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 2,201–2,300 of 14,752
A Coarse-to-Fine Approach for Remote-Sensing Image Registration Based on a Local Method
Lee, S. R. (2010) · International Journal on Smart Sensing and Intelligent Systems · doi:10.21307/ijssis-2017-416 · Cited by 33
An Online Sparsity-Cognizant Loop-Closure Algorithm for Visual Navigation
Latif, Y., Huang, G. P., Leonard, J. J., & Neira, J. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.036 · Cited by 29
Pande, P., Shelton, R. L., Monroy, G. L., Nolan, R. M., & Boppart, S. A. (2016) · Journal of the Association for Research in Otolaryngology · doi:10.1007/s10162-016-0576-6 · Cited by 33
“Some of the more popular featurematching methods include Scale-Invariant Feature Transform (SIFT) (Lowe 1999) and Speeded Up Robust Features (SURF) (Bay et al. 2006).”
MethodDimensionality reduction through PCA over SIFT and SURF descriptors
Gonzalez-Valenzuela, R. E., Schwartz, W. R., & Pedrini, H. (2012) · IEEE International Conference on Cybernetic Intelligent Systems (CIS) · doi:10.1109/cis.2013.6782160 · Cited by 32
Image Location Inference by Multisaliency Enhancement
Qian, X., Wang, H., Zhao, Y., et al. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2638207 · Cited by 32
Binary Online Learned Descriptors
Balntas, V., Tang, L. H. Y., & Mikolajczyk, K. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2679193 · Cited by 32
Engstrom, R. N., Newhouse, D., Haldavanekar, V., Copenhaver, A., & Hersh, J. S. (2017) · Joint Urban Remote Sensing Event (JURSE) · doi:10.1109/jurse.2017.7924590 · Cited by 37
“By deriving a number of spatial and spectral features from high resolution satellite imagery, including: Fourier Transform (FT) [16], Histogram of Oriented Gradients (HoG) [17], Local Binary Patterns (LBP) [18], Line Support Regions (LSR) [19], a texture derived builtup presence index (PanTex) [20], Speeded Up Robust…”
MethodHuman activity recognition in egocentric video using PNN, SVM, kNN and SVM+kNN classifiers
Kumar, K. P. S., & Bhavani, R. (2017) · Cluster Computing · doi:10.1007/s10586-017-1131-x · Cited by 35
“For features, it utilizes the total value of the Haar wavelet responses around the point of interest [33,34].”
MethodNo-Reference Image Quality Assessment Using Image Statistics and Robust Feature Descriptors
Oszust, M. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2754539 · Cited by 32
(2017) · doi:10.1145/3132211.3134456 · Cited by 32
“This technique is used by many feature detection and extraction techniques such as SIFT [38], SURF [22] and ORB [45].”
MethodDesai, A. P., Peña‐Castillo, L., & Meruvia-Pastor, O. (2017) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2017.16 · Cited by 38
A Saliency-Based Band Selection Approach for Hyperspectral Imagery Inspired by Scale Selection
Su, P., Liu, D., Li, X., & Liu, Z. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2800034 · Cited by 32
“The trace and determinant of a Hessian matrix have a strong ability to describe local structures of an image [28], [31], [32], so the Hessian matrix is used to measure the saliency of a band.”
MethodReal-Time Detection, Tracking and Classification of Multiple Moving Objects in UAV Videos
Baykara, H. C., Bıyık, E., Gül, G., Onural, D., Öztürk, A. S., & Yildiz, I. (2017) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2017.00145 · Cited by 38
Augmented Reality of the Middle Ear Combining Otoendoscopy and Temporal Bone Computed Tomography
Marroquin, R., Lalande, A., Hussain, R., Guigou, C., & Grayeli, A. B. (2018) · Otology & Neurotology · doi:10.1097/mao.0000000000001922 · Cited by 32
Fall Detection in Videos With Trajectory-Weighted Deep-Convolutional Rank-Pooling Descriptor
Zhang, Z., Ma, X., Wu, H., & Li, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2887144 · Cited by 33
“In order to estimate homography matrix, SURF features [23] and dense optical flow features are first extracted.”
