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 8,601–8,700 of 14,752
Content Based Image Search for Clothing Recommendations in E-Commerce
Wang, H., Zhou, Z., Xiao, C., et al. (2015) · Springer eBooks · doi:10.1007/978-3-319-14998-1_11 · Cited by 3
“Local features such as SIFT [13] and SURF [1] are widely used in image retrieval, which detect interest points from the images and use descriptors to describe them.”
MethodA HYBRID LEARNING SYSTEM FOR OBJECT RECOGNITION
Häming, K., & Peters, G. (2011) · International Conference on Informatics in Control, Automation and Robotics (ICINCO) · doi:10.5220/0003572103290332 · Cited by 3
An Indoor Localization Method for Humanoid Robot Based on Artificial Landmark
Guohua, L., Xu, X., Yu, X., et al. (2015) · International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC) · doi:10.1109/imccc.2015.394 · Cited by 3
An improved SIFT algorithm based on adaptive threshold canny
Ran, S., Zhong, W., Ye, L., et al. (2015) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2015.7407901 · Cited by 3
Wu, B., & Jen, C.-L. (2013) · INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences · doi:10.4156/aiss.vol5.issue10.115 · Cited by 3
Energy transfer features combined with DCT for object detection
Fusek, R., & Sojka, E. (2015) · Signal Image and Video Processing · doi:10.1007/s11760-015-0777-1 · Cited by 3
“[4] is also one of the widely used keypoint descriptors.”
Gradient-based Image Local Features
Fujiyoshi, H., & Ambai, M. (2011) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.77.1109 · Cited by 3
Detection of Direction Indicators on Road Surfaces Using Inverse Perspective Mapping and NN
Kim, J. B. (2015) · KIPS Transactions on Software and Data Engineering · doi:10.3745/ktsde.2015.4.4.201 · Cited by 3
Multimedia Event Detection (MED) Evaluation Task.
Dantone, M., Sullivan, K., & Tešić, J. (2010) · Cited by 3
Feature Tracking and Synchronous Scene Generation with a Single Camera
Chai, Z., & Matsumaru, T. (2016) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2016.06.01 · Cited by 3
“SIFT and SURF (Speeded up Robust Features) [19] algorithms cost too more time than ORB algorithm to make the system work in real-time.”
MethodAn extension to the brightness clustering transform and locally contrasting keypoints
Lomeli-R., J., & Nixon, M. S. (2016) · Machine Vision and Applications · doi:10.1007/s00138-016-0785-3 · Cited by 3
Using Spatial Order to Boost the Elimination of Incorrect Feature Matches
Talker, L., Moses, Y., & Shimshoni, I. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.200 · Cited by 3
Methods of Visual Navigation of the UAV Flying Over the Nonplanar District
Stepanov, D., & Tishchenko, I. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-31293-4_45 · Cited by 3
Efficient visual positioning with adaptive parameter learning: poster abstract
Wen, H., Wang, S., Clark, R., et al. (2016) · Information Processing in Sensor Networks · doi:10.5555/2959355.2959389 · Cited by 3
Combining Low-Level Features of Offline Questionnaires for Handwriting Identification
Siegmund, D., Ebert, T., & Damer, N. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-41501-7_6 · Cited by 3
Towards binary robust fast features using the comparison of pixel blocks
Oszust, M. (2016) · Measurement Science and Technology · doi:10.1088/0957-0233/27/3/035402 · Cited by 3
“The proposed descriptor calculates the first-order gradients in the x and y directions using Haar-like box filters [14, 29].”
BackgroundMethodInfluentialRobust monocular visual odometry using optical flows for mobile robots
Li, H., Hu, Z., & Chen, X. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554300 · Cited by 3
Estimation of sparse depth based on an inspiration from SFF
Senthilnathan, R., Subhasree, P., Sivaramakrishnan, R., et al. (2016) · International Conference on Recent Trends in Information Technology · doi:10.1109/icrtit.2016.7569574 · Cited by 3
Zhao, Y., Li, Y., Shao, Z., et al. (2016) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2964284.2967217 · Cited by 3
“Many algorithms were proposed to improve SIFT in the following years, SURF [3] is one of them, which is faster but less accurate than SIFT.”
