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 8,301–8,400 of 14,752
Performance-oriented networked visual servo control with sending rate scheduling
Wu, H., Lou, L., Chen, C., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979989 · Cited by 4
Ishikura, M., Takeuchi, E., Konyo, M., et al. (2010) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2010.5708296 · Cited by 4
“These feature vectors have the following properties[4]: ∙ Stability against luminance variations ∙ Stability against scale variations ∙ Stability against image rotation The change in luminance in the images from tip camera is caused by LED lights.”
BackgroundMethodUsing Local Symmetry for Landmark Selection
Kootstra, G., de Jong, S., & Schomaker, L. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04667-4_10 · Cited by 4
Feature Segmentation for Object Recognition Using Robot Manipulation
Sushkov, O. O., & Sammut, C. (2011) · Cited by 4
Nakamoto, S., & Toriu, T. (2011) · Cited by 4
An augmented reality platform for CABG surgery
Heydarzadeh, M., Nourani, M., & Park, J. L. (2015) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas.2015.7348441 · Cited by 4
Random features vs Harris Corners in Real-Time Visual Egomotion Estimation
Moutinho, N., Ferreira, R. P. M., Bernardino, A. J. M., et al. (2010) · Cited by 4
Höllerer, T., & DiVerdi, S. (2007) · Cited by 4
Phase-sensitive periodical correlation of local beam descriptors for image registration
Yang, S., Zhang, J., & Zhang, W. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.09.042 · Cited by 4
Study on the Indoor SLAM Using Kinect
Takeda, Y., Aoyama, N., Tanaami, T., et al. (2012) · Proceedings in information and communications technology · doi:10.1007/978-4-431-54216-2_24 · Cited by 4
A Dense Pipeline for 3D Reconstruction from Image Sequences
Schneevoigt, T., Schroers, C., & Weickert, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11752-2_52 · Cited by 4
Similarity Search over the Cloud Based on Image Descriptors' Dimensions Value Cardinalities
Antaris, S., & Rafailidis, D. (2015) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2716315 · Cited by 4
“2002] of 64-dimensions (CIME-240K-64d), global CEDD descriptors [Chatzichristos and Boutalis 2008] of 144-dimensions (CEDD-240K-144d) and global SURF descriptors [CBay et al. 2008] of 5000-dimensions (SURF-240K-5000d).”
BackgroundObeidy, W. K., Arshad, H., Yee, T. S., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25939-0_9 · Cited by 4
Takahashi, M., Yamanouchi, Y., & Nakamura, T. (2015) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2015.46 · Cited by 4
“Many conventional appearance features, which have been used for many applications in computer vision, were used for comparison with the proposed system: color histogram [29], LBP [21], ORB [20], SURF [19], and SIFT [18].”
BackgroundMethodA Top-Down Design Approach for an Automated Testing Framework
Méndez-Porras, A., Hidalgo, M. N., García‐Chamizo, J. M., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26401-1_4 · Cited by 4
The Brightness Clustering Transformand Locally Contrasting Keypoints
Lomeli-R., J., & Nixon, M. S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23192-1_30 · Cited by 4
Improving Data Association in Robot SLAM with Monocular Vision
Wang, Y.-T., Hung, D.-Y., & Sun, C.-H. (2011) · Tamkang University Institutional Repository (TKUIR) · Cited by 7
UAV Motion Estimation Using Low Quality Image Features
Gariepy, R., & Waslander, S. L. (2010) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2010-8210 · Cited by 4
Real-time tracking of deformable objects based on combined matching-and-tracking
Yan, J., Wang, Z., & Wang, S. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.2.023011 · Cited by 4
“Compared to SIFT and SURF, the computational complexity is greatly reduced and the robustness is improved.”
