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 201–300 of 1,007
Discovering Higher Level Structure in Visual SLAM
Gee, A. P., Chekhlov, D., Calway, A. D., & Mayol-Cuevas, W. W. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004641 · Cited by 121
“For measurements, we use the features from accelerated segment test (FAST) salient point detector [40] to identify potential features and”
Hwang, S.-Y., & Song, J. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2011.2109333 · Cited by 106
“We use the features from the accelerated segment test (FAST) feature [10]”
MethodDense reconstruction on-the-fly
Wendel, A., Maurer, M., Graber, G., Pock, T., & Bischof, H. (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.2012.6247833 · Cited by 121
“For every acquired frame, our tracking system extracts FAST-10 [19] features on a four-level image pyramid.”
MethodImproving vehicle localization using semantic and pole-like landmarks
Sefati, M., Daum, M., Sondermann, B., Kreisköther, K., & Kampker, A. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995692 · Cited by 108
“Popular detectors are Speeded-Up Robust Features (SURF) [7], Scale-Invariant Feature Transform (SIFT) [8], Features from Accelerated Segment Test (FAST) [9] and Maximally Stable Extremal Region (MSER) [10].”
MethodBergen, T., & Wittenberg, T. C. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2384134 · Cited by 115
“More recent developments include fast feature detectors, such as the accelerated segment test (e.g., FAST by Rosten and Drummond [130] and AGAST by Mair et al. [131]) and CenSurE (center-surrounded extrema) by Agrawal et al. [132], as well as descriptors that are represented by binary vectors, such…”
MethodA Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos
Ullah, F. U. M., Obaidat, M. S., Ullah, A., Muhammad, K., Hijji, M., & Baik, S. W. (2023) · ACM Computing Surveys · doi:10.1145/3561971 · Cited by 99
“is the combination of FAST [101] and BRISK [99] and has been proven to be invariant in rotation and scale, robust to affine transformation and noise.”
BackgroundMethodCorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence
Ren, S., Zeng, Y., Hou, J., & Chen, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3208859 · Cited by 145
“SfM [6] is a traditional method of recovering the point cloud from a sequence of images while using the handcrafted image feature (SIFT [27], ORB [31], or FAST [32]) to generate the 2D-3D correspondence.”
MethodZhang, Y., Yao, Y., Wan, Y., Liu, W., Yang, W., Zheng, Z., & Xiao, R. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.12.018 · Cited by 122
Chaivivatrakul, S., & Dailey, M. N. (2014) · Precision Agriculture · doi:10.1007/s11119-014-9361-x · Cited by 111
“FAST corner detector (Rosten and Drummond 2006), which searches for high-gradient points.”
BackgroundDeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning
Spencer, J., Bowden, R., & Hadfield, S. (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/cvpr42600.2020.01441 · Cited by 138
Joint Video Stitching and Stabilization From Moving Cameras
Guo, H., Liu, S., He, T., Zhu, S., Zeng, B., & Gabbouj, M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2607419 · Cited by 112
“Our grid-based tracker is built upon the FAST feature detector [40] and KLT tracker [19].”
Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection
Liu, W., Hasan, I., & Liao, S. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109071 · Cited by 113
“It is usually viewed as a low-level technique, with typical tasks including edge detection (e.g. Canny [9], Sobel [10]), corner (or interest point) detection (e.g. SUSAN [11], FAST [12]), and blob (or region of interest point) detection (e.g. LoG [13], DoG [14], MSER [15]).”
MethodVisual loop closure detection with a compact image descriptor
Liu, Y., & Zhang, H. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386145 · Cited by 104
“Gálvez-López and Tardós in [8] used the BRIEF descriptor [19] plus FAST keypoint [20] detection to extract local invariant features.”