MethodInfluentialBanerjee, S., Gupta, N., Das, S., Chowdhury, P. R., & Sinha, L. K. (2016) · Sadhana · doi:10.1007/s12046-016-0540-5 · Cited by 3
“Results of matching by using two state-of-the-art feature extraction techniques: (a) scale invariant feature transform (SIFT) proposed by Lowe [8], and (b) speeded up robust features (SURF) proposed by Bay et al [9] are shown in figure 1.”
MethodResultInfluentialSPiKeS: Superpixel-Keypoints structure for robust visual tracking
Derue, F.-X., Bilodeau, G.-A., & Bergevin, R. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0884-9 · Cited by 4
“Figure 9 compares different combinations of features such as SIFT [24] and SURF [26] for keypoints and SLIC [33] and SEEDS [29] for superpixels.”
MethodVideo instance search for embedded marketing
Lin, T.-C., Kao, J.-H., Liu, C.-T., et al. (2012) · Cited by 3
Amma, K., Yaguchi, Y., Niitsuma, Y., et al. (2013) · doi:10.1109/icawst.2013.6765431 · Cited by 3
Step and activity detection based on the orientation and scale attributes of the SURF algorithm
Marouane, C., Ebert, A., Linnhoff–Popien, C., & Christil, M. (2016) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2016.7743645 · Cited by 4
A novel global and local saliency coding method for polyp recognition in WCE videos
Yuan, Y., & Meng, M. Q. ‐. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759373 · Cited by 3
Multiple object detection for smart TV shopping video using point to point feature based SURF method
Chhabra, D., & Verma, A. (2016) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/inventive.2016.7824829 · Cited by 3
“Present research work makes use of Speeded Up Robust Feature (SURF) technique to identify multiple type of objects in a video [4].”
MethodAoki, R., & Miyamoto, R. (2016) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2016.7848555 · Cited by 3
“We found that recent schemes for feature point extraction [8] could be applied to extract key points required for analysis of human gait because they enable accurate extraction of facial parts considering the global structure of feature points in addition to local evaluation using Harris corner detector [9], SIFT [10]…”
MethodInstrument contact force estimation using endoscopic image sequence and 3D reconstruction model
Lin, W.-C., & Song, K. (2016) · International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris.2016.7886629 · Cited by 3
Trackerbot: A robotic surveillance system based on stereo-vision and artificial neural networks
Khosravi, H., & Fazl-Ersi, E. (2016) · doi:10.1109/icrom.2016.7886781 · Cited by 3
Spatial and temporal segmented dense trajectories for gesture recognition
Yamada, K., Yoshida, T., Sumi, K., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2266859 · Cited by 3
Frequency divergence image: A novel method for action recognition
Cruz, A. C., & Street, B. D. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950722 · Cited by 3
“[20] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “SURF:Speeded Up Robust Features,” Comput.”
MethodInfluentialObject instance recognition using best increasing subsequence
Harjono, K. D., & Kusuma, G. P. (2016) · doi:10.1109/kicss.2016.7951432 · Cited by 3
“Feature extraction method such as SIFT [6], SURF [7], ORB [10], KAZE [11]”
InfluentialSafe Long‐RangeTravel for Planetary Rovers through Forward Sensing
Nevatia, Y., Bulens, F., Gancet, J., et al. (2013) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 3
Local Logo Recognition System for Mobile Devices
Nguyen, P. H., Dinh, T. B., & Dinh, T. B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39640-3_41 · Cited by 3
“Speeded-up Robust Feature (SURF) [10] is another robust local feature detector which was first presented by Herbert Bay et al.”
MethodRobust orientation estimate via inertial guided visual sample consensus
Zhang, Y., Liang, W. G., Li, Y., An, H., & Tan, J. (2017) · Personal and Ubiquitous Computing · doi:10.1007/s00779-017-1040-2 · Cited by 3
KCF based 3D object tracking via RGB-D camera of a quadrotor
Ma, Y., Pei, P., Xiang, C., et al. (2017) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2017.7991411 · Cited by 3
Gao, Y., Esquivel, S., Koch, R., Ziegler, M., Zilly, F., & Keinert, J. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296431 · Cited by 3
“[19] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, “SURF: Speeded up robust features,” in European Conference on Computer Vision (ECCV), 2006, pp. 404–417.”
