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 6,701–6,800 of 14,752
Hasheminasab, S. M., Zhou, T., Lin, Y.-C., et al. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3167378 · Cited by 6
THE USE OF COMPUTER VISION ALGORITHMS FOR AUTOMATIC ORIENTATION OF TERRESTRIAL LASER SCANNING DATA
Markiewicz, J. S. (2016) · 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/isprsarchives-xli-b3-315-2016 · Cited by 6
Face detection algorithm based on improved Retinaface
Chen, Y., Wu, Z., Peng, H., et al. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9728659 · Cited by 6
Peppa, M. V., Morelli, L., Mills, J. P., Penna, N. T., & Remondino, F. (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-xliii-b2-2022-1183-2022 · Cited by 7
VIDI: A Video Dataset of Incidents
Sesver, D., Gencoglu, A. E., Yildiz, C. E., Gunindi, Z., Habibi, F., Yazıcı, Z. A., & Ekenel, H. K. (2022) · Multidimensional Signal Processing Workshop · doi:10.1109/ivmsp54334.2022.9816319 · Cited by 10
Yao, G., Huang, P., Ai, H., et al. (2022) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.16.036502 · Cited by 6
“Using the FAST operator, the method proposed in Bay et al. 12 pays more attention to the gray-scale difference between the surrounding pixels and the center pixel, realizing real-time feature point detection.”
MethodAn Improved KNN Classifier for 3D Face Recognition Based on SURF Descriptors
Boumedine, A. Y., Bentaieb, S., & Ouamri, A. (2022) · Journal of Applied Security Research · doi:10.1080/19361610.2022.2099688 · Cited by 6
The Revisiting Problem in Simultaneous Localization and Mapping
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-09396-8_1 · Cited by 12
Visual Place Recognition via a Multitask Learning Method With Attentive Feature Aggregation
Guan, P., Cao, Z., Yu, J., Tan, M. H., & Wang, S. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3206500 · Cited by 6
“An impressive case is fast appearance-based mapping (FAB-MAP) [28], which extracts the SURF features from an image and converts them into a BoW representation for effective place recognition.”
A Generic Image Processing Pipeline for Enhancing Accuracy and Robustness of Visual Odometry
Sabry, M., Osman, M., Hussein, A., Mehrez, M. W., Jeon, S. J., & Melek, W. (2022) · Sensors · doi:10.3390/s22228967 · Cited by 8
“Figure 3a shows the original output of the SURF feature detector, where the feature density is higher in the top right region of the image.”
MethodA Multi-Channel Descriptor for LiDAR-Based Loop Closure Detection and Its Application
Wang, G., Wei, X., Chen, Y., Zhang, T., Hou, M., & Liu, Z. (2022) · Remote Sensing · doi:10.3390/rs14225877 · Cited by 6
Wan, G., Zhong, R., Wu, C., et al. (2022) · Remote Sensing · doi:10.3390/rs14235976 · Cited by 6
Hybrid Data Selection With Context and Content Features for Visual Crowdsensing
Song, W. (2022) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2022.3205422 · Cited by 6
“Moreover, speeded up robust features (SURF) [18], a speeded-up version of SIFT, are used to assess visual similarities in the calculation of the content influence factor.”
MethodA NOVEL APPROACH TO LANDSLIDE MONITORING BASED ON UNMANNED AERIAL SYSTEM PHOTOGRAMMETRY
Jakopec, I., Marendić, A., & Grgac, I. (2022) · Rudarsko-geološko-naftni zbornik · doi:10.17794/rgn.2022.5.8 · Cited by 6
“( Alcantarilla et al., 2013 ), Speeded Up Robust Features (SURF) ( Bay et al., 2006 ), Hessian Affine feature point detector, and Histogram of Oriented Gradients descriptor (HAHOG) ( Meza et al., 2018 ), Oriented Fast and Rotated Brief (ORB) ( Rublee et al. , 2011 ), and Scale Invariant Feature…”
Lee, C.-E., Chen, C., Wang, H., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3214212 · Cited by 6
MD-Net: Multi-Detector for Local Feature Extraction
Santellani, E., Sormann, C., Rossi, M., Kühn, A., & Fraundorfer, F. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956504 · Cited by 10
Nie, H., Fu, Z., Tang, B., et al. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3234531 · Cited by 6
“In recent decades, hand-made orientation estimation methods [3], [4], [5], [6], [7], [8] have dominated the field of feature point orientation estimation and have produced good results; among these methods, scale-invariant feature transform (SIFT) [4] chooses the peak of the feature point gradient…”
MethodAn Effective End-to-End Image Matching Network with Attentional Graph Neural Networks
Fu, K., Liu, Z., Wu, X., Sun, C., & Chen, W. (2022) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea54703.2022.10005924 · Cited by 6
“SURF [14] is a modified version of SIFT, which uses the Hessian matrix to increase the speed of operation.”
