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 12,701–12,800 of 14,752
Multimedia Databases: Description, Analysis, Modeling, and Retrieval
Oria, V., Li, Y., Dorai, C., et al. (2022) · Chapman & Hall/CRC eBooks · doi:10.1201/9780429171529-107
Speed Up Learning based Descriptor for Face Verification
Wang, H., Kang, B.-N., Yoon, J., et al. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004278007620767
Collaborative Annotation of Videos Relying on Weak Consistency
Wilk, S., Kopf, S., & Wolfgang Effelsberg, A. (2016) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2907983
An Efficient Approach to Object Recognition for Mobile Robots
Ahmed, M. S., Saatchi, R., & Caparrelli, F. (2013) · International Conference on Pervasive and Embedded Computing and Communication Systems · doi:10.5220/0004314800600065
Reclassement d'images par le contenu.
Quénot, G., & Thollard, F. (2012) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.24348/coria.2012.203
RECOGNITION OF TRAFFIC SIGN FOR DRIVER ASSISTANCE SYSTEMS
Ameen, N. M. A. (2014) · International Journal of Engineering Development and Research
Zhang, X., Chen, G., Saruta, K., et al. (2015) · Journal of Computers · doi:10.17706/jcp.10.1.57-67
Lin, S., Ke, J.-C., Liu, H.-Y., et al. (2014) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2014.6987748
Casamento de modelos baseado em projeções radiais e circulares invariante a pontos de vista.
Lopez, G. A. P. (2016) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.3.2016.tde-24052016-150250
Hoai, V., Thai, T., & Quoc, L. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070536
“[27] such as SIFT [7] and SURF [3] with Adaboost algorithm.”
MethodMultimodal Retinal Image Registration method Based on Speed-up Robust Feature
Xiao, Z., Zhu, W., Zhang, F., et al. (2016) · doi:10.2991/wartia-16.2016.137
Integral-map Based Fast and Robust Screening Method for Endoscope image
lei, J. G. W. (2009)
A Robotic Mobile Platform for Application in Automotive Production Environment
Rovetta, A. (2013) · Mechanisms and machine science · doi:10.1007/978-3-319-00398-6_18
Trajectory-based stereo visual odometry with statistical outlier rejection
Zhang, J., Gan, R., Zeng, G., et al. (2015) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2015.7486575
Efficient near-duplicate image detection with created feature subset
Yildiz, B. C., & Demirci, M. F. (2016) · doi:10.1109/siu.2016.7496136
Detecting Moving Object via Projection of Forward-Backward Frame Difference
Bian, Z., & Wang, L. (2016) · International Journal of Future Generation Communication and Networking · doi:10.14257/ijfgcn.2016.9.5.14
“SIFT (Scale-Invariant Feature Transform) [4], HOG (Histogram of Oriented Gradient) [5], SURF (Speeded-Up Robust Features) [6], FAST (Features from Accelerated Segment Test) [7] are widely studied spatial detectors in object detection as their merit on accuracy, unfortunately, the detectors are…”
MethodA GPU-based MapReduce framework for MSR-Bing Image Retrieval Challenge