MethodCollaborative visual SLAM for multiple agents:A brief survey
Zou, D., Tan, P., & Yu, W. (2019) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2019.09.002 · Cited by 99
Representation of binary feature pooling for detection of insulator strings in infrared images
Zhao, Z., Xu, G., & Qi, Y. (2016) · IEEE Transactions on Dielectrics and Electrical Insulation · doi:10.1109/tdei.2016.7736846 · Cited by 101
“Due to the fact that infrared image of electrical equipment has low resolution that resulting limited number of keypoints being detected [15], we adopt FAST (Features from Accelerated Segment Test) [21] key point detector instead of BRISK detector.”
MethodLearning-Based Symmetry Detection in Natural Images
Tsogkas, S., & Kokkinos, I. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33786-4_4 · Cited by 111
“Starting from works on boundary detection [1,2,3], recent works have also used learning-based techniques for corner detection [4] and junction detection [5,6].”
MethodThermal Stereo Odometry for UAVs
Mouats, T., Aouf, N., Chermak, L., & Richardson, M. A. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2456337 · Cited by 104
“More specifically, we studied the repeatability and matching scores of feature detectors namely DoG [30], Fast-Hessian [31], FAST [32], Harris [33], Shi-Tomasi [34] and CenSurE [35].”
MethodAutomatic LiDAR-Camera Calibration of Extrinsic Parameters Using a Spherical Target
Tóth, T., Pusztai, Z., & Hajder, L. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197316 · Cited by 115
“Finally, the projections of the corners are selected from FAST [33], [34] features and the Perspective-n-Point (PnP) problem is defined by the 3D-2D correspondences.”
MethodBVMatch: Lidar-Based Place Recognition Using Bird's-Eye View Images
Luo, L., Cao, S.-Y., Han, B., Shen, H.-L., & Li, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3091386 · Cited by 110
SiLK: Simple Learned Keypoints
Gleize, P., Wang, W., & Feiszli, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02056 · Cited by 133
“Hand-crafted techniques like Harris-corners[20], SIFT[31], ORB[41] and others [40, 8, 26, 2, 5, 13] have used explicit geometric notions like corners, gradients, and scale-space extrema to achieve results which remain both efficient and competitive to date [44, 34].”
MethodA Vision-Based Approach to UAV Detection and Tracking in Cooperative Applications
Opromolla, R., Fasano, G., & Accardo, D. (2018) · Sensors · doi:10.3390/s18103391 · Cited by 98
“Another algorithm based on visual features (i.e., the FAST, Features from Accelerated Segment Test, points [30]), but designed for moving target tracking from a UAV is presented in [31].”
MethodAutomatic Relocalization and Loop Closing for Real-Time Monocular SLAM
Williams, B., Klein, G., & Reid, I. D. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.41 · Cited by 101
“Keypoints were detected in each frame of the test sequence using the FAST corner detector [ 21 ].”
MethodA visual navigation algorithm for paddy field weeding robot based on image understanding
Zhang, Q., Chen, M. E. S., & Li, B. (2017) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2017.09.008 · Cited by 98
Zaffar, M., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2969917 · Cited by 116
“FAST [21] is a high-speed corner detector for real-time image processing that has been used for SLAM by Mei et al. [22], coupled with SIFT descriptor.”
MethodLi, H., Zhao, J., Li, J., Yu, Z., & Lu, G. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.02.011 · Cited by 103
Ninja on a Plane: Automatic Discovery of Physical Planes for Augmented Reality Using Visual SLAM
Chekhlov, D., Gee, A. P., Calway, A. D., & Mayol-Cuevas, W. W. (2007) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2007.4538840 · Cited by 108
“For measurements, we use the FAST salient point detector [15] to detect potential features and SIFT-like descriptors with scale prediction [7] for repeatable matching of initialised features across frames.”
MethodCombining Multiple Feature for Robust Traffic Sign Detection
Utaminingrum, F., Prasetya, R. P., & Rizdania, R. (2020) · Journal of Image and Graphics · doi:10.18178/joig.8.2.53-58 · Cited by 92
“There are some corner detection methods have been developed, such as FAST [6].”
MethodManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames
Yunus, R., Li, Y., & Tombari, F. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9562030 · Cited by 112
“1) Points: For points, we use ORB features, which are based on the FAST keypoint detector [32] and BRIEF”
MethodAitken, J. M., Evans, M. H., Worley, R., Edwards, S., Zhang, R., Dodd, T. J., Mihaylova, L. S., & Anderson, S. (2021) · IEEE Access · doi:10.1109/access.2021.3115981 · Cited by 116
“A number of solutions exist to this problem; the Harris corner detector [131], SIFT [37], SURF [38], FAST [132], BRIEF [133], and ORB [134], being some historically popular examples.”
Multimodal image matching: A scale-invariant algorithm and an open dataset
Li, J., Hu, Q., & Zhang, Y. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.08.010 · Cited by 112
Adaptive Image-Based Visual Servoing With Temporary Loss of the Visual Signal
Shi, H., Sun, G., Wang, Y., & Hwang, K. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2865004 · Cited by 94
Large-scale, real-time visual–inertial localization revisited
Lynen, S., Zeisl, B., Aiger, D., Bosse, M. C., Hesch, J. A., Pollefeys, M., Siegwart, R., & Sattler, T. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920931151 · Cited by 114
“, ORB (Rublee et al. 2011), FREAK (Alahi et al. 2012) descriptors using FAST (Rosten and Drummond 2006) or DoG (Lowe 2004) interest points that can be computed at 30+ FPS on mobile platforms.”
MethodMulti-camera visual SLAM for autonomous navigation of micro aerial vehicles
Yang, S., Scherer, S., Yi, X., & Zell, A. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.018 · Cited by 101
“The resulted visual odometry mainly consists of two separate threads, in which images from multiple cameras are utilized: In the first thread responsible for camera pose tracking, fixed-range searches are applied to FAST corners (Rosten and Drummond, 2006) correspond to potentially observable map points in images from…”
MethodAutonomous Quadrotor Flight Despite Rotor Failure With Onboard Vision Sensors: Frames vs. Events
Sun, S., Cioffi, G., de Visser, C. C., & Scaramuzza, D. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3048875 · Cited by 98
Zitnick, C. L., & Ramnath, K. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126263 · Cited by 103
“Computationally efficient detectors have also been proposed, including SURF [2], FAST [ 21 ] and CenSurE [12].”
MethodRobust Keyframe-based Monocular SLAM for Augmented Reality
Liu, H., Zhang, G., & Bao, H. (2016) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2016.24 · Cited by 105
Hierarchical Place Recognition for Topological Mapping
Garcia‐Fidalgo, E., & Ortiz, A. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2704598 · Cited by 93
“For each image, we also compute a collection of FAST corners [51] described each by an LDB binary descriptor [18].”
MethodApplication of Artificial Intelligence in Marine Corrosion Prediction and Detection
Imran, M. M. H., Jamaludin, S., Ayob, A. F. M., Ali, A. A. I. M., Ahmad, S. Z. A. S., Akhbar, M. F. A., Suhrab, M. I. R., Zainal, N., Norzeli, S. M., & Mohamed, S. B. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11020256 · Cited by 94
Rey-Otero, I., & Delbracio, M. (2014) · Image Processing On Line · doi:10.5201/ipol.2014.82 · Cited by 121
“These add to the numerous non multi-scale detectors such as the Harris-Stephens detector [10], SUSAN [25], the Förstner detector [7], the morphological corner detector [1] and the machine learning based FAST [23] and AGAST [18].”
Digital Restoration of Cultural Heritage With Data-Driven Computing: A Survey
Basu, A., Paul, S., Ghosh, S., Das, S., Chanda, B., Bhagvati, C., & Snåšel, V. (2023) · IEEE Access · doi:10.1109/access.2023.3280639 · Cited by 113
“[92] refers to an ML-based technique for high-speed corner detection rather than FAST, non-maximal suppression.”
