SURF: Speeded Up Robust Features
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 18 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
SURF is a scale- and rotation-invariant interest point detector and descriptor that uses integral images, Hessian-based detection, and Haar-wavelet responses to be faster than prior methods while matching or exceeding their repeatability and distinctiveness. It reports strong results on standard benchmarks and a museum object recognition task.
Key findings
- The Fast-Hessian detector is more than 3× faster than DoG and 5× faster than Hessian-Laplace, with comparable or better repeatability on Graffiti, Leuven, Boat, and Wall; on the first Graffiti image (800×640), computation times were 120 ms for Fast-Hessian, 400 ms for DoG, 650 ms for Hessian-Laplace, and 1800 ms for Harris-Laplace.
- SURF’s 64-dimensional descriptor outperformed GLOH, SIFT, and PCA-SIFT in most comparisons, sometimes by more than 10% improvement in recall for the same precision; SURF-128 was slightly better but slower to match.
- Joint detector-descriptor computation times on the first Graffiti image were 255 ms for U-SURF, 354 ms for SURF, 391 ms for SURF-128, and 1036 ms for SIFT.
- In museum object recognition, recognition rates were 85.7% for SURF-128, 83.8% for U-SURF, 82.6% for SURF, 78.3% for GLOH, 78.1% for SIFT, and 72.3% for PCA-SIFT.
Methods
- Design: a scale- and rotation-invariant detector/descriptor. The detector uses the determinant of the Hessian with box-filter approximations evaluated via integral images; the descriptor uses Haar-wavelet responses in a 4×4 subregion grid, producing a 64-dimensional vector, with an upright U-SURF variant and an extended SURF-128 variant.
- Data: standard evaluation sequences from Mikolajczyk (including Graffiti, Wall, Boat, Leuven, Bikes, Trees, and Ubc; Bark excluded from descriptor evaluations) and a real-life museum object recognition database of 216 images of 22 objects, with 116 test images at 320×240.
- Analysis: detector repeatability scores, descriptor recall-(1-precision) graphs under similarity-threshold and nearest-neighbour-ratio matching, recognition rates, and computation timings on a standard Linux PC (Pentium IV, 3 GHz).
Limitations
- The paper has no explicit limitations section. It states that space limitations prevent showing results on all sequences, and it assumes skew, anisotropic scaling, and perspective effects are second-order effects covered only by overall descriptor robustness.
- Evident from the text: the method is scale- and rotation-invariant but not affine-invariant; Fig. 4 notes the interest points are not affine invariant, and the descriptor does not use colour.
- Evident from the text: the object recognition experiment uses small 320×240 test images and matching without additional geometric constraints, which the authors say would reduce false positives but were omitted for comparison purposes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
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
“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 Bay et al. 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
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable 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
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 9,201–9,300 of 14,752
Bukała, A., Koziarski, M., Cyganek, B., Koc̨, O. N., & Kara, A. (2020) · JUCS - Journal of Universal Computer Science · doi:10.3897/jucs.2020.024 · Cited by 3
Ronen, R., Jigalin, A., & Berman, Z. (2020) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans46316.2020.9110128 · Cited by 3
“Several types of well-known features can be used in VI-SLAM applications such as Harris [15], FAST [6], ORB [9], SIFT [16], SURF [17] and others.”
MethodDistillation of neural network models for detection and description of image key points
Yashchenko, A. V., Belikov, A. V., Peterson, M. V., et al. (2020) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2020-20-3-402-409 · Cited by 3
VEst: An Efficient Solution to the Camera Velocity Estimation from Minimal Feature Points
Zhang, Y., Fathian, K., & Gans, N. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9147699 · Cited by 3
“There are many techniques that can be used here, including corner features [18], SIFT features [19], SURF features [20], or ORB features [21].”
MethodEvaluation of Bag of Visual Words for Category Level Object Recognition
Sujatha, K. S., Karthiga, G. M., & Vinod, B. (2013) · International Journal of Electronics Signals and Systems · doi:10.47893/ijess.2013.1111 · Cited by 3
DCNet: Dense Correspondence Neural Network for 6DoF Object Pose Estimation in Occluded Scenes
Chen, Z., Yang, W., Xu, Z., Xie, X., Huang, L., & null, N. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413672 · Cited by 4
“Classical methods tend to find local feature points through traditional feature detection algorithms, such as SIFT [20], SURF [2] and HOG [8].”