MethodInfluentialAn enhanced hybrid tracking-mosaicking approach for surgical view expansion
Takada, C., Afifi, A., Suzuki, T., et al. (2017) · doi:10.1109/embc.2017.8037659 · Cited by 3
“A GPU-version of the Speed-Up Robust Feature (SURF) algorithm [10] is employed to extract a set of interest points from different views.”
MethodThe inter-frame feature matching and tracking of binocular vision based on the ORB-PyrLK algorithm
Yu, Z., Wang, K., & Li, R. (2017) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2017.8028449 · Cited by 3
“SURF algorithm[6] is an improved algorithm based on SIFT, which improves efficiency of feature detection and matching.”
MethodNovel method for joining missing line fragments for medical image analysis
Najgebauer, P., Rutkowski, L., & Scherer, R. (2017) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2017.8046941 · Cited by 3
Malagi, V. P., & Babu, D. R. R. (2017) · Lecture notes in networks and systems · doi:10.1007/978-981-10-5146-3_20 · Cited by 3
Feng, C. (2015) · Deep Blue (University of Michigan) · Cited by 4
Systems, Q., Agronik, A., & Fralenko, V. P. (2016) · Program systems theory and applications · doi:10.25209/2079-3316-2016-7-2-61-71 · Cited by 3
Qualitative Review of Object Recognition Techniques for Tabletop Manipulation
Wallbridge, C. D., Lemaignan, S., & Belpaeme, T. (2017) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3125739.3132593 · Cited by 3
Dense Feature Matching Core for FPGA-based Smart Cameras
Aguilar‐González, A., Arias-Estrada, M., & Berry, F. (2017) · International Conference on Distributed Smart Cameras · doi:10.1145/3131885.3131922 · Cited by 3
Understanding Scenery Quality: A Visual Attention Measure and Its Computational Model
Loh, Y. P., Tong, S., Liang, X., Kumada, T., & Chan, C. S. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.43 · Cited by 3
“As detailed in Section 4.1, a total of four types of features (i.e. MWHFE, LBP, SURF (BoVW), and SURF (FV)) were tested on eight domains (i.e. the original image, DWT, NSCT-1, NSCT-2, NSCT-3, NSST-1, NSST-2, and NSST3).”
MethodInfluentialAutomated feature-based registration techniques for satellite imagery
Okorie, A. M., & Makrogiannis, S. K. (2017) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2017.8128159 · Cited by 3
“The descriptor component is composed of the construction of a square region aligned to the selected orientation from which the SURF descriptor will be extracted [8].”
MethodInfluentialDevelopment of presentation slide retrieval system based on visual information
Oida, Y., Hiekata, K., Mitsuyuki, T., et al. (2018) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2018.01.001 · Cited by 3
Object insertion and removal in images with mirror reflection
Sun, Z. H., & Hoogs, A. J. (2017) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs.2017.8267645 · Cited by 4
“A large number of robust features have been proposed, including SIFT (Scale Invariant Feature Transform) [12], SURF (Speeded Up Robust Features) [3], BRIEF [5], FAST (Features from Accelerated Segment Test) [20], ORB (Oriented FAST and Rotated BRIEF) [21], AKAZE [2], BRISK [10], Censure [1], LUCID [26], DAISY [24], an…”
MethodSaliency-Based Feature Selection Strategy in Stereoscopic Panoramic Video Generation
Wang, H., Sandin, D. J., & Schonfeld, D. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461649 · Cited by 3
Wide baseline matching for autonomous approaches of MAVs
Mueller, K., Kleis, R., & Trommer, G. F. (2018) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2018.8373456 · Cited by 3
Face recognition using interest points and ensemble of classifiers
Vinay, A., Sampat, P. R., Belavadi, S. V., Pratik, R., Rao, B., Ragesh, R., Murthy, K. N. B., & Natarajan, S. (2018) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait.2018.8389033 · Cited by 3
Towards recent developments in the field of digital image forgery detection
Kumar, T., & Khurana, G. (2018) · International Journal of Computer Applications in Technology · doi:10.1504/ijcat.2018.10015265 · Cited by 3
The Improved SIFT Algorithm Based on Rectangular Operator and Its Parallel Implementation
Yang, W., Yang, J., & Song, H. (2018) · Journal of Information Technology Research · doi:10.4018/jitr.2019010101 · Cited by 3
On feature selection in network flow based traffic sign tracking models
Li, D., & Jiang, H. (2018) · Computers & Industrial Engineering · doi:10.1016/j.cie.2018.11.002 · Cited by 3
High-Precision Camera Localization in Scenes with Repetitive Patterns
Liu, X., Xu, Q., Mu, Y., Yang, J., Lin, L., & Yan, S. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3226111 · Cited by 3
“We use the SURF method [4] to detect interest points in each video frame.”