MethodDistinctive interest point selection for efficient near-duplicate image retrieval
Yildiz, B., & Demirci, M. F. (2016) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2016.7459172 · Cited by 4
Lesson Learned from Eurathlon 2013 Land Robot Competition
Majek, K., Musialik, P., Kaczmarek, P., et al. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-05353-0_42 · Cited by 4
Feedback-Based Gameplay Metrics
Marczak, R., Hanna, P., Schott, G. R., et al. (2013) · Cited by 4
Extending a Hippocampal Model for Navigation Around a Maze Generated from Real-World Data
Boorman, L. W., Damianou, A., Martínez-Hernández, U., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22979-9_44 · Cited by 4
“tures (SURF) features [11] for each images and merging similar feature vectors using a k-means cluster approach.”
MethodPose Invariant Face Recognition for New Born: Machine Learning Approach
Singh, R., & Om, H. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-81-322-2734-2_4 · Cited by 4
Kholopov, I. S., & Oleg, V. P. (2016) · International Siberian Conference on Control and Communications · doi:10.1109/sibcon.2016.7491682 · Cited by 4
“The most widely used in practice algorithms for finding the KP and their descriptors are SIFT [6], SURF [7], ORB [8], BRISK [9], FAST [10], KAZE [11], and A-KAZE [12].”
MethodMatching images based on consistency graph and region adjacency graphs
Luo, S., Zhou, H., Xu, J., et al. (2016) · Signal Image and Video Processing · doi:10.1007/s11760-016-0987-1 · Cited by 4
“There have a lot of works in this area, but dominated by the point feature-based methods, especially the local features, e.g. SIFT [1], SURF [2], HOG [3], over the last decade.”
MethodThe SIFT image feature reduction method using the Histogram Intersection Kernel
Usui, Y., & Kondo, K. (2009) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs.2009.5383787 · Cited by 4
Emergency light detection in tunnel environment: An efficient method
Wang, Z., Kagesawa, M., Ono, S., et al. (2011) · doi:10.1109/acpr.2011.6166528 · Cited by 4
“In data collected using ordinary cameras, keypoints [2], [19] invariant to rotations, affine changes, and illumination changes are preferable.”
MethodPerformance comparison of image keypoint detection, description, and matching methods
Peng, W.-H., Lee, M.-Y., Li, T., et al. (2016) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2016.7800416 · Cited by 4
“In this paper, we compare four different keypoint comparison methods, including SIFT [1] [2], SURF [3] [4], ORB [5], and BRISK [6].”
MethodImage matching with an improved descriptor based on SIFT
Hu, X., & Ding, Y. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2265595 · Cited by 4
“/ 3 m ij j i ij j N N m i= m N = = ⎛ ⎞ ⎜ ⎟ ⎜ ⎟ = ⎜ ⎟ ⎛ ⎞ ⎜ ⎟ ⎜ ⎟ ⎜ ⎟ ⎝ ⎠ ⎝ ⎠ ∑ ∑ (6)”
Near-Duplicate Retrieval: A Benchmark Study of Modified SIFT Descriptors
Alyosef, A. A., & Nürnberger, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-53375-9_7 · Cited by 4
Vokhmintcev, A., & Yakovlev, K. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-52920-2_33 · Cited by 6
Pai, N., Hong, J.-H., Chen, P.-Y., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4449-8 · Cited by 4
On a Possibility of Pen-Tip Camera for the Reconstruction of Handwritings
Uchida, S., Itou, K., Iwamura, M., et al. (2012) · Cited by 4
SIFT Features in Multiple Color Spaces for Improved Image Classification
Verma, A., & Liu, C. (2017) · Intelligent systems reference library · doi:10.1007/978-3-319-52081-0_7 · Cited by 4
“Several modifications to the SIFT features have been proposed; among them are the PCA-SIFT [18], GLOH [28], and SURF [3].”
MethodSalient object based action recognition using histogram of Changing Edge Orientation (HCEO)
Aye, H. M., & Zaw, S. M. M. (2017) · IEEE International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera.2017.7965716 · Cited by 4
Toward a smart camera for fast high-level structure extraction
de Lima, R., Martínez-Carranza, J., Morales-Reyes, A., et al. (2017) · Journal of Real-Time Image Processing · doi:10.1007/s11554-017-0704-5 · Cited by 4
An improved ASIFT algorithm for indoor panorama image matching
Fu, H., Xie, D., Zhong, R., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2281615 · Cited by 4
“In terms of efficiency, compared with the original ASIFT algorithm, our algorithm can save about 1/3 of the operation time, but it still cannot achieve the execution efficiency of SIFT algorithm and SURF algorithm.”