MethodSantos, B. O., Valença, J., & Júlio, E. (2019) · Structural Control and Health Monitoring · doi:10.1002/stc.2320 · Cited by 32
Image and WLAN Bimodal Integration for Indoor User Localization
Redzic, M., Laoudias, C., & Kyriakides, I. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2903044 · Cited by 36
Multi-modal brain fingerprinting: A manifold approximation based framework
Kumar, K., Toews, M., Chauvin, L., Colliot, O., & Desrosiers, C. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2018.08.006 · Cited by 42
“Various local feature extraction and representation approaches [77] can be used, for example, Scale Invariant Feature Transfrom (SIFT) [53], Generalized Robust Invariant Feature (G-RIF) [78] or Speeded UP Robust Features (SURF) [79, 80].”
An Available Open-Source Vein Recognition Framework
Kauba, C., & Uhl, A. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-27731-4_4 · Cited by 32
“Similar to SIFT, SURF is another general purpose key-point extractor and descriptor proposed by Bay et al. [5].”
MethodOptimized CNN-based Diagnosis System to Detect the Pneumonia from Chest Radiographs
Aledhari, M., Joji, S., Hefeida, M., & Saeed, F. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983114 · Cited by 40
“Traditional Machine learning techniques uses feature extraction using techniques such as Scale Invariant Feature Transform (SIFT) [16], Speeded Up Robust Features (SURF) [17], and other methods [18].”
MethodReal-Time Perception and Positioning for Creature Picking of an Underwater Vehicle
Cui, S., Wang, Y., Wang, S., Wang, R., Wang, W., & Tan, M. H. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2973656 · Cited by 32
Yoneda, K., Kuramoto, A., Suganuma, N., Asaka, T., Aldibaja, M. A., & Yanase, R. (2020) · Sensors · doi:10.3390/s20041181 · Cited by 32
Image copy‐move forgery detection algorithm based on ORB and novel similarity metric
Tian, X., Zhou, G., & Xu, M. K. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1145 · Cited by 37
Novel and Robust Image Watermarking for Copyright Protection and Integrity Control
Tarhouni, N., Charfeddine, M., & Amar, C. B. (2020) · Circuits Systems and Signal Processing · doi:10.1007/s00034-020-01401-1 · Cited by 32
Comparing pedestrians’ gaze behavior in desktop and in real environments
Dong, W., Liao, H., Liu, B., Zhan, Z., Liu, H., Meng, L., & Liu, Y. (2020) · Cartography and Geographic Information Science · doi:10.1080/15230406.2020.1762513 · Cited by 44
“Evidence showed that, when used to match distorted images, ORB performed more e ffi ciently than SIFT and SURF, whereas SIFT outperformed the others in matching accuracy (Karami et al., 2017).”
InfluentialVisual Place Recognition using LiDAR Intensity Information
Giammarino, L. D., Aloise, I., Stachniss, C., & Grisetti, G. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636649 · Cited by 32
Wild-Animal Recognition in Agriculture Farms Using W-COHOG for Agro-Security
Andavarapu, N., & Vatsavayi, V. K. (2017) · International Journal of Computational Intelligence Research · doi:10.37622/ijcir/13.9.2017.2247-2257 · Cited by 32
Bridging the Gap Between Visual Servoing and Visual SLAM: A Novel Integrated Interactive Framework
Li, C., Zhang, X., Gao, H., Wang, R., & Fang, Y. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3067792 · Cited by 33
“…and robustness, ORiented Brief (ORB) features [40] are detected and matched in the images for initialization, although other features, such as scale-invariant feature transform (SIFT) [41], speeded-up robust features (SURF) [42], Harris corner features [43], and so on, are also applicable.”
BackgroundZhu, R., Guo, Z., & Zhang, X. (2021) · Remote Sensing · doi:10.3390/rs13091633 · Cited by 32
Mirzazade, A., Popescu, C., Blanksvärd, T., & Täljsten, B. (2021) · Remote Sensing · doi:10.3390/rs13142665 · Cited by 32
Extreme Rotation Estimation using Dense Correlation Volumes
Cai, R., Hariharan, B., Snavely, N., & Averbuch‐Elor, H. (2021) · 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/cvpr46437.2021.01433 · Cited by 56
A Comprehensive Survey on Multimodal Data Representation and Information Fusion Algorithms
Gaonkar, A., Chukkapalli, Y., Raman, P. J., Srikanth, S., & Gurugopinath, S. (2021) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit51480.2021.9498415 · Cited by 42
REG-Net: Improving 6DoF Object Pose Estimation With 2D Keypoint Long-Short-Range-Aware Registration
Jiang, J., He, Z., Zhao, X., Zhang, S., Wu, C., & Wang, Y. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3165979 · Cited by 33
“In the pose estimation of texture-rich objects [19] and regular”
BackgroundLocation graphs for visual place recognition
Stumm, E. S., Christopher Mei, A., Lacroix, S., & Chli, M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139964 · Cited by 33
3D Object Recognition Using Hyper-Graphs and Ranked Local Invariant Features
Xia, S., & Hancock, E. R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89689-0_16 · Cited by 30
“Recently, local invariant feature extraction (LIFE) methods[5] [8][10], such as SIFT, PCA-SIFT,GLOH and SURF, have proven successful and have been widely used for object recognition [5] [9], scene classification [1][2] [7] and video retrieval [12][13].”