MethodAutonomous flight in unstructured and unknown indoor environments
Bachrach, A. (2009) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 99
Keyframe‐based thermal–inertial odometry
Khattak, S., Papachristos, C., & Alexis, K. (2019) · Journal of Field Robotics · doi:10.1002/rob.21932 · Cited by 101
“In its original implementation, it relies on the detection of FAST features (Rosten & Drummond, 2006) to initialize patches for establishing image correspondences and for providing state update corrections.”
MethodDetecting Dominant Motions in Dense Crowds
Cheriyadat, A., & Radke, R. J. (2008) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2008.2001306 · Cited by 95
“We first identify low-level features in the initial frame using the standard Shi–Tomasi–Kanade detector [46] as well as the Rosten–Drummond detector [47], a fast algorithm for finding corners.”
MethodSPHORB: A Fast and Robust Binary Feature on the Sphere
Zhao, Q., Feng, W., Wan, L., & Zhang, J. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-014-0787-4 · Cited by 94
“Based on this hexagonal spherical grid, we reinvent the FAST algorithm (Rosten and Drummond, 2006; Rosten et al, 2010) and the ORB feature (Rublee et al, 2011) in the spherical 6-neighborhood system, which results in SPHORB, a new spherical binary feature detector and descriptor.”
BackgroundMethodGuo, X., Hu, J., Chen, J., Deng, F., & Lam, T. L. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3058935 · Cited by 100
RoboCup@Home: Analysis and results of evolving competitions for domestic and service robots
Iocchi, L., Holz, D., Ruiz-del-Solar, J., Sugiura, K., & van der Zant, T. (2015) · Artificial Intelligence · doi:10.1016/j.artint.2015.08.002 · Cited by 86
Machine learning framework for image classification
Loussaief, S., & Abdelkrim, A. (2016) · International Conference on Sciences of Electronics, Technologies of Information and Telecommunications · doi:10.1109/setit.2016.7939841 · Cited by 90
“As a built-in pre-requisite to feature detection, the input image is usually smoothed by a Gaussian kernel in a scale-space representation and one or several feature images are computed, often expressed in terms of local image derivatives operations [17].”
BackgroundAn Analysis and Implementation of the Harris Corner Detector
Sánchez, J., Monzón, N., & Salgado, A. (2018) · Image Processing On Line · doi:10.5201/ipol.2018.229 · Cited by 83
“Despite the appearance of many feature detectors in the last decade [11, 1, 17, 24, 23], it continues to be a reference technique, which is typically used for camera calibration, image matching, tracking [21] or video stabilization [18].”
BackgroundPatch Volumes: Segmentation-Based Consistent Mapping with RGB-D Cameras
Henry, P., Fox, D., Bhowmik, A., & Mongia, R. (2013) · 2013 International Conference on 3D Vision · doi:10.1109/3dv.2013.59 · Cited by 85
“We compute FAST features [17] and BRIEF descriptors [3], associate them with their points from the depth image (or discard them if they lack valid depth), and save only this information for the keyframe to minimize memory usage.”
MethodPULP: A Ultra-Low Power Parallel Accelerator for Energy-Efficient and Flexible Embedded Vision
Conti, F., Rossi, D., Pullini, A., Loi, I., & Benini, L. (2015) · Journal of Signal Processing Systems · doi:10.1007/s11265-015-1070-9 · Cited by 109
“The benchmark is composed of three kernels: FAST corner detection [58][59], non-maximal suppression and Lucas-Kanade optical flow estimation [42].”
MethodSequential Non-Rigid Structure from Motion Using Physical Priors
Agudo, A., Moreno-Noguer, F., Calvo, B., & Montiel, J. M. M. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2469293 · Cited by 88
“The camera transition state function m k +1 ≡ m k +1 ( m k , ∆ v , ∆ ω C ) is: where q (( ω C k + ∆ ω C )∆ t ) denotes the quaternion defined by the rotation vector ( ω C k + ∆ ω C )∆ t .”