MethodInfluentialImproved SURF Algorithm and Its Application in Seabed Relief Image Matching
Zhang, H., Yang, L., & Li, M.-L. (2017) · ITM Web of Conferences · doi:10.1051/itmconf/20171205017 · Cited by 4
3D image reconstruction from multiview images
Boora, S., Sahu, B. C., & Patra, D. (2017) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt.2017.8204120 · Cited by 4
“Herbert Bay et al.[5] presented Speeded Up Robust Features (SURF), which is an efficient scale and rotation invariant interest point detector and descriptor in feature extraction and matching.”
BackgroundMethodExpediting Automated Face Recognition Using the Novel ORB2-IPR Framework
Vinay, A., Shekhar, V. S., Manjunath, N., et al. (2017) · Lecture notes in networks and systems · doi:10.1007/978-981-10-5146-3_21 · Cited by 4
Real-time recognition of suicidal behavior using an RGB-D camera
Li, B., Bouachir, W., Gouiaa, R., et al. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310087 · Cited by 4
Woicke, S., & Mooij, E. (2017) · Springer eBooks · doi:10.1007/978-3-319-65283-2_39 · Cited by 4
Design of real-time SIFT feature extraction
Wang, R., & Jeon, J. W. (2017) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2017.8216600 · Cited by 4
Object tracking with movement prediction algorithms
Raj, A., Sivaraman, A., Bhowmick, C., et al. (2016) · doi:10.1109/iciinfs.2016.8262952 · Cited by 4
Eragi, S. M., Ouarda, W., & Alimi, A. M. (2017) · doi:10.1109/sccsit.2017.8293056 · Cited by 5
“Examples of some techniques used for extracting features: dense local feature extraction with Speeded Up Robust Features (SURF) [11], Histogram of oriented gradients (HOG) and Principal Component Analysis (PCA).”
MethodLiao, M., & Gu, X. (2018) · IET Signal Processing · doi:10.1049/iet-spr.2017.0514 · Cited by 4
Color image retrieval based on the hypergraph and the fusion of two descriptors
Yu, S., Niu, D., Zhao, X., et al. (2017) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2017.8301985 · Cited by 4
Image recognition of individual cow based on SIFT in Lαβ color space
Feng, L., Zhang, C., & Lv, C. (2018) · MATEC Web of Conferences · doi:10.1051/matecconf/201817601023 · Cited by 4
Transportation Object Detection with Bag of Visual Words Model by PLSA and MLP
Song, H. C., & Choi, K. N. (2018) · Mobile Networks and Applications · doi:10.1007/s11036-018-1075-2 · Cited by 4
“Some other papers introduced other features, including Haarlike features [13], color features [14–17], HOG [18], speed-up robust features (SURF) [19], and local binary pattern (LBP) [20].”
BackgroundMeniscus tear classification using histogram of oriented gradients in knee MR images
Saygılı, A., & Albayrak, S. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404375 · Cited by 4
“Bu yönüyle ölçekten ba ğ ı ms ı z öznitelik dönü ş ümü (Scale-invariant feature transform (SIFT)) [14] ve h ı zland ı r ı lm ı ş sa ğ lam öznitelikler (Speeded-up robust features (SURF)) [15] yöntemleri ile benzerlik göstermektedir.”
HYPERSPECTRAL PANORAMIC IMAGING
Muller-Rowold, M., & Reulke, R. (2018) · 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-xlii-1-323-2018 · Cited by 4
Autonomous Robot KUKA YouBot Navigation Based on Path Planning and Traffic Signals Recognition
Gordón, C., Encalada, P., Lema, H. P., et al. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-02686-8_6 · Cited by 4
Development and Laboratory Testing of a Multipoint Displacement Monitoring System
Lydon, D., Taylor, S. E., Robinson, D., Çatbaş, F. N., & Lydon, M. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-17795-9_45 · Cited by 4
Improved MAR Natural Feature Recognition Algorithm Based on SURF and ORB
Feng, C., Yang, Z., Wang, L., & Li, Y. (2018) · International Conference on Sensor Networks and Signal Processing (SNSP) · doi:10.1109/snsp.2018.00093 · Cited by 4
Image Registration Algorithm Based on Super pixel Segmentation and SURF Feature Points
Wei, W., Chengfeng, A., Zhao, Y., et al. (2018) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2018.8608151 · Cited by 4
“However, in the actual process, there will be some aliasing of the discretized Gaussian filter, so the box filter proposed by Bay et al. [11] is used to approximate the Gaussian filter.”