MethodDesign of Novel Hybrid Model for Detection of Liver Cancer
Srivastava, K., Malhotra, G., Chauhan, M., et al. (2020) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/gucon48875.2020.9231143 · Cited by 3
Application of improved SURF algorithm in real scene matching and recognition
Wang, Y., Yang, X., Wang, X., et al. (2020) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl51233.2020.00-32 · Cited by 3
“Bay and Wang et al [8] improved the SIFT algorithm and proposed the Accelerated Up Robust Features (SURF) algorithm, which inherits the invariance of SIFT algorithm and extracts image feature points at about 3 times faster than SIFT.”
MethodUsing Traffic Signs as Landmarks in Object-oriented EKF-SLAM
Hrustic, E., & Vivet, D. (2020) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv50220.2020.9305318 · Cited by 4
“In classical SLAM approaches, hand-crafted features like Harris corners [1], SIFT [2] or SURF [3] features are extracted from images and used as landmarks for 3D mapping.”
MethodWei, M., Bian, H., Li, S., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3049521 · Cited by 3
“The feature-based image registration method mainly collects the feature points and corresponding descriptors in the image, such as SIFT, ORB, SURF, etc [6]–[9].”
MethodComputer Vision and Machine Learning
Bi, Y., Xue, B., & Zhang, M. (2021) · Adaptation, learning, and optimization · doi:10.1007/978-3-030-65927-1_2 · Cited by 5
Corner Detection Algorithm Based on Cellular Neural Networks (CNN) and Differential Evolution (DE)
Cuevas, E., Rodríguez, A., Alejo-Reyes, A., et al. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-66007-9_4 · Cited by 3
Das, S., Sundaramurthy, S., Aiswarya, M., et al. (2021) · Indian Journal of Artificial Intelligence and Neural Networking · doi:10.35940/ijainn.b1011.041221 · Cited by 3
Development of Recommendation Model for Image Keypoint Detection and Descriptor Extraction Algorithm
Kim, Y.-W., Kim, D., & Kim, S. (2021) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2021.19.4.27 · Cited by 3
“SIFT를 베이스로 하며, 특징점 추출 과정에서 헤시 안 행렬의 행렬식과 적분 이미지를 활용하여 속도 의 향상을 보였다[5][6].”
Real time Localization Method Research with Monoslam and BIM Model
Shan, S., Xu, D., & Gong, J. (2021) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/768/1/012126 · Cited by 4
“A common technology combination is a feature point detectors such as Harris corner detection [1] with a feature measurement algorithm, the popular choices includes SIFT, SURF (Speed up robust feature) algorithm [4, 5] and ORB (Oriented fast and rotated BRIEF) feature algorithm [6].”
MethodA Novel Low Power Method of Combining Saliency and Segmentation for Mobile Displays
Suh, S., Hong, S. M., Kim, Y., & Park, J. (2021) · Electronics · doi:10.3390/electronics10101200 · Cited by 3
Sketch-and-Fill Network for Semantic Segmentation
Jin, Y., Eum, S., Han, D. K., & Ko, H. (2021) · IEEE Access · doi:10.1109/access.2021.3088854 · Cited by 3
“In the beginning of semantic segmentation task, the hand-crafted features (i.e., SIFT [8], SURF [9], HOG [10]) are used to segment images into coherent regions or super-pixels [11].”
MethodClosed-loop feedback registration for consecutive images of moving flexible targets
Ma, R., & Du, X. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04068-0 · Cited by 2
Picture semantic similarity search based on bipartite network of picture-tag type
Zhang, M., Yang, L., Dong, Y., Wang, J., & Zhang, Q. (2021) · PLoS ONE · doi:10.1371/journal.pone.0259028 · Cited by 5
Human Action Recognition by Random Features and Hand-Crafted Features: A Comparative Study
Shen, H., Zhang, J., & Zhang, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16181-5_2 · Cited by 3
Efficient 3D Model Visualization System of Design Drawing Based on Mobile Augmented Reality
Oh, Y.-J., & Kim, E.-K. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-41674-3_115 · Cited by 3
Semantic-Context-Based Augmented Descriptor for Image Feature Matching
Khoualed, S., Château, T., & Castellani, U. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37444-9_28 · Cited by 3
“[4] shows that SURF descriptor performs better than SIFT, PCA-SIFT and GLOH.”