MethodSIFT-CCH: Increasing the SIFT distinctness by Color Co-occurrence Histograms
Ancuți, C., & Bekaert, P. (2007) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2007.4383677 · Cited by 39
[POSTER] Realtime Shape-from-Template: System and Applications
Collins, T., & Bartoli, A. (2015) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2015.35 · Cited by 32
“These match salient keypoints from the template’s texturemap and the video frame using e.g. SURF [3].”
MethodSimultaneous Global Localization and Mapping
Choi, H., Yang, K. W., & Kim, E. (2013) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2013.2274822 · Cited by 32
“Known correspondence approaches usually extract unique features from measurements, called “descriptors” [4]–[7].”
BackgroundInteractive bookshelf surface for in situ book searching and storing support
Matsushita, K., Iwai, D., & Sato, K. (2011) · Augmented Human International Conference · doi:10.1145/1959826.1959828 · Cited by 32
Algorithms for video retargeting
Kopf, S., Haenselmann, T., Kiess, J., Guthier, B., & Wolfgang Effelsberg, A. (2011) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0717-6 · Cited by 32
Initial experiments on 3D modeling of complex disaster environments using unmanned aerial vehicles
Ferworn, A., Tran, J., Ufkes, A., & D’souza, A. (2011) · IEEE International Symposium on Safety, Security and Rescue Robotics · doi:10.1109/ssrr.2011.6106781 · Cited by 26
“We found that as the completeness of the depth data decreased, the success of traditional feature detectors such as Shi-Tomasi [11] and descriptor based methods such as SURF [12] was lowered drastically.”
MethodMovie posters classification into genres based on low-level features
Ivašić-Kos, M., Pobar, M., & Mikec, L. (2014) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro.2014.6859750 · Cited by 36
“In the future work, we plan to test the dense SURF [13], GIST [14] and other visual low-level features used for scene representation [10] as well as features for text recognition.”
MethodLocalizing Genes to Cerebellar Layers by Classifying ISH Images
Lior, K., Liscovitch, N., & Chechik, G. (2012) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002790 · Cited by 41
Design of a Multi-Sensor Cooperation Travel Environment Perception System for Autonomous Vehicle
Chen, L. F., Li, Q., Li, M., Zhang, L., & Mao, Q. (2012) · Sensors · doi:10.3390/s120912386 · Cited by 34
A fast feature extraction in object recognition using parallel processing on CPU and GPU
Kim, J., Park, E., Cui, X., Kim, H., & Gruver, W. A. (2009) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2009.5346612 · Cited by 32
Andreopoulos, A., & Tsotsos, J. K. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.91 · Cited by 41
FAB-MAP: Appearance-Based Place Recognition and Mapping using a Learned Visual Vocabulary Model
Cummins, M., & Newman, P. M. (2010) · International Conference on Machine Learning · Cited by 35
Muijrers, R., van Woudenberg, J. G. J., & Batina, L. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-27257-8_17 · Cited by 32
“To be more speci c the proposed algorithm is inspired by U-SURF [3].”
MethodInfluentialSpatio-temporal action localization and detection for human action recognition in big dataset
Megrhi, S., Jmal, M., Mseddi, W. S., & Beghdadi, A. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.10.016 · Cited by 32
“As for interest points detectors, SIFT (Scale Invariant Feature Transform) [15] and SURF (Speed-Up-RobustFeatures) [16] descriptors are widely employed.”