MethodUrban landmark detection using A-KAZE features and vector of aggregated local descriptors
Orhei, C., Radu, L., Mocofan, M., et al. (2022) · International Symposium on Electronics and Telecommunications (ISETC) · doi:10.1109/isetc56213.2022.10009951 · Cited by 6
CVML-Pose: Convolutional VAE Based Multi-Level Network for Object 3D Pose Estimation
Zhao, J., Sanderson, E., & Matuszewski, B. J. (2023) · IEEE Access · doi:10.1109/access.2023.3243551 · Cited by 7
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Sedlář, J., Štěpánová, K., Škoviera, R., Behrens, J. K., Tuna, M., Šejnová, G., Šivic, J., & Babuška, R. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3259735 · Cited by 12
Review of Research on Multi-robot Visual Simultaneous Localization and Mapping
Hesheng, Y., Shuo, P., Xu, L., & Bo, H. (2022) · Journal of Mechanical Engineering · doi:10.3901/jme.2022.11.011 · Cited by 8
Hybrid Feature Based 6D Pose Tracking under Binocular Vision for Automated Micro-assembly
Xie, T., Zhang, X., Li, H., & Zhang, J. (2023) · International Conference on Mechatronics and Robotics Engineering (ICMRE) · doi:10.1109/icmre56789.2023.10106573 · Cited by 8
A CNN-Based Layer-Adaptive GCPs Extraction Method for TIR Remote Sensing Images
Zhao, L., Jiao, J., Yang, L., Pan, W., Zeng, F., Li, X., & Chen, F. (2023) · Remote Sensing · doi:10.3390/rs15102628 · Cited by 6
From Digital Recording to Advanced AI Applications in Archaeology and Cultural Heritage
Pavlidis, G. P. (2023) · Interdisciplinary Contributions to Archaeology/Interdisciplinary contributions to archaeology · doi:10.1007/978-3-031-27330-8_69 · Cited by 6
Gao, R., Li, Y., Liu, Z., et al. (2023) · Applied Sciences · doi:10.3390/app132011302 · Cited by 6
Coarse-to-Fine Homography Estimation for Infrared and Visible Images
Wang, X., Luo, Y., Fu, Q., et al. (2023) · Electronics · doi:10.3390/electronics12214441 · Cited by 6
On-Board Geometric Rectification for Micro-Satellite Based on Lightweight Feature Database
Wang, L., Xiang, Y., Wang, Z., You, H., & Hu, Y. (2023) · Remote Sensing · doi:10.3390/rs15225333 · Cited by 9
Object detection in inland vessels using combined trained and pretrained models of YOLO8
Goudah, A. A., Jarofka, M., El-Habrouk, M., Schramm, D. H., & Dessouky, Y. G. (2023) · Advances in Computing and Engineering · doi:10.21622/ace.2023.03.2.064 · Cited by 6
Adaptive feature extraction method for capsule endoscopy images
Wu, D., Wang, Y., Ma, H., et al. (2023) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-023-00151-6 · Cited by 6
Loop closure detection of visual SLAM based on variational autoencoder
Song, S., Yu, F., Jiang, X., Zhu, J., Cheng, W., & Fang, X. (2024) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2023.1301785 · Cited by 7
“However, appearance-based methods usually depend on traditional handcrafted features, such as SIFT (Lowe, 2004), SURF (Bay et al., 2006), and BRIEF (Calonder et al., 2010).”