MethodSpatio-Temporal Pattern Representation from AI Inspired Brain Model in Spiking Neural Network
(2021) · Biointerface Research in Applied Chemistry · doi:10.33263/briac125.66186631 · Cited by 3
“There are several doctor algorithms presented, like Scale Invariant Feature Transform (SIFT)[31], Speed up Robust Feature (SURF)[32], Binary Robust Independent Elementary Features (BRIEF)[33], and Oriented FAST and Rotated BRIEF (ORB) [34].”
MethodShape binary patterns: an efficient local descriptor and keypoint detector for point clouds
Romero-González, C., García-Varea, I., & Martínez-Gómez, J. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11586-5 · Cited by 5
“Traditionally, SIFT [22] and SURF [4] have been the most commonly used methods, despite their high computational requirements.”
BackgroundMethodTopology and Local Optima in Computer Vision
Carlsson, E., & Carlsson, J. G. (2022) · SN Computer Science · doi:10.1007/s42979-021-01003-x · Cited by 3
“One way to deal with this is to only study key points of the two images, as is the case for the highly successful SIFT and SURF methods [1, 6].”
MethodBronstein, A. M., & Bronstein, M. M. (2010) · Springer eBooks · doi:10.1007/978-0-387-92920-0_32 · Cited by 4
Quantifying the Degradation of Optical Algorithms in Increasingly Turbid Mediums
Scott, M., & Marburg, A. (2021) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.23919/oceans44145.2021.9705942 · Cited by 3
Yang, L., Cai, Y., Hanjalić, A., et al. (2012) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0023-3 · Cited by 3
Yang, H., Chen, Q., Riaz, M., et al. (2017) · ACM SIGARCH Computer Architecture News · doi:10.1145/3140659.3080224 · Cited by 3
Image and Video Copy Detection Using Content-Based Fingerprinting
Fatourechi, M., Lv, X., Esmaeili, M. M., Wang, Z., & Ward, R. K. (2012) · Image processing series · doi:10.1201/b11716-23 · Cited by 3
An Improved Multi Biometric System for Authentication
Sharma, O. P., & Sivaramkumar, P. (2019) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.b3217.129219 · Cited by 3
MetaMars: 3DoF+ Roaming With Panoramic Stitching for Tianwen-1 Mission
Zheng, D., Wei, L., Liu, Y., et al. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3175632 · Cited by 3
FEATURE MATCHING ENHANCEMENT USING THE GRAPH NEURAL NETWORK (GNN-RANSAC)
Elashry, A., & Toth, C. (2022) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlvi-m-2-2022-83-2022 · Cited by 3
Waheed, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981722 · Cited by 12
Aerial Image Stitching Based on Fusion of Geographic Coordinates and Image Features
Guo, L., Zhu, H., Liu, Y., et al. (2022) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus55513.2022.9986913 · Cited by 3
The Evaluation of Cascade Object Detector in Recognizing Different Samples of Road Signs
Shahbaz, S. J., Al-Zuky, A. A. D., & Al-Obaidi, F. E. M. (2022) · doi:10.1109/iiccit55816.2022.10010605 · Cited by 3
“Some of the challenges that drivers confront are during time day, overcast weather day, and poor visibility [3].”
BackgroundUnsupervised deep homography with multi‐scale global attention
Hu, W., He, C., Lin, M., et al. (2023) · IET Image Processing · doi:10.1049/ipr2.12842 · Cited by 3
Using Accurate Feature Matching for Unmanned Aerial Vehicle Ground Object Tracking
Desai, A., Lee, D.-J., & Zhang, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_41 · Cited by 3
Joint localization and target tracking with a monocular camera
Basit, A., Dailey, M. N., Moonrinta, J., & Laksanacharoen, P. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.05.012 · Cited by 3
“SURF [19], and shape matching algorithms such as contour matching [20] are potentially useful for tracking, but they are slow.”