Tauro, F., Tosi, F., Mattoccia, S., Toth, E., Piscopia, R., & Grimaldi, S. (2018) · Remote Sensing · doi:10.3390/rs10122010 · Cited by 92
“The features from accelerated segment test (FAST) directly addresses computation efficiency by a machine learning approach that yields high quality features [59].”
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters Revisited
Barroso-Laguna, A., & Mikolajczyk, K. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3145820 · Cited by 101
“FAST [32] was one of the first attempts to use machine learning to derive a corner keypoint detector.”
MethodAccurate and Linear Time Pose Estimation from Points and Lines
Vakhitov, A., Funke, J., & Moreno-Noguer, F. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46478-7_36 · Cited by 95
“The proliferation of feature point detectors [16, 36] and descriptors [3, 26, 29, 37, 40] able to consistently retrieve many feature points per image, brought a series of new PnP algorithms that could efficiently handle arbitrarily large sets of points [9, 13, 18, 24, 25, 27, 30, 38, 45].”
BackgroundFast loop-closure detection using visual-word-vectors from image sequences
Bampis, L., Amanatiadis, A. A., & Gasteratos, A. C. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917740639 · Cited by 85
“As the robot moves, the Nf most prominent ORB features are extracted using the oFAST algorithm (the orientation invariant alteration of FAST (Rosten and Drummond, 2006), proposed by Rublee et al. (2011)) from every input image.”
MethodInfluentialSLAM Overview: From Single Sensor to Heterogeneous Fusion
Chen, W., Zhou, C., Shang, G., Wang, X., Li, Z., Xu, C., & Hu, K. (2022) · Remote Sensing · doi:10.3390/rs14236033 · Cited by 91
Direct Visual Odometry in Low Light Using Binary Descriptors
Alismail, H., Kaess, M., Browning, B., & Lucey, S. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2635686 · Cited by 88
“FOVIS makes use of FAST corners [52] matched with a Zeromean Normalized Cross Correlation (ZNCC).”
MethodActively articulated suspension for a wheel-on-leg rover operating on a Martian analog surface
Reid, W., Pérez-Grau, F. J., Göktoğan, A. H., & Sukkarieh, S. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487777 · Cited by 91
“The features are extracted using the Features from the Accelerated Segment Test (FAST) algorithm [14], which is a computationally efficient method for corner detection.”
MethodIntegration of Machine Learning and Optimization for Robot Learning
Mosavi, A. H., & Várkonyi-Kóczy, A. R. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-46490-9_47 · Cited by 80
“Robot vision [9], Robot navigation [10], fi eld Robotics [11], humanoid Robotics [12], legged locomotion [13], modeling vehicle dynamics [14], medical and surgery Robotics [15], off-road rough-terrain mobile Robot navigation [16], are few of the areas within Robotics for which utilizing ML…”
BackgroundWhen to use what feature? SIFT, SURF, ORB, or A-KAZE features for monocular visual odometry
Chien, H.-J., Chuang, C.-C., Chen, C., & Klette, R. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804434 · Cited by 98
“As its self-explanatory name, the ORB algorithm combines an enhanced FAST (features from accelerated segment test) [12] technique to locate keypoints, with a direction-normalised BRIEF (binary robust independent elementary) [13] descriptor extraction process.”
Method3D Mapping and 6D Pose Computation for Real Time Augmented Reality on Cylindrical Objects
Tang, F., Wu, Y., Hou, X., & Ling, H. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2950449 · Cited by 96
“Fast corners [27] are detected and ORB descriptors [26], instead of SIFT features, are extracted on each image for real-time performance.”