MethodSun, W., Chen, W., Huang, R., & Tian, J. (2024) · Sensors · doi:10.3390/s24030855 · Cited by 8
Stathoulopoulos, N., Pagliari, E., Davoli, L., et al. (2023) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar58858.2023.10406402 · Cited by 6
Research on Image-Based 3D Reconstruction Method in Underwater Welding Scenes
Chi, P., Wang, Z., Liao, H., Li, T., Wu, X., Tian, J., & Zhang, Q. (2023) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd60522.2023.10490960 · Cited by 7
“SURF (Speeded Up Robust Features) has improved the SIFT algorithm to enhance its efficiency[9].”
MethodChen, Z., Zhao, R. Z., Guo, X., et al. (2024) · Sensors · doi:10.3390/s24092859 · Cited by 6
“…smallest right singular vector of ψ , scaled so that the last element is 1, and the following equation holds: During the registration process, SURF [59] is used to compute features in each frame of the image, and then RANSAC [60] is employed to eliminate point matches with significant errors,…”
MethodTracking and co-location of global point clouds for large-area indoor environments
Michiels, N., Jorissen, L., Put, J., et al. (2024) · Virtual Reality · doi:10.1007/s10055-024-01004-0 · Cited by 6
“We use SURF (Bay et al. 2006) features for matching.”
Crack Detection of Curved Surface Structure Based on Multi-Image Stitching Method
Cui, D., & Zhang, C. (2024) · Buildings · doi:10.3390/buildings14061657 · Cited by 6
“Scholars have successively proposed SURF [17], ASIFT [18], CSIFT [19], and other feature algorithms.”
Zhang, Z., Wu, R., Li, D., et al. (2024) · Frontiers in Marine Science · doi:10.3389/fmars.2024.1418113 · Cited by 6
Samanta, S., & Chanda, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41914-0_50 · Cited by 6
Human Attention Modelization and Data Reduction
Mancaş, M., De, D., Riche, N., et al. (2012) · InTech eBooks · doi:10.5772/34942 · Cited by 6
“As shown in Figure 6, similarly to Gao, Seo & Milanfar (2009) introduced the time dimension in addition to his static model.”
ResultA Trip to Rome: Physical Replicas of Historical Objects Created in a Fully Automated Way from Photos
Barazzetti, L. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-18348-5_7 · Cited by 6
Guillot, C., Taron, M., Sayd, P., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22822-3_4 · Cited by 6
Rigid Transformation Using Interval Analysis for Robot Motion Estimation
Mustafa, M., Stancu, A., Pacheco-Gutiérrez, S., Codres, E., & Jaulin, L. (2015) · International Conference on Control Systems and Computer Science · doi:10.1109/cscs.2015.98 · Cited by 7
“Then, feature detector algorithms such as SIFT [18] or SURF [19], are used to find pixels with distinctive descriptors.”
Multiple-View Object Recognition in Smart Camera Networks
Yang, A. Y., Maji, S., Christoudias, C. M., et al. (2011) · Springer eBooks · doi:10.1007/978-0-85729-127-1_4 · Cited by 6
A metric of stereoscopic image retargeting quality assessment
Liu, Y., Sun, L., Zhu, W., et al. (2015) · IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP) · doi:10.1109/chinasip.2015.7230488 · Cited by 6
“Under the guide of the SURF correspondence[23], we build the relations between the regions in two images.”