BackgroundMethodVisual Localization in Changing Environments using Place Recognition Techniques
Xin, Z., Cai, Y., Cai, S., Zhang, J., Yang, Y., & Wang, Y. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545833 · Cited by 2
“In addition, Lowry et al. [14] showed pose estimation with the combination of HOG or conv3 [1] features and SURF keypoints, which are robust to appearance and viewpoint changes.”
MethodRobust Multi-scale ORB Algorithm in Real-Time Monocular Visual Odometry
Cui, Q., Liu, H., & Wang, C. (2017) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2017.101 · Cited by 3
“SIFT [10] (Scale-invariant feature transform) and SURF [11] (Speeded Up Robust Features) features are two popular choices when solving the pose and position estimation problem in VO.”
MethodFrame Registration for Motion Compensation in Imaging Photoplethysmography
Iakovlev, D., Hu, S., & Dwyer, V. M. (2018) · Sensors · doi:10.3390/s18124340 · Cited by 4
Automatic monitoring of honeybees’ activity outside of the hive from UHD video
Avramović, A., Jovanović, V., Pilipović, R., et al. (2018) · Symposium on Neural Networks and Applications (NEUREL) · doi:10.1109/neurel.2018.8587026 · Cited by 3
“For keypoint detection and description we used Speeded-Up Robust Features (SURF) algorithm [5] because it is robust but still fast enough for high resolution videos.”
MethodIndoor Navigation using Text Extraction
Eden, J. T., Kawchak, T., & Narayanan, V. (2018) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2018.8598409 · Cited by 3
“SURF matching then occurs on all images in the top matching clusters to produce the best match among overall image scene structure and local features.”
MethodInfluentialSparsely encoded distinctive visual features for object recognition
Dawood, H., Shabbir, S., Dawood, H., Majeed, M. N., Raza, A., & Mehboob, R. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.6.063035 · Cited by 3
Fast Bag-Of-Words Candidate Selection in Content-Based Instance Retrieval Systems
Siedlaczek, M., Wang, Q., Chen, Y., & Suel, T. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8621935 · Cited by 4
“Then, a local descriptor is identified for each key point [20], [21], [22].”
Background3-D Mapping and Localization using RGB-D Camera
Pudchuen, N., & Jitviriya, W. (2019) · International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP) · doi:10.1109/ica-symp.2019.8646104 · Cited by 3
“Popular multi-purpose feature detectors and descriptors include SIFT [6], SURF [7], and ORB [8].”
MethodInfluentialImprovement of H.265/HEVC Encoding for 8K UHDTV by GOP Size and Prediction Mode Selection
Sakamoto, Y., YOKOYAMA, R., Takeuchi, M., et al. (2019) · International Conference on Consumer Electronics · doi:10.1109/icce.2019.8662077 · Cited by 3
“To analyze motion complexity, we use Speed-Up Robust Features (SURF) points [4] matching between two frames.”
MethodEfficient and distinctive binary descriptor for rotated circular image recognition
Zhang, D., Chen, H., Yin, F., Chen, Z., Tang, H., & Xu, H. (2019) · Machine Vision and Applications · doi:10.1007/s00138-019-01026-8 · Cited by 3
“Over the past decades, the representative high-quality descriptors including SIFT [1], SURF [2], MROGH [3], HOG [4, 5], LIOP [6], AKAZE [7], etc.”