MethodVideo Tracking Based on Template Matching and Particle Filter
Lin, S. D., & Chen, T.-Y. (2018) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2018.8633149 · Cited by 5
Unsupervised Feature Learning for Visual Place Recognition in Changing Environments
Zhao, D., Si, B., & Tang, F. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852466 · Cited by 4
“Classical feature-base methods for place recognition rely on hand-crafted features, such as SIFT descriptor [7], SURF descriptor [8] or Gist descriptor [9].”
MethodSecure signal processing using fully homomorphic encryption
Shortell, T., & Shokoufandeh, A. (2019) · IET Information Security · doi:10.1049/iet-ifs.2019.0157 · Cited by 4
DENSE MULTI-VIEW IMAGE MATCHING FOR DSM GENERATION FROM SATELLITE IMAGES
Mahphood, A., Arefi, H., Hosseininaveh, A., et al. (2019) · 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-xlii-4-w18-709-2019 · Cited by 4
A Segmentation-Driven Approach for 6D Object Pose Estimation in the Crowd
Bi, S., Chai, Z., Liu, C., & Xiong, Z. (2019) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2019.8868606 · Cited by 5
Computerized Hittite Cuneiform Sign Recognition and Knowledge-Based System Application Examples
Aktaş, A. Z., Yesiltepe, B., & Aşuroğlu, T. (2019) · European Scientific Journal ESJ · doi:10.19044/esj.2019.v15n33p32 · Cited by 4
Merino, I., Azpiazu, J., Remazeilles, A., & Sierra, B. (2019) · International Journal of Artificial Intelligence & Applications · doi:10.5121/ijaia.2019.10601 · Cited by 4
Training Convolutional Neural Network for Sketch Recognition on Large-Scale Dataset
Zhou, W. J., & Jia, J. (2019) · The International Arab Journal of Information Technology · doi:10.34028/iajit/17/1/10 · Cited by 4
“individually such as, Speeded Up Robust Features (SURF) [1], and found the fact that Histogram of Oriented Gradients (HOG) features generally are believed as the best feature descriptor for the sketch.”
MethodHaar Pattern Based Binary Feature Descriptor for Retinal Image Registration
Saha, S., & Kanagasingam, Y. (2019) · Digital Image Computing: Techniques and Applications · doi:10.1109/dicta47822.2019.8946021 · Cited by 4
“[9] considered SURF [10] key-points and SURF features to register retinal image pairs.”
BackgroundA Fast Epipolar Line Matching Method Based on 3D Spherical Panorama
Liu, S., Chen, J., Sun, M., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2961184 · Cited by 4
“The proposed method was compared with the gray matching method, SIFT, SURF, and CSIFT, and the experimental results are shown in Table 1.”
MethodInfluentialShishido, H., Kim, H., & Kitahara, I. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006399 · Cited by 4
UAV-Multispectral Sensed Data Band Co-Registration Framework
Júnior, J. D. D., Backes, A. R., Escarpinati, M. C., Silva, L. H. F. P., Costa, B., & Avelar, M. H. F. (2020) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip48289.2020.9145079 · Cited by 4
“…detection and extraction methods: Binary Robust Invariant Scalable Keypoints (BRISK) [9], Features from Accelerated Segment Test (FAST) [10], Maximally Stable Extremal Regions (MSER) [11], Harris-Stephens Features (HSF) [12], Speeded-Up Robust Features (SURF) [13], and KAZE Features (KAZE) [14].”