BackgroundPredicting sensory evaluation of spinach freshness using machine learning model and digital images
Koyama, K., Tanaka, M., Cho, B.-H., Yoshikawa, Y., & Koseki, S. (2021) · PLoS ONE · doi:10.1371/journal.pone.0248769 · Cited by 84
Exploring Event Camera-Based Odometry for Planetary Robots
Mahlknecht, F., Gehrig, D., Nash, J., Rockenbauer, F. M., Morrell, B. J., Delaune, J. H., & Scaramuzza, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3187826 · Cited by 102
Lin, B., Sun, Y., Qian, X., Goldgof, D. B., Gitlin, R. D., & You, Y. (2015) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.1661 · Cited by 87
“In the features from accelerated segment test (FAST) (32), Rosten et al.”
MacInnes, J., Iqbal, S., Pearson, J., & Johnson, E. N. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/299925 · Cited by 104
“License-free alternative algorithms exist (e.g. BRISK (Leutenegger, Chli, and Siegwart 2011) , FAST (Rosten and Drummond 2006; Rosten, Porter, and Drummond 2010) , ORB (Rublee, Rabaud, and Konolige 2011) ), and are available within OpenCV, but are not discussed in detail here.”
MethodOn-patient see-through augmented reality based on visual SLAM
Mahmoud, N., Grasa, Ó. G., Nicolau, S., Doignon, C., Soler, L., Marescaux, J., & Montiel, J. M. M. (2016) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-016-1444-x · Cited by 83
“To do so, a set of interest points has to be matched along the sequence; we use sparse features detected in the image by the features from accelerated segment test (FAST) detector [21].”
MethodDeep learning serves traffic safety analysis: A forward‐looking review
Razi, A., Chen, X., Li, H., Wang, H., Russo, B. J., Chen, Y., & Yu, H. (2022) · IET Intelligent Transport Systems · doi:10.1049/itr2.12257 · Cited by 98
Shape-Former: Bridging CNN and Transformer via ShapeConv for multimodal image matching
Chen, J., Chen, X., Chen, S., Liu, Y., Rao, Y., Yang, Y., Wang, H., & Wu, D. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.10.030 · Cited by 82
Knowledge Transfer Through Machine Learning in Aircraft Design
Min, A. T. W., Sagarna, R., Gupta, A., Ong, Y.-S., & Goh, C.-K. (2017) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2017.2742781 · Cited by 85
“The existing methods in the literature have been successfully applied in a host of practical domains spanning natural language processing [14], computer vision [15], [16], recommender systems [17], etc.”
MethodFeature Tracking and Motion Compensation for Action Recognition
Uemura, H., Ishikawa, S., & Mikolajczyk, K. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.30 · Cited by 77
“These features and motion tracks are used by subsequent components of the system to estimate the plane homographies and to represent the actions.”
MethodEye Blink Detection Using Variance of Motion Vectors
Drutarovsky, T., & Fogelton, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16199-0_31 · Cited by 76
“Features are detected using FAST [14] and tracked with a KLT tracker.”
MethodLiFF: Light Field Features in Scale and Depth
Dansereau, D. G., Girod, B., & Wetzstein, G. (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.2019.00823 · Cited by 86
“ate a broad range of research in feature detection, registration, interpolation, SfM, and SLAM. II. RELATED WORK Feature Detection and Matching: 2D feature detectors such as SIFT [25], SURF [2], FAST [33], and ORB [34], are instrumental in many computer vision algorithms, including SfM, SLAM, disparity estimation, and…”
MethodShi, X., Zhao, D., Yao, H., Li, X., Hale, D., & Ghiasi, A. (2021) · Communications in Transportation Research · doi:10.1016/j.commtr.2021.100014 · Cited by 85
Learning to Detect Features in Texture Images
Zhang, L., & Rusinkiewicz, S. M. (2018) · 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.2018.00662 · Cited by 86
“Learned Feature Detectors FAST [16] achieves fast corner detection, and machine learning techniques are applied to accelerate detection.”
MethodBakour, K., & Ünver, H. M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05816-y · Cited by 74
“ORB This algorithm uses FAST keypoint detector [33] and BRIEF descriptor [34] with many modifications to enhance the performance.”