BackgroundMethodTowards 3D Pipe Reconstruction Employing Affine Transformations from Video Information
Reyes-Acosta, A., López-Juárez, I., Osorio-Comparán, R., et al. (2018) · IEEE Latin America Transactions · doi:10.1109/tla.2018.8789567 · Cited by 3
Spectrally-shaped correlation with application to image registration
DelMarco, S. P., Webb, H. F., & Tom, V. T. (2019) · doi:10.1117/12.2518171 · Cited by 3
Environment Scene Classification Based on Images Using Bag-of-Words
Petraitis, T., Maskeliūnas, R., Damaševičius, R., Połap, D., Woźniak, M., & Gabryel, M. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-16469-0_15 · Cited by 3
A Multi-label Scene Categorization Model Based on Deep Convolutional Neural Network
Zhao, G., Wang, L., Cui, Y., Fan, Q., Peng, Q., Kong, Z., Zhu, L., & Zhang, T. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-6508-9_17 · Cited by 3
A Method of Penicillin Bottle Defect Inspection Based on BP Neural Network
Feng, Y., Tang, T., & Chen, S. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9917-6_4 · Cited by 3
Scale Estimation of Monocular SfM for a Multi-modal Stereo Camera
Sumikura, S., Sakurada, K., Kawaguchi, N., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_18 · Cited by 3
Design and implementation of tunnel image mosaic system based on open CV
Xia, Y., Nie, B., Zhang, Y., et al. (2019) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-019-00849-y · Cited by 3
“In Bay et al. (2006) proposed Speeded Up Robust Features (SURF), which is an improved feature point detection algorithm based on SIFT algorithm.”
MethodNguyen, K. D., Nguyen, T.-T., & Ha, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-26969-2_58 · Cited by 3
Patch-Based Image Processing: From Dictionary Learning to Structural Clustering
Li, X. (2017) · doi:10.1201/b13016-13 · Cited by 4
Structure From Motion on XSlit Cameras
Yang, W. H., Zhang, Y., Ye, J., Ji, Y., Li, Z., Zhou, M., & Yu, J. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2957119 · Cited by 3
Local Feature Descriptor Learning with a Dual Hard Sampling Strategy
Wang, S., Guo, X., Tie, Y., et al. (2019) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism46123.2019.00026 · Cited by 3
“Matching local features from different images or patches is a challenging task in computer vision application, such as image retrieval [1], 3D reconstruction [2] and image registration [3]– [5].”
BackgroundCalculating Absolute Scale and Scale Uncertainty for SfM Using Distance Sensor Measurements
Nikolov, I. A., & Madsen, C. B. (2020) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-5225-5294-9.ch008 · Cited by 3
Moreira, L. A. S., Justel, C. M., Oliveira, J. C. D., & Rosa, P. F. F. (2020) · Robotica · doi:10.1017/s0263574720000570 · Cited by 3
“[ M 1 ] [ H3,1 H3,2 H3,3 H3,4 ]T = Fz (4)”
BackgroundUAV path automation using visual waypoints acquired from the ground
Luiz, F., Moreira, L. A. S., Moreira, E. M., et al. (2020) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie45063.2020.9152523 · Cited by 3
“For this, they used a monocular camera on a micro UAV and the SURF method (Speeded-Up Robust Features) [8] to calculate the keypoints and descriptors.”
MethodA Region Adaptive Image Classification Approach Using Genetic Programming
Fan, Q., Xue, B., & Zhang, M. (2020) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec48606.2020.9185908 · Cited by 3
Descriptor Scoring for Feature Selection in Real-Time Visual Slam
Laddha, P., Omer, O. J., Kalsi, G. S., Mandal, D. K., & Subramoney, S. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190889 · Cited by 3
“A feature descriptor is a statistical representation of pixel values in a region around the feature point using distribution of gradients [21, 2] or relative intensity differences [29, 5, 20].”
BackgroundRough or Noisy? Metrics for Noise Estimation in SfM Reconstructions
Nikolov, I. A., & Madsen, C. B. (2020) · Sensors · doi:10.3390/s20195725 · Cited by 3
Banach, A., Strydom, M. L., Jaiprakash, A. T., Carneiro, G., Brown, C., Crawford, R., & McFadyen, A. (2020) · IEEE Access · doi:10.1109/access.2020.3040187 · Cited by 3
Visual-Based Localization Using Pictorial Planar Objects in Indoor Environment
Yu, M., Lin, K.-J., Tsai, B.-L., et al. (2020) · Applied Sciences · doi:10.3390/app10238583 · Cited by 3
Multiframe Astronomical Image Registration Based on Block Homography Estimation
Li, R., Luo, L., & Zhang, Y. (2020) · Journal of Sensors · doi:10.1155/2020/8849552 · Cited by 3
A fast, accurate and dense feature matching algorithm for aerial images
Li, Y., Guanghong, G., & Sun, L. (2020) · Journal of Systems Engineering and Electronics · doi:10.23919/jsee.2020.000085 · Cited by 3
Manni, F., Mamprin, M., Holthuizen, R., et al. (2021) · BioMedical Engineering OnLine · doi:10.1186/s12938-020-00843-7 · Cited by 3
“For this purpose, the SURF algorithm was used to extract the feature vector [27].”