BackgroundMethodInfluentialGait Recognition Using Motion Trajectory Analysis
Khan, M. H., Li, F., Farid, M. S., & Grzegorzek, M. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-59162-9_8 · Cited by 37
“…been successfully exploited in various computer vision problems; SIFT (Scale Invariant Feature Transform) [20], SURF (Speeded-Up Robust Feature) [21], HOG (Histogram of Oriented Gradient) [22], HOF (Histogram of Optical Flow) [23], MBH (Motion Boundary Histogram) [24], and trajectory [25] are a…”
MethodProduct image classification using Eigen Colour feature with ensemble machine learning
Oyewole, S. A., & Olugbara, O. O. (2017) · Egyptian Informatics Journal · doi:10.1016/j.eij.2017.10.002 · Cited by 33
Mohamed, B. A., & Afify, H. M. (2018) · Cairo International Biomedical Engineering Conference · doi:10.1109/cibec.2018.8641799 · Cited by 35
“[22] and based on Hessian matrix and 2D Haar wavelet [23].”
PHOTOGRAMMETRIC SURVEY WITH FISHEYE LENS FOR THE CHARACTERIZATION OF THE LA SASSA CAVE
Alessandri, L., Baiocchi, V., Pizzo, S. D., 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-2-w9-25-2019 · Cited by 32
Sadeghi‐Tehran, P., Angelov, P. P., Virlet, N., & Hawkesford, M. J. (2019) · Journal of Imaging · doi:10.3390/jimaging5030033 · Cited by 38
Yuan, J., Guo, Z., Lv, L., et al. (2007) · Cited by 32
DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local FeaturesPreprint
Kang, R., Shi, J., Li, X., Liu, Y., & Liu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.07223 · Cited by 60
“Based on classical hand-craft local features like SIFT [31], SURF [5], ORB [36], early combination of low-level machine learning and local feature descriptors pro-2 duce PCA-SIFT [19], ASD [43], BOLD [4], Binboost [40], RFD [11], RMGD [13], GRIEF[23] etc.”
Large-scale fingerprint identification on GPU
Cappelli, R., Ferrara, M., & Maltoni, D. (2015) · Information Sciences · doi:10.1016/j.ins.2015.02.016 · Cited by 31
Research on Pedestrian Detection Algorithm Based on MobileNet-YoLo
Liu, L., Ke, C., He, L., & Xu, H. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8924027 · Cited by 43
A deep learning-based framework for retinal fundus image enhancement
Lee, K., Song, S. J., Lee, S., Yu, H. G., Kim, D. I., & Lee, K. M. (2023) · PLoS ONE · doi:10.1371/journal.pone.0282416 · Cited by 33
Srivastava, D., Singh, S. S., Rajitha, B., Verma, M., Kaur, M., & Lee, H.-N. (2023) · IEEE Access · doi:10.1109/access.2023.3308911 · Cited by 49
Context in object detection: a systematic literature review
Jamali, M., Davidsson, P., Khoshkangini, R., Ljungqvist, M. G., & Mihailescu, R. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11186-x · Cited by 53
FLARE: Feed-Forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
Zhang, S., Wang, J., Xu, Y., Xue, N., Rupprecht, C., Zhou, X., Shen, Y., & Wetzstein, G. (2025) · 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/cvpr52734.2025.02043 · Cited by 216
“We therefore reported its optimal results.”
A new algorithm for image recognition and classification based on improved Bag of Features algorithm
Li, K., Wang, F., & Zhang, L. (2015) · Optik · doi:10.1016/j.ijleo.2015.08.219 · Cited by 37
Robust large scale monocular visual SLAM
Bourmaud, G., & Mégret, R. (2015) · 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.2015.7298772 · Cited by 27
“First of all, SURF PoI [14] are extracted from all keyframes.”
MethodFast Neuromimetic Object Recognition Using FPGA Outperforms GPU Implementations
Orchard, G., Martin, J. G., Vogelstein, R. J., & Etienne‐Cummings, R. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2253563 · Cited by 32
Detection and tracking of RC model aircraft in LWIR microgrid polarimeter data
Ratliff, B. M., LeMaster, D. A., Mack, R. T., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.894669 · Cited by 31
Online generation of scene descriptions in urban environments
Posner, I., Schroeter, D., & Newman, P. M. (2008) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.08.009 · Cited by 31
“– SURF descriptors [3] for the POIs.”