BackgroundBuilding and Evaluation of a Mosaic of Images Using Aerial Photographs
Coito, T., Pinto, J. R. C., & Azinheira, J. R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39094-4_92 · Cited by 3
“Relevant examples for this dissertation are the Harris operator [8]; SUSAN [9] [10]; HarrisLaplacian scale invariant [11] [7]; Speed Up Robust Feature (SURF) [12]; Scale-Invariant Feature Transform (SIFT) [13] [6] [14]; Affine Sift Invariant Feature Transform (ASIFT) [15] [16] [17] [18].”
Color Invariant Feature Detection and Matching in Underwater Stereo Images
Prabhakar, C. J., & Kumar, P. U. P. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-81-322-0997-3_54 · Cited by 3
Yazdian‐Dehkordi, M., & Azimifar, Z. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.06.015 · Cited by 3
Visual Objects Description for Their Re-identification in Multi-Camera Systems
Ellwart, D., & Czyżewski, A. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-32335-5_5 · Cited by 3
High Performance Model-Based Object Detection and Tracking
Ladikos, A., Benhimane, S., & Navab, N. (2008) · Communications in computer and information science · doi:10.1007/978-3-540-89682-1_14 · Cited by 3
“However, despite a recently proposed optimization of SIFT called SURF [3], SIFT has a lower runtime performance than the Randomized Trees, which exhibit a fast feature matching thanks to an offline learning step.”
MethodEverything is in the Face? Represent Faces with Object Bank
Liu, X., Shan, S., Li, S., & Hauptmann, A. G. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16634-6_14 · Cited by 2
“, low-level local features [22–24], mid-level features [25], high-level semantic features [1], and their combination via hierarchical deep models [21].”
BackgroundVideo Processing for Judicial Applications.
Avgerinakis, K., Briassouli, A., & Kompatsiaris, I. Y. (2009) · Cited by 3
Pharmaceutical Blister Pack Recognition using Local Features
Saitoh, K. (2013) · Machine Vision and Applications · Cited by 3
A Robust Appearance Model and Similarity Measure for Image Matching
Liang, D., Kaneko, S. I., & Satoh, Y. (2015) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2015.p0126 · Cited by 3
Amor, M. B., Kammoun, F., & Masmodi, N. (2016) · IEEE International Conference on Image Processing, Applications and Systems (IPAS) · doi:10.1109/ipas.2016.7880121 · Cited by 3
3D Dynamic Pose Estimation from Marker-Based Optical Data
Selbie, W. S., & Brown, M. (2017) · Springer eBooks · doi:10.1007/978-3-319-30808-1_152-1 · Cited by 3
Paper Prototyping in a Model-Driven Process for Android Application Simulation Support
de Oliveira, A. A. L., & de Souza, C. T. (2017) · doi:10.1145/3131151.3131192 · Cited by 3
“com/studio/ebooks/guide-to-prototyping/ [3] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool.”
Bayazitov, D. N., Kresyun, N. V., Buzinovsky, А. B., et al. (2017) · Pathologia · doi:10.14739/2310-1237.2017.2.109219 · Cited by 3
Multi-image Enhancement Technique Using Max-Plus Algebra-Based Morphological Wavelet Transform
Kannoth, S., & Sateesh Kumar, H. C. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-5758-9_36 · Cited by 3
Objective Models for Performance Comparison of Compression Algorithms for 3DTV
Kufa, J., Kaller, O., Zach, O., et al. (2019) · Radioengineering · doi:10.13164/re.2019.0207 · Cited by 3
“The disparity is calculated for a sufficient amount of significant corresponding pixels by the Speeded-Up Robust Features (SURF) algorithm [35].”
MethodImproving Visual Feature Extraction in Glacial Environments
Morad, S., Nash, J., Higa, S., et al. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2959490 · Cited by 3
Augmented Reality Tracking Registration Based on Improved KCF Tracking and ORB Feature Detection
Yangping, W., Yong, J., Zhengping, Z., et al. (2019) · doi:10.1109/icicn.2019.8834947 · Cited by 3
“When extracting and matching feature points for tracked target position, SIFT(Scale Invariant Feature Transform) [5], SURF(Speeded Up Robust Features) [6] and ORB(Oriented FAST and Rotated BRIEF)[7] are commonly used as feature detection algorithm.”