MethodRobust Feature Detection Method in High-density Structured Light System
Gu, F., Feng, J., Xie, P., et al. (2019) · doi:10.1145/3374587.3374618 · Cited by 4
“FAST[17], SIFT[18], SURF[19] and so on.”
BackgroundДу, С., Li, Y., & Ikenaga, T. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019mvp0019 · Cited by 4
“Compared with other local feature extraction algorithms, such as SIFT [8] and SURF [9], nonlinear scale space is able to keep more boundary information of the original image, leading to higher matching accuracy.”
MethodVisual Servoing for Final Approach Phase of Spacecraft Proximity Operations with Unknown Targets
Harris, W. J., Cobb, R. G., & Taylor, C. N. (2020) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans46316.2020.9110218 · Cited by 4
“Many feature detectors and descriptors exist, such as Scale Invariant Feature Transform (SIFT) [36] and Speeded-Up Robust Features (SURF) [37].”
MethodOne-Way Observation-based Cooperative Robot Mapping
Lee, H. (2020) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case48305.2020.9216996 · Cited by 4
“…individual maps, which are spectra-based map merging (SMM) [13], mean squared error (MSE) based image registration method, Harris corner detector (HCD) [17] based map matching, Shi-Tomasi corner detector (STCD) [18] based map matching, and speeded up robust features (SURF) [19] based map matching.”
MethodLidiawaty, B. R., Irawan, M. I., & Ginardi, R. V. H. (2020) · International Electronics Symposium (IES) · doi:10.1109/ies50839.2020.9231950 · Cited by 5
Air-Ground Collaborative Surveillance with Human-Portable Hardware
Dille, M., Grochosky, B., Nuske, S., et al. (2018) · Figshare · doi:10.1184/r1/6551843 · Cited by 4
New opportunities and challenges in surveying underground cavities using photogrammetric methods
Gurgel, M. J. M., & Preuße, A. (2020) · International Journal of Mining Science and Technology · doi:10.1016/j.ijmst.2020.12.005 · Cited by 4
“Among the best-known algorithms from the scientific community are SIFT (scale invariant feature transform) [12] and SURF (speeded-up robust features) [13].”
MethodCockpit Display Graphics Symbol Detection for Software Verification Using Deep Learning
Pal, D., Alladi, A., Pothireddy, Y., et al. (2020) · doi:10.1109/icdse50459.2020.9310145 · Cited by 5
“For object detection many researchers use feature matching algorithms like Scale Invariant Feature Transform (SIFT) [12], Speeded up robust features (SURF) [13], maximally stable extremal regions (MSER) [14] where wide range of templates need to process at run time.”
MethodLocalizing Against Drawn Maps via Spline-Based Registration
Chen, K., Vázquez, M., & Savarese, S. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341630 · Cited by 6
Gait based Human Identification through Intra-Class Variations
Tun, K. Z. C., & Zaw, S. M. M. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358706 · Cited by 5
“Speeded Up Robust Features (SURF) [5] are local descriptors that are extracted at points of interest in an image.”
BackgroundMethodA survey of smartphone-based Face Recognition systems for Security Purposes
AbdElaziz, A. (2021) · Kafr El-Sheikh Journal of Information Sciences · doi:10.21608/kjis.2021.5484.1006 · Cited by 4
“They applied three feature extraction techniques includes Speeded Up Robust Features (SURF) [18], Scale Invariant Feature Transform (SIFT) [19] and Binarized Statistical Image Features (BSIF) [20].”