The IMMED Project: Wearable Video Monitoring of People with Age Dementia
Mégret, R., Dovgalecs, V., Wannous, H., et al. (2010) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 31
Crowdtruth validation: a new paradigm for validating algorithms that rely on image correspondences
Maier‐Hein, L., Kondermann, D., Roß, T., Mersmann, S., Heim, E., Bodenstedt, S., Kenngott, H., Sanchez, A., Wagner, M., Preukschas, A. A., et al. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1168-3 · Cited by 31
Learning Human Actions by Combining Global Dynamics and Local Appearance
Luo, G., Yang, S., Tian, G., Yuan, C., Hu, W., & Maybank, S. J. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2329301 · Cited by 34
Automatic Descriptor-Based Co-Registration of Frame Hyperspectral Data
Vakalopoulou, M., & Karantzalos, K. G. (2014) · Remote Sensing · doi:10.3390/rs6043409 · Cited by 40
Building Location Models for Visual Place Recognition
Stumm, E. S., Christopher Mei, A., & Lacroix, S. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915570140 · Cited by 29
“Various global image descriptors have been applied to the task of place recognition, such as binary descriptors in BRIEF-Gist [Sünderhauf and Protzel, 2011], or vectorial descriptors in WI-SURF [Badino et al., 2012].”
MethodInfluentialMoving Object Detection and Tracking in Forward Looking Infra-Red Aerial Imagery
Bhattacharya, S., Idrees, H., Saleemi, I., Ali, S., & Shah, M. A. (2011) · Springer eBooks · doi:10.1007/978-3-642-11568-4_10 · Cited by 35
Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories
Fenzi, M., Leal-Taixé, L., Rosenhahn, B., et al. (2013) · 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.2013.103 · Cited by 31
“We evaluated the performance of our method by using two different feature descriptors, SIFT [15] and SURF [2].”
MethodInfluentialPeople Reidentification in a Camera Network
de Oliveira, Í. O., & Pio, J. L. D. S. (2009) · IEEE International Conference on Dependable, Autonomic and Secure Computing · doi:10.1109/dasc.2009.33 · Cited by 31
“In this paper, we use the Bay, Tuytelaars, and Van Gool [10] detector.”
BackgroundMethodInfluentialAn Orientation Invariant Visual Homing Algorithm
Churchill, D. G., & Vardy, A. (2012) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-012-9730-5 · Cited by 35
“Numerous variants of the SIFT framework have been proposed and could be used for this purpose (e.g. SURF features [47]).”
MethodBBN VISER TRECVID 2011 Multimedia Event Detection System
Natarajan, P., Natarajan, P., Manohar, V., Wu, S., Tsakalidis, S., Vitaladevuni, S. N. P., Zhuang, X., Prasad, R., Ye, G., Liu, D., et al. (2011) · Journal of International Crisis and Risk Communication Research · Cited by 32
Visual Information Retrieval using Java and LIRE
Lux, M., & Marques, O. (2013) · Synthesis lectures on information concepts, retrieval, and services · doi:10.2200/s00468ed1v01y201301icr025 · Cited by 59
Towards the verification of image integrity in online news
Pasquini, C., Brunetta, C., Vinci, A. F., Conotter, V., & Boato, G. (2015) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2015.7169801 · Cited by 29
“We exploited the Matlab Computer Vision System Toolbox, which offers algorithms for both SURF computation (based on [7]), face detection (based on [8]), MSER features computation (based on [9]) and feature matching [10].”
MethodFEATURE VECTOR APPROXIMATION BASED ON WAVELET NETWORK
Dammak, M., Mejdoub, M., Zaied, M., & Amar, C. B. (2012) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0003776803940399 · Cited by 31
Fast Automatic Detection of Wildlife in Images from Trap Cameras
Figueroa, K., Camarena–Ibarrola, A., García, J. R. L., & Tejeda, H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_114 · Cited by 31
Motion keypoint trajectory and covariance descriptor for human action recognition
Yi, Y., & Wang, H.-L. (2018) · The Visual Computer · doi:10.1007/s00371-016-1345-6 · Cited by 32
“To obtain matched points for computing M, we employ two complementary strategies including optical-flow-based matches and SURF-based matches.”
MethodInfluentialTelecom Inventory Management via Object Recognition and Localisation on Google Street View Images
Hebbalaguppe, R., Garg, G., Hassan, E., Ghosh, H., & Verma, A. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.86 · Cited by 38
“The descriptors such as SURF [3], SYBA [6], and TreeBASIS [10] are hand crafted features werent as powerful enough to provide matches between two distinct object instances from the same visual object category.”