MethodChen, Z., Liu, X., Kojima, M., Huang, Q., & Arai, T. (2021) · Sensors · doi:10.3390/s21041536 · Cited by 84
“…extractors, including Star (or CenSurE, Center Surround Extremes, by Agrawal et al. [21]), GFTT (Good Feature to Track by Shi et al. [22]), SIFT (by Lowe et al. [23]), SURF (by Bay et al. [24,25]), ORB (by Rublee et al. [26]), BRISK (by Leutenegger et al. [27]), and FAST (by Rosten et al. [28]).”
BackgroundRobust Place Recognition using an Imaging Lidar
Shan, T., Englot, B., Duarte, F., Ratti, C., & Rus, D. L. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9562105 · Cited by 90
“ORB feature descriptors are obtained by first extracting FAST corner features [20] and then describing them using BRIEF descriptors [21].”
MethodAutomation of thermographic 3D modelling through image fusion and image matching techniques
Lagüela, S., Armesto, J., Arias, P., & Herráez, J. (2012) · Automation in Construction · doi:10.1016/j.autcon.2012.05.011 · Cited by 76
Robust Real-Time Visual SLAM Using Scale Prediction and Exemplar Based Feature Description
Chekhlov, D., Pupilli, M., Mayol-Cuevas, W. W., & Calway, A. D. (2007) · 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.2007.383026 · Cited by 73
“To minimise computation, candidate feature points within search regions, indicated in yellow in Fig. 1, are detected using a fast salient point operator (we use that proposed by Rosten and Drummond [ 14 ]), and the most likely feature positions are then found by comparison with feature measurements taken around each s…”
MethodActive exposure control for robust visual odometry in HDR environments
Zhang, Z., Förster, C., & Scaramuzza, D. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989449 · Cited by 89
“To quantitatively measure the image quality, we compute the number of FAST features [14] that can be extracted from the best images.”
MethodCamouflage performance analysis and evaluation framework based on features fusion
Xue, F., Chengxi, Y., Xu, S. Z., Dong, H., Luo, Y., & Jia, W. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2946-1 · Cited by 72
“In our implementation, the FAST corner detection algorithm [13] is used to detect corner points in camouflaged regions.”
MethodInterest Point Detector and Feature Descriptor Survey
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_6 · Cited by 80
Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera
Linegar, C., Churchill, W., & Newman, P. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487208 · Cited by 76
“Many prior works in this area use local, low-level image features such as corners [6][7], blobs [8], or lines [9] as the underlying point of interest detector.”
BackgroundAutomated Machine Vision System for Liquid Particle Inspection of Pharmaceutical Injection
Zhang, H., Li, X., Zhong, H., Yang, Y., Wu, Q. M. J., Ge, J., & Wang, Y. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2800258 · Cited by 74
“In order to solve the problem, a new method of binary descriptor block matching is proposed based on features of the accelerated segment test (FAST) [31].”
MethodInfluentialACE: An Efficient Asynchronous Corner Tracker for Event Cameras
Alzugaray, I., & Chli, M. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00080 · Cited by 96
Multiscale Locality and Rank Preservation for Robust Feature Matching of Remote Sensing Images
Jiang, X., Jiang, J., Fan, A., Wang, Z., & Ma, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2906183 · Cited by 74
“It achieves a much higher speed by using FAST detector [19] and BRIEF”
MethodYuk, E. H., Park, S. H., Park, C.-S., & Baek, J. (2018) · Applied Sciences · doi:10.3390/app8060932 · Cited by 74
Advances in Computer Vision: Proceedings of the 2019 Computer Vision Conference (CVC), Volume 1
O’Mahony, N., Campbell, S., Carvalho, A., Harapanahalli, S., Velasco-Hernandez, G., Krpálková, L., Riordan, D., & Walsh, J. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-17795-9 · Cited by 104
“…CV tasks: • Scale Invariant Feature Transform (SIFT) [14] • Speeded Up Robust Features (SURF) [15] • Features from Accelerated Segment Test (FAST) [16] • Hough transforms [17] • Geometric hashing [18] Feature descriptors such as SIFT and SURF are generally combined with traditional machine…”
MethodEdge-SIFT: Discriminative Binary Descriptor for Scalable Partial-Duplicate Mobile Search
Zhang, S. S., Tian, Q., Lü, K., Huang, Q., & Gao, W. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2251650 · Cited by 73
A Highly Accurate and Reliable Data Fusion Framework for Guiding the Visually Impaired
Elmannai, W., & Elleithy, K. M. (2018) · IEEE Access · doi:10.1109/access.2018.2817164 · Cited by 86
“Therefore, ORB is an integration of the modified Features from Accelerated Segment Test (FAST) detector [77] and the modified Binary”
2D Object Recognition Techniques: State-of-the-Art Work
Bansal, M., Kumar, M., & Kumar, M. (2020) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-020-09409-1 · Cited by 82
“A new corner detector algorithm called FAST (Features from Accelerated Segment Test) was presented by Rosten and Drummond [46] to solve the issues of Harris algorithm.”