MethodGPU Accelerated Target Tracking Method
Cao, J., Xie, X., Liang, J., et al. (2011) · Advances in intelligent and soft computing · doi:10.1007/978-3-642-25989-0_42 · Cited by 6
Georeferencing in Social Networks
Kelm, P., Murdock, V., Schmiedeke, S., Schockaert, S., Serdyukov, P., & Laere, O. V. (2012) · Computer communications and networks · doi:10.1007/978-1-4471-4555-4_6 · Cited by 8
Minutiae based fingerprint image hashing
Muthu, R., Bouridane, A., & Khelifi, F. (2014) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit.2014.6996981 · Cited by 6
Evaluating and Comparing of 3D Shape Descriptors for Object Recognition
Cerón, A., & Prieto, F. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41939-3_47 · Cited by 6
“Like other detectors as SIFT [9] and SURF [10], NARF gives a sort of relevant key points in a scene with a descriptor for each one, but in this case with a”
MethodNew Object Detection for On-board Robot Vision by Lifting Complex Wavelet Transforms
Takano, S., & Suzuki, E. (2011) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2011.129 · Cited by 6
“[2], that can be used in computer vision tasks like object recognition or 3D reconstruction.”
BackgroundA fast egomotion estimation method based on visual feature tracking and Iterative Closest Point
Hong, S., & Ye, C. (2014) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc.2014.6819610 · Cited by 6
Pfingsthorn, M. F., Bülow, H., Birk, A., Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2013) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-bergen.2013.6608146 · Cited by 6
“SURF features [30] are extracted from the image data and compared to previously recorded ones.”
MethodWang, K., Liu, Y., & Li, L. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942645 · Cited by 6
“The SURF feature points [7] were extracted from the natural surrounding environment of the robot and their relative motions with respect to the robot on the image plane were tracked for the position estimation.”
MethodDynamic 3D surface reconstruction and motion modeling from a pan–tilt–zoom camera
Dhou, S., & Motai, Y. (2015) · Computers in Industry · doi:10.1016/j.compind.2015.02.005 · Cited by 6
“SURF is a scale- and rotation-invariant detector by building on the strengths of the leading existing detectors and descriptors using a Hessian matrix-based measure for the detector, and a distribution-based descriptor.”
MethodInfluentialRGB-D sensor data correction and enhancement by introduction of an additional RGB view
Mkhitaryan, A., & Burschka, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696484 · Cited by 6
“For each (cid:11) j , we project the rotated plane (cid:5) to the image plane of the auxiliary sensor, which results in set of images f I g and homographies f H j g , such that: Next, for each I we extract SURF features and match them with SURF features from I RGB (cid:0) D (Fig.”
BackgroundInfluentialFrontoni, E., Ascani, A., Mancini, A., et al. (2010) · doi:10.1109/mesa.2010.5551994 · Cited by 6
Photo-mosaicing of images of pipe inner surface
Rzhanov, Y. (2011) · Signal Image and Video Processing · doi:10.1007/s11760-011-0275-z · Cited by 6
“Salient point features (keypoints) are extracted from a pair of sequential images (acquired respectively by “first” and “second” cameras) using SIFT [2], SURF [5], or a simpler Harris operator-based [6] algorithm.”
MethodSelf-help: Seeking out perplexing images for ever improving topological mapping
Paul, R., & Newman, P. M. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913509859 · Cited by 5
“A visual vocabulary (Sivic and Zisserman, 2003) of approximately 11, 000 visual words was generated by clustering SURF features (Bay et al., 2006) extracted from the Urban data set.”
MethodIntegration of 3D and 2D imaging data for assured navigation in unknown environments
Dill, E. T., & de Haag, M. U. (2010) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2010.5507244 · Cited by 6
Photogrammetric 3D reconstruction using mobile imaging
Fritsch, D., & Syll, M. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083332 · Cited by 6
“SIFT and SURF operators for fast feature detection and matching are analyzed in [10].”
MethodAn Augmented Reality Setup with an Omnidirectional Camera Based on Multiple Object Detection
Hayashi, T., Uchiyama, H., Pilet, J., et al. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.776 · Cited by 6
“SIFT [3] and SURF [6] are robust to a camera rotation and translation, and illumination change.”