MethodFast structural global registration of indoor colored point cloud
Wang, C., Xu, Y., Wang, L., & Li, C. (2021) · The Visual Computer · doi:10.1007/s00371-021-02295-z · Cited by 4
Bio-inspired Multi-scale Visual Place Recognition for the Aerial Vehicle Navigation
Fan, C., Jacobson, A., Chen, Z., He, X., Zhang, L., Hu, X., & Milford, M. J. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8155-7_87 · Cited by 4
Feature-based visual odometry and featureless place recognition for SLAM in 2.5D environments
Milford, M. J., McKinnon, D. H., Warren, M., Wyeth, G. F., & Upcroft, B. (2011) · QUT ePrints (Queensland University of Technology) · Cited by 5
Penggunaan Fitur Saliency-SURF untuk Klasifikasi Citra Sel Darah Putih dengan Metode SVM
Devella, S., Yohannes, Y., & Putra, C. A. (2021) · JATISI (Jurnal Teknik Informatika dan Sistem Informasi) · doi:10.35957/jatisi.v8i4.1547 · Cited by 4
A Scan-to-Locality Map Strategy for 2D LiDAR and RGB-D Data Fusion
Zhang, J., Yang, M., Qu, Y., et al. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-92310-5_41 · Cited by 4
Reporting Neighbors in High-Dimensional Euclidean Space
Aiger, D., Kaplan, H. Y., & Sharir, M. (2013) · ACM-SIAM Symposium on Discrete Algorithms (SODA) · doi:10.1137/1.9781611973105.56 · Cited by 4
Improved Point Pair Feature based Cloud Registration on Visibility and Downsampling
Wang, X., Shang, H., & Jiang, L. (2021) · International Conference on Networking Systems of AI (INSAI) · doi:10.1109/insai54028.2021.00026 · Cited by 6
A Fast Video Stabilization System Based on Speeded-up Robust Features
Zhou, M., & Asari, V. K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24031-7_43 · Cited by 4
Efficient Video Copy Detection Using Simple and Effective Extraction of Color Features
Roopalakshmi, R., & Reddy, G. R. M. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-22726-4_49 · Cited by 4
An Integrated MEMS IMU/Camera System for Pedestrian Indoor Navigation Using Smartphones
Du, S., Huang, B., & Gao, Y. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-29187-6_66 · Cited by 4
Springmann, M., Ispas, A., Schuldt, H., Norrie, M. C., & Signer, B. (2007) · VUBIR (Vrije Universiteit Brussel) · Cited by 5
Evaluating the trackability of natural feature-point sets
Gruber, L., Zollmann, S., Wägner, D., et al. (2009) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2009.5336469 · Cited by 4
“Common feature-point based approaches such as SIFT [4], SURF [1] or Ferns [7] work under the assumption that a point can be characterized by its close proximity, called the support area.”
MethodHamdoun, O., & Moutarde, F. (2009) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2009.5289390 · Cited by 4
DOVO: Mixed Visual Odometry Based on Direct Method and Orb Feature
Zhang, Z., & Wan, W. (2018) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2018.8455316 · Cited by 4
Nguyen, A., & Yoshitaka, A. (2019) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/siprocess.2019.8868828 · Cited by 4
“For traditional Image Process techniques, researchers manually analyze the distribution of colors, textures and characteristics and then apply classic methods such as edge detection (i.e. Canny), shape detection (i.e. Hough Transformation), thresholding (i.e. Otsu) and visual features like SIFT [1], SURF [2], HOG [3],…”
MethodNakazawa, S., Ushijima, S., & Nakada, Y. (2019) · doi:10.1145/3368926.3369672 · Cited by 4
“Keypoints were then detected by Scale-Invariant Feature Transform (SIFT) [24], Speeded-Up Robust Features (SURF) [25], and Accelerated KAZE (AKAZE) [26] on the RMC and ETG images.”
MethodREAL-TIME FEATURELESS VISUAL ODOMETRY FOR SEA FLOOR IMAGING WITH A LAGRANGIAN FLOAT
Casagrande, D. S. (2013) · doi:10.23860/thesis-casagrande-david-2013 · Cited by 4
Wearable-assisted social interaction as assistive technology for the blind
Hayden, D. S. (2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 4
Unsupervised Feature Learning for low-level Local Image DescriptorsPreprint
Osendorfer, C., Bayer, J., Urban, S., & van der Smagt, P. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.2840 · Cited by 6
OUTDOOR DELAYED-STATE VISUALLY AUGMENTED ODOMETRY
Ila, V., Andrade‐Cetto, J., & Sanfeliu, A. (2007) · IFAC Proceedings Volumes · doi:10.3182/20070903-3-fr-2921.00093 · Cited by 5
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.