MethodMonocular VO Scale Ambiguity Resolution Using an Ultra Low-Cost Spike Rangefinder
Amin, A. E. S., & El‐Rabbany, A. (2020) · Positioning · doi:10.4236/pos.2020.114004 · Cited by 3
Structural Features based Visual Odometry for Indoor Textureless Environments
Guo, Z., Yu, Q., Guo, R., et al. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327452 · Cited by 3
Frontal Face Generation Based Multi-angle Face Identification System
Zhang, Z., Zhang, H., Liu, H., Xin, S., Xiao, N., & Zhang, L. (2021) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr49711.2021.9349409 · Cited by 3
“To deal with the identification of a multi-angle face, the method mainly contains holistic methods [2,3], feature-based methods [4,5], etc.”
MethodPL‐VSCN: Patch‐level vision similarity compares network for image matching
You, X., Li, Q., Li, K., Yu, A., & Bu, S. (2021) · IET Computer Vision · doi:10.1049/cvi2.12018 · Cited by 3
Vidya, M. S., Sunitha, K., Ashok, S., et al. (2021) · Electrical Engineering · doi:10.1007/s00202-021-01269-7 · Cited by 3
Modelling Software Architecture for Visual Simultaneous Localization and Mapping
Mishra, B., Griffin, R. J., & Sevil, H. E. (2021) · Automation · doi:10.3390/automation2020003 · Cited by 3
“Feature detection: Feature detection is used to generate keypoints from corners (Harris [20], Shi-Tomasi [21], Moravec [22], Forstner [23], FAST [24], and KLT [21]), blobs (SIFT [25], SURF [26], CENSUR [27], and ORB [28]) or line segments [29–33] for correspondence matching.”
MethodSujata, & Mitra, S. K. (2021) · SN Computer Science · doi:10.1007/s42979-021-00610-y · Cited by 4
“Bay [4] launched Speed Up Robust Features (SURF) because it runs quicker than SIFT.”
BackgroundA Comparative Experiment in Classifying Jewelry Images Using Convolutional Neural Networks
Singh, V. (2018) · Science & Technology Asia · doi:10.14456/scitechasia.2018.27 · Cited by 3
Kuo, C.-H., Huang, E.-H., Chien, C.-H., et al. (2021) · Electronics · doi:10.3390/electronics10141632 · Cited by 3
“Since the summations among different partition areas present large differences, values in the feature descriptors will be normalized to acceptable ones by a simple scheme without considerably altering the original character of distribution.”
BackgroundHow Many Bedrooms Do You Need? A Real-Estate Recommender System from Architectural Floor Plan Images
Gan, Y. S., Wang, S.-Y., Huang, C.-E., Hsieh, Y.-C., Wang, H.-Y., Lin, W.-H., Chong, S.-N., & Liong, S. (2021) · Scientific Programming · doi:10.1155/2021/9914557 · Cited by 3
“Particularly, the SURF [18] feature descriptor is utilized to spot the building element in enhancing semantic information extraction.”
MethodAkyol, K., & Şen, B. (2021) · SN Applied Sciences · doi:10.1007/s42452-021-04754-7 · Cited by 3
“…texture analyses of patch images compatible with the keypoints detected with Oriented FAST and rotated BRIEF (ORB) [9], Scale-Invariant Feature Transform (SIFT) [10], and Speeded up robust features (SURF) [11] keypoint detection algorithms on the RGB image and its color channels were carried out.”
MethodInfluentialA Boosted 3-D PCA Algorithm Based on Efficient Analysis Method
Lee, K., & Lin, C.-H. (2021) · Applied Sciences · doi:10.3390/app11167609 · 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.