BackgroundHistogram shifting-based blind watermarking scheme for copyright protection in 5G
Manikandan, V. M., & Masilamani, V. (2018) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2018.03.007 · Cited by 31
Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India
Ranguelova, E., Weel, B., Roy, D., et al. (2018) · European Journal of Remote Sensing · doi:10.1080/22797254.2018.1535838 · Cited by 31
“Step 6: image pixel segmentation After the multi-class SVM classifiers with all combinations of different parameters (such as tile size, N and SURF vocabulary size, V ) have been trained on the BoVW from SURF features extracted from all “ pure ” tiles from the selected ROIs, the best performing model with correspondin…”
InfluentialToward Optimal Prediction Error Expansion-Based Reversible Image Watermarking
Roy, A., & Chakraborty, R. S. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2911042 · Cited by 31
Towards an Inpainting Framework for Visual Cultural Heritage
Jboor, N. H., Belhi, A., Al-Ali, A. K., Bouras, A., & Jaoua, A. (2019) · IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT) · doi:10.1109/jeeit.2019.8717470 · Cited by 34
“We then compute visual global features of each image using either CNN features, SIFT [17] or SURF [18] features with Bag of Visual Words, etc.”
MethodScene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization
Li, X., Ylioinas, J., Verbeek, J. J., & Kannala, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11015-4_19 · Cited by 35
Sarkhel, R., & Nandi, A. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/466 · Cited by 36
“Our second baseline (A2 et al. , 2006] for encoding each document.”
BackgroundDing, Y., Yang, J. J., Ponce, J., & Kong, H. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00174 · Cited by 30
Dynamic auto-weighted multi-view co-clustering
Hu, S., Yan, X., & Ye, Y. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107101 · Cited by 35
Cheng, R., Wang, K., Lin, S., Hu, W., Yang, K., Huang, X. M., Li, H., Sun, D., & Bai, J. Y. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917508 · Cited by 28
Natural Feature-based Visual Servoing for Grasping Target with an Aerial Manipulator
Luo, B., Chen, H., Quan, F., et al. (2020) · Journal of Bionic Engineering · doi:10.1007/s42235-020-0017-4 · Cited by 31
“Many feature extraction algorithms have been developed in the field of computer vision [32] , where SIFT [33] , SURF [34] and ORB [35] are the three most popular algorithms.”
MethodNawaz, S. A., Li, J., Bhatti, U. A., Mehmood, A., Shoukat, M. U., & Bhatti, M. A. (2020) · PLoS ONE · doi:10.1371/journal.pone.0232902 · Cited by 31
A novel image retrieval method based on multi-features fusion
Niu, D., Zhao, X., Lin, X., & Zhang, C. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115911 · Cited by 32
Trajectory and image-based detection and identification of UAV
Liu, Y., Liao, L., Wu, H., Qin, J., He, L., Yang, G., Zhang, H., & Zhang, J. (2020) · The Visual Computer · doi:10.1007/s00371-020-01937-y · Cited by 35
“Before the extensive application of deep learning in the detection of small flying objects, the hand-designed features of the image (such as HOG [22], Fourier descriptors [23] and SURF [24]) are generally applied in the detection and classification of UAV.”
MethodHussain, R., Lalande, A., Girum, K. B., Guigou, C., & Grayeli, A. B. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02240-w · Cited by 33
“Consequently, an image feature tracking based on SURFwas used to determine the transformation TT between consecutive image frames for each camera [30,36].”
MethodSteno, P., Alsadoon, A., Prasad, P. W. C., Al-Dala’in, T., & Alsadoon, O. H. (2020) · The Journal of Supercomputing · doi:10.1007/s11227-020-03418-4 · Cited by 31
“Deep learning-based object detection frameworks perform better with higher real-time detection speed than the traditional detection methods such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF) [4, 5].”
MethodIntelligent Hoisting with Car-Like Mobile Robots
Li, H., Luo, X., & Skitmore, M. (2020) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001931 · Cited by 32
“This involves two methods – speeded up robust 228 features (SUBF) (e.g., Bay et al, 2006, 2008) and a normalized eight-point algorithm (Hartley, 229 1997) – to realize automatic computation.”
MethodDing, J., Yan, Z., & We, X. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10040234 · Cited by 31
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.