimilating nucleus (SUSAN) [42] and features from accelerated segment test (FAST) [43] algorithms, these are however less popular.”
MethodA comparative experimental study of image feature detectors and descriptors
Mukherjee, D., Wu, Q. M. J., & Wang, G. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0679-9 · Cited by 126
“Rosten and Drummond [37] propose Features from Accelerated Segment Test (FAST).”
BackgroundImage Stitching based on Feature Extraction Techniques: A Survey
Adel, E., Elmogy, M. M., & El-Bakry, H. M. (2014) · International Journal of Computer Applications · doi:10.5120/17374-7818 · Cited by 115
“The FAST technique introduced by Rosten Drummond [15] for identifying interest points in an image.”
BackgroundMethodInfluentialMultiple target detection and tracking with guaranteed framerates on mobile phones
Wagner, D., Schmalstieg, D., & Bischof, H. (2009) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2009.5336497 · Cited by 113
“We therefore replaced the DoG with the FAST corner detector [20] with non-maximum suppression that is known to be one of the fastest corner detectors, but still provides a high repeatability.”
MethodRGB-D Inertial Odometry for a Resource-Restricted Robot in Dynamic Environments
Liu, J., Li, X., Liu, Y., & Chen, H. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191193 · Cited by 124
“The FAST feature detector [28] can efficiently extract feature points but easily treats noise as features and extracts similar clustered features.”
LIFT: Learned Invariant Feature Transform
Yi, K. M., Trulls, E., Lepetit, V., & Fua, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.09114 · Cited by 88
“FAST [15] used Machine Learning techniques but only to speed up the process of finding corners.”
MethodLocal feature point extraction for quantum images
Zhang, Y., Lü, K., Xu, K., Gao, Y., & Wilson, R. C. (2014) · Quantum Information Processing · doi:10.1007/s11128-014-0842-7 · Cited by 109
“…of the reasons is that there has been no quantum feature extraction algorithm based on the existing quantum image models so that none of the traditional recognition and classification methods based on feature points [21] can be leveraged to design a quantum counterpart algorithms for quantum images.”
BackgroundFeng, R., Shen, H., Bai, J., & Li, X. (2021) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3081763 · Cited by 115
Hu, G., Huang, S., Zhao, L., Alempijevic, A., & Dissanayake, G. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386103 · Cited by 117
“Doing so, we are able to overcome some of the fundamental problems as described above.”
BackgroundServer-side object recognition and client-side object tracking for mobile augmented reality
Gammeter, S., Gassmann, A., Bossard, L., Quack, T., & Gool, L. V. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543248 · Cited by 108
Local feature matching using deep learning: A survey
Xu, S., Chen, S., Xu, R., Wang, C., Lu, P., & Guo, L. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102344 · Cited by 154
“For instance, RIFT [105] utilizes FAST [106] for extracting repeatable feature points on the phase congruency (PC) map, subsequently constructing robust descriptors using frequency domain information to tackle the challenges in multimodal image feature matching.”
MethodAlways-on Vision Processing Unit for Mobile Applications
Barry, B., Brick, C., Connor, F., Donohoe, D., Moloney, D., Richmond, R., O'Riordan, M., & Toma, V. (2015) · IEEE Micro · doi:10.1109/mm.2015.10 · Cited by 106
Metadata
- Authors
- Rosten, E., & Drummond, T.
- Affiliations
- University of Cambridge (GB)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 430-443
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1532362218
- Cited by
- 4,555
- References
- 33
- Citations by year
- 2026: 90 · 2025: 201 · 2024: 241 · 2023: 268 · 2022: 328 · 2021: 346 · 2020: 311 · 2019: 335 · 2018: 350 · 2017: 333 · 2016: 301 · 2015: 339 · 2014: 298 · 2013: 245 · 2012: 184
- FWCI
- 37.10
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- corner detection, feature detection, real-time video processing, computational efficiency, SIFT, Harris corner detector
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.