MethodSpatial attention model based target detection for aerial robotic systems
Zhang, M., Wang, S., Yang, D., Li, Y., & He, H. (2019) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-019-00108-0 · Cited by 3
A Topological Graph-Based Representation for Denoising Low Quality Binary Images
Potts, C., Yang, L., Oyen, D., & Wohlberg, B. E. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00222 · Cited by 3
New approach to calculating the fundamental matrix
Chater, A., & Lasfar, A. (2020) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v10i3.pp2357-2366 · Cited by 3
Assessing the Adequability of FFT-based Methods on Registration of UAV-Multispectral Images
Júnior, J. D. D., Backes, A. R., Escarpinati, M. C., da Silva, L. H. G., Costa, B., & Avelar, M. H. F. (2020) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0009123704370444 · Cited by 3
“Integral images are also used to obtain speed performance on the construction of SURF’s descriptor (Bay et al., 2006).”
BackgroundMethodInfluentialSnakeStrike: A Low-Cost Open-Source High-Speed Multi-Camera Motion Capture System
Jensen, G. W., van der Smagt, P., Heiss, E., et al. (2020) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2020.00116 · Cited by 3
“The SURF-like (Bay et al., 2006) difference of Gaussian filter (Li et al., 2013) detectors must find a pair of images that can be paired for further calibration.”
BackgroundA Review on Steel Surface Image Features Extraction and Representation Methods
Ashour, M. W., Khalid, F., Halin, A. B. A., Darwish, S. H., & Abdulrazzaq, M. M. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-60036-5_17 · Cited by 3
Keyframes retrieval for robust long-term visual localization in changing conditions
Bouaziz, Y., Royer, E., Bresson, G., & Dhome, M. (2021) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami50585.2021.9378614 · Cited by 4
Radius Nearest Neighbour Based Feature Classification for Occlusion Handling
Singh, K. M., Karar, V., & Poddar, S. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820030268 · Cited by 3
“Some of the widely used scale invariant feature detectors and descriptors are SIFT [19], SURF [20] and ORB [21].”
MethodDong, H. (2021) · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · doi:10.7275/5411092 · Cited by 3
DEPTH-BASED DETECTION OF SALIENT MOVING OBJECTS IN SONIFIED VIDEOS FOR BLIND USERS
Deville, B., Bologna, G., Vinckenbosch, M., et al. (2008) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0001084104340439 · Cited by 3
Vision-Based Control of a Handheld Micromanipulator for Robot-Assisted Retinal Surgery
Becker, B. C. (2012) · KiltHub Repository · doi:10.1184/r1/6724241 · Cited by 3
SVR-Based Jitter Reduction for Markerless Augmented Reality
Salti, S., & Stefano, L. D. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04146-4_5 · Cited by 3
“1, the output of pose estimation based on SURF correspondences is full of spikes and jitter that significantly disturb human perception.”
MethodInfluentialLiang, Y., Cao, B., Li, J., et al. (2009) · TRECVID · Cited by 3
(2012) · Springer eBooks · doi:10.1007/springerreference_186913 · Cited by 3
Mobile Mapping Using Smartphones
Al-Hamad, A. (2014) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/26928 · Cited by 3
GENERATION AND OPTIMIZATION OF LOCAL SHAPE DESCRIPTORS FOR POINT MATCHING IN 3-D SURFACES
Taati, B. (2009) · QSpace (Queen's University Library) · Cited by 3
Event Matching from Significantly Different Views using Motion Barcodes.Preprint
Ben-Artzi, G., Werman, M., & Peleg, B. (2014) · arXiv (Cornell University) · Cited by 3
Towards Autonomous Situation Awareness
Naikal, N. (2014) · eScholarship (California Digital Library) · Cited by 3
Point, Line Segment, and Region-Based Stereo Matching for Mobile Robotics
Mckinnon, B. (2009) · Mspace (University of Manitoba) · Cited by 3
Modèles graphiques probabilistes pour la reconnaissance de formes
Barrat, S. (2009) · HAL · Cited by 9
RGB Slemmings: An augmented reality game in your room
Panayiotou, A. (2016) · Utrecht University Repository (Utrecht University) · Cited by 3
Simultaneous Localisation and Mapping Using a Single Camera
Williams, B. P., & Williams, B. (2009) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-d5ewx6gxv · Cited by 4
AutoScaler: Scale-Attention Networks for Visual CorrespondencePreprint
Wang, S., Luo, L., Zhang, N., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05837 · Cited by 3
Panoramic Structure from Motion via Geometric Relationship DetectionPreprint
Ikehata, S., Boyadzhiev, I., Shan, Q., & Furukawa, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.01256 · Cited by 6
“We use a standard non-linear least squares optimization library Ceres [1] to refine the parameters.”