MethodShariq, M. H., & Hughes, B. R. (2020) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2020.109979 · Cited by 86
Inverse design of acoustic metamaterials based on machine learning using a Gauss–Bayesian model
Zheng, B., Yang, J., Liang, B., & Cheng, J. (2020) · Journal of Applied Physics · doi:10.1063/5.0012392 · Cited by 71
Zhao, D., Zhang, H., Huang, K., Zhu, X., Arun, P. V., Jiang, W., Li, S., Pei, X., & Zhou, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126721 · Cited by 86
Keypoint Signatures for Fast Learning and Recognition
Calonder, M., Lepetit, V., & Fua, P. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_6 · Cited by 78
“However, to ensure fairness, we added a “virtual” amount of time on the GT side to account for the time spent by an efficient detection algorithm such as FAST [14] to detect 1000 interest-points.”
MethodRGB-T SLAM: A flexible SLAM framework by combining appearance and thermal information
Chen, L. F., Sun, L., Yang, T., Fan, L., Huang, K., & Xuanyuan, Z. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989668 · Cited by 82
“They find that feature detector can be performed on the thermal map once lowering the sensitivity threshold, and then they utilize GFTT [12] and FAST [13] detectors for their approach.”
MethodHWNet v2: an efficient word image representation for handwritten documents
Krishnan, P., & Jawahar, C. V. (2019) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-019-00336-x · Cited by 88
“In [70,86], bowbased representationwas adapted forword image retrieval for machine-printed documents using standard keypoint detectors such as Harris [27] and fast [62] corner detectors, while the local features at the keypoints were computed using sift.”
MethodDeep Feature-Based Classifiers for Fruit Fly Identification (Diptera: Tephritidae)
Leonardo, M. M., Carvalho, T., Rezende, E., Zucchi, R. A., & Faria, F. A. (2018) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2018.00012 · Cited by 70
“F-SIFT+MLP is a multiple layer perceptron technique using a Bow-of-Words (BoW) representation based on BossaNova [19] with keypoint detector FAST [30] and local feature detector SIFT [15] Figure 4 shows the effectiveness results among the best tuples (feature + learning technique) and the best baseline existing in the…”
MethodImage Feature Detectors for Deepfake Video Detection
Kharbat, F. F., Elamsy, T., Mahmoud, A., & Abdullah, R. (2019) · 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa47632.2019.9035360 · Cited by 66
“Features from Accelerated Segment Test (FAST) [17] was proposed to solve the problem of complexity for real-time applications.”
BackgroundI Can See the Light: Attacks on Autonomous Vehicles Using Invisible Lights
Wang, W., Yao, Y., Liu, X., Li, X., Hao, P., & Zhu, T. (2021) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3460120.3484766 · Cited by 126
“During the visual odometry (VO) process, the autonomous vehicle extracts FAST key points [61] 22m 85 m Destination”
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.