BackgroundVirtual Knee Arthroscopy Using Haptic Devices and Real Surgical Images
Rasool, S., Sourin, A., Pestrikov, V., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07725-3_44 · Cited by 6
3D hand recognition for telerobotics
Hafiane, S., Salih, Y., & Malik, A. S. (2013) · IEEE Symposium on Computers & Informatics (ISCI) · doi:10.1109/isci.2013.6612390 · Cited by 6
Gillham, M., Howells, G., Spurgeon, S. K., & McElroy, B. (2013) · Sensors · doi:10.3390/s131217501 · Cited by 7
A comparison between different feature-based methods for ROV vision-based speed estimation
Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120410-3-pt-4028.00054 · Cited by 6
Rotation invariant fast features for large-scale recognition
Takacs, G., Chandrasekhar, V., Tsai, S. S., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.945968 · Cited by 6
Efficient video segment matching for detecting temporal-based video copies
Chiu, C., Tsai, T., & Hsieh, C.-Y. (2012) · Neurocomputing · doi:10.1016/j.neucom.2012.04.036 · Cited by 6
Smartphone indoor localization by photo-taking of the environment
Gao, R., Ye, F., & Wang, T. (2014) · International Conference on Communications · doi:10.1109/icc.2014.6883715 · Cited by 6
Laser and vision based map building techniques for mobile robot navigation
Majdik, A., Szőke, I., Tamás, L., et al. (2010) · IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR) · doi:10.1109/aqtr.2010.5520858 · Cited by 6
A Novel Tracking Algorithm via Feature Points Matching
Luo, N., Sun, Q., Chen, Q., Ji, Z., & Xia, D. (2015) · PLoS ONE · doi:10.1371/journal.pone.0116315 · Cited by 9
Robot mapping using local invariant feature detectors
Wang, Y.-T., Chi, C.-T., & Feng, Y.-C. (2014) · Engineering Computations · doi:10.1108/ec-01-2013-0024 · Cited by 6
A LEARNING METHOD TO DETERMINE HOW TO APPROACH AN UNKNOWN OBJECT TO BE GRASPED
Balaguer, B., & Carpin, S. (2011) · International Journal of Humanoid Robotics · doi:10.1142/s0219843611002575 · Cited by 6
Color calibration of multi-view video plus depth for advanced 3D video
Fezza, S. A., & Larabi, M. (2015) · Signal Image and Video Processing · doi:10.1007/s11760-015-0761-9 · Cited by 6
“…of local invariant features have been proposed in the literature, such as Scale Invariant Feature Transform (SIFT) [32], Speeded Up Robust Features (SURF) [28], Maximally Stable Extremal Regions (MSER) [33], Harris-Laplace [34], Principal Component Analysis (PCA-SIFT) [35], and SIFT-Flow [36].”
MethodFace identification using affine simulated dense local descriptors
Kang, B.-N., & Kim, D. (2013) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2013.6677383 · Cited by 6
“However, the blob-based keypoints detector used methods such as SIFT [12] and SURF [1] detect and generate keypoints on parts of a face image having high blobness.”
MethodToward mutual information based place recognition
Pandey, G., McBride, J. R., Savarese, S., & Eustice, R. M. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907317 · Cited by 6
Optimization of speeded-up robust feature algorithm for hardware implementation
Cai, S., Liu, L., Yin, S., et al. (2014) · Science China Information Sciences · doi:10.1007/s11432-013-4946-y · Cited by 6
Automated 3D Structure Inference of Civil Infrastructure Using a Stereo Camera Set
Fathi, H., Brilakis, I., & Vela, P. A. (2011) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/41182(416)15 · Cited by 7
An Algorithm for Stitching Images with Different Contrast and Elimination of Ghost
Su, H., Wang, J., Li, Y., et al. (2014) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2014.75 · Cited by 6
Trajectory feature fusion for human action recognition
Megrhi, S., Beghdadi, A., & Mseddi, W. S. (2014) · European Workshop on Visual Information Processing · doi:10.1109/euvip.2014.7018409 · Cited by 6
Toward Compressed 3D Descriptors
Malaguti, F., Tombari, F., Salti, S., Pau, D. P., & Stefano, L. D. (2012) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2012.9 · Cited by 6
Hashimoto, M., Okuda, H., Sumi, K., et al. (2011) · IEEJ Transactions on Industry Applications · doi:10.1541/ieejias.131.531 · Cited by 6
An object based image retrieval framework based on automatic image annotation
Bhargava, A., Shekhar, S., & Arya, K. V. (2014) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2014.7036485 · Cited by 6
A learning algorithm for model‐based object detection
Guodong, C., Xia, Z., Sun, R., et al. (2013) · Sensor Review · doi:10.1108/02602281311294324 · Cited by 6
“There are many prior work have done by using codebook representation (Elidan et al., 2006; Marr and Hildreth, 1980; Bay et al., 2006).”