InfluentialReal-time Moving Object Detection using SURF
Journals, I., Desai, H. M., & Gandhi, V. C. (2015) · Figshare · doi:10.6084/m9.figshare.1476298 · Cited by 3
OSNI: Searching for Needles in a Haystack of Social Network Data
Cheng, S., Fang, J., Hristidis, V., Madhyastha, H. V., Mithun, N. C., Perkins, D., Roy–Chowdhury, A. K., Shahbazi, M., & Tsotras, V. J. (2016) · Movebank · doi:10.5441/002/edbt.2016.62 · Cited by 3
“After experimenting with various classifiers and image feature extraction methods, we chose Support Vector Machine (SVM) as classifier and SURF Detector [6] based Bag-of Words Model [13].”
MethodAutomatic Positioning and Design of a Variable Baseline Stereo Boom
Fanto, P. L. (2012) · VTechWorks (Virginia Tech) · Cited by 3
Scale-invariance in local heat kernel descriptors without scale selection and normalization
Bronstein, M. M., & Kokkinos, I. (2009) · HAL · Cited by 3
Timescapes: Putting history in your hip pocket
Whitehead, A. D., & Opp, J. (2013) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · Cited by 3
Egocentric Hand Detection Via Dynamic Region GrowingPreprint
Huang, S., Wang, W., He, S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.03677 · Cited by 3
“The extraction of these descriptors is much faster compared with SIFT [26] and SURF [27] descriptors.”
MethodBRUISE DETECTION IN APPLES USING 3D INFRARED IMAGING AND MACHINE LEARNING TECHNOLOGIES
Hu, Z. (2017) · Digital Commons - Michigan Tech (Michigan Technological University) · doi:10.37099/mtu.dc.etdr/509 · Cited by 4
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained VideosPreprint
Hu, B., Cai, J., Cham, T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00304 · Cited by 3
FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB ImagePreprint
Huang, J., Zhou, Y., Funkhouser, T. A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.12305 · Cited by 3
van der Wal, T. E. P. (2012) · Cited by 6
Satellite Image-based Localization via Learned EmbeddingsPreprint
Kim, D.-K., & Walter, M. R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01133 · Cited by 3
Target Aware Network Adaptation for Efficient Representation LearningPreprint
Yang, Z., Li, V., Okada, R., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.01104 · Cited by 3
Human Body Parts Tracking: Applications to Activity RecognitionPreprint
Dargazany, A. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05281 · Cited by 3
Heterogeneous Domain Adaptation via Soft Transfer NetworkPreprint
Yao, Y., Zhang, Y., Li, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10552 · Cited by 3
“oose 10 overlapping categories of these two datasets to construct the Office+Caltech-256 dataset. Furthermore, we adopt two different feature representations for this type of task: 800-dimension SURF [3] and 4096-dimension DeCAF6 [13]. Some sample images of the category of bike are shown in Figure 4. The text-to-image…”
MethodAligning Points to Lines: Provable ApproximationsPreprint
Jubran, I., & Feldman, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.08446 · Cited by 3
Coarse-To-Fine Visual Localization Using Semantic Compact MapPreprint
Liao, Z., Shi, J., Qi, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.04936 · Cited by 3
“To ensure robustness in urban scenarios, researchers must carefully design features [5], [6] unaffected by viewpoints and highly dynamic objects.”
BackgroundFast and Incremental Loop Closure Detection Using Proximity GraphsPreprint
An, S., Che, G., Zhou, F., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.10752 · Cited by 3
“The methods above use local features such as SURF [13] and BRIEF [14].”
MethodInfluentialSem-LSD: A Learning-based Semantic Line Segment DetectorPreprint
Sun, Y., Han, X., Sun, K., Li, B., Chen, Y., & Li, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06591 · Cited by 4
Zhao, Z., Qi, H., Qi, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06236 · Cited by 3
SketchDesc: Learning Local Sketch Descriptors for Multi-view CorrespondencePreprint
Deng, Y., Li, L., Zheng, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.05744 · Cited by 3
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- 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 Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.