3D robotic mapping: A biologic approach
Silveira, L., Guth, F., Drews, P., et al. (2013) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2013.6766531 · Cited by 6
Visual odometry using RGB-D camera on ceiling vision
Wang, H., Mou, W., Suratno, H., et al. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491051 · Cited by 6
Simplified map representation and map learning system for autonomous navigation of mobile robots
Morioka, K., Yamanaka, S., & Hoshino, F. (2013) · Intelligent Service Robotics · doi:10.1007/s11370-013-0143-5 · Cited by 6
“to image feature matching using Speeded Up Robust Features (SURF) features [12].”
Cross-modal social image clustering and tag cleansing
Peng, J., Shen, Y., & Jianping Fan, B. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.06.004 · Cited by 6
Humanitarian demining robot Gryphon: New vision techniques and optimization methods
Kaneko, A. M., Marino, M., & Fukushima, E. F. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650117 · Cited by 8
Semantic analysis of human visual attention in mobile eye tracking applications
Fritz, G., & Paletta, L. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5653005 · Cited by 6
Recognition of degraded ancient characters based on dense SIFT
Saleem, S., Hollaus, F., & Sablatnig, R. (2014) · doi:10.1145/2595188.2595201 · Cited by 6
“Similarly, Uchida et al. [12] use SURF features [1] instead of SIFT in order to recognize handwritten character.”
MethodLocal Hybrid Coding for Image Classification
Wu, X., Wang, J., & Long, M. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.643 · Cited by 6
“SIFT [6], HOG [7], SURF [8]) is represented by a linear combination of only a few bases automatically selected from an over-complete dictionary.”
MethodDirectional pedestrian counting with a hybrid map-based model
Kim, G., An, T.-K., Kim, J.-P., Cheong, Y.-G., & Kim, M.-H. (2014) · International Journal of Control Automation and Systems · doi:10.1007/s12555-013-0382-4 · Cited by 6
Key issues in automatic classification of defects in post-inspection review process of photomasks
Pereira, M. P., Maji, M., Pai, R. R., Samir, B., Seshadri, R., & Patil, P. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.964403 · Cited by 6
Active learning for semi-supervised clustering based on locally linear propagation reconstruction
Chang, C.-C., & Lin, P.-Y. (2014) · Neural Networks · doi:10.1016/j.neunet.2014.11.006 · Cited by 6
Dense statistic versus sparse feature-based approach for 3D object recognition
Decker, P., Thierfelder, S., Paulus, D. W. R., et al. (2011) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661811020246 · Cited by 6
Luckner, M., & Rzążewska, K. (2014) · Annals of Computer Science and Information Systems · doi:10.15439/2014f304 · Cited by 6
A framework for estimating geometric distortions in video copies based on visual-audio fingerprints
Roopalakshmi, R., & Reddy, G. R. M. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0424-7 · Cited by 6
“SURF is a scale and rotation invariant descriptor [10], which is popularly used in the copy detection literature to identify duplicate videos [11].”
BackgroundMethodINTENSITY AND RANGE IMAGE BASED FEATURES FOR OBJECT DETECTION IN MOBILE MAPPING DATA
Palmer, R., Borck, M., WEST, G. A. W., & Tan, T. (2012) · 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/isprsarchives-xxxix-b3-315-2012 · Cited by 6
Topological maps based on graphs of planar regions
Montijano, E., & Sagüés, C. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354184 · Cited by 6
“In all the cases we have used SURF features [1] for the matching and the computation of the homographies.”
MethodLearning of face components in coherent and disturbed constellations
Stommel, M., & Herzog, O. (2010) · doi:10.1109/ivcnz.2010.6148832 · Cited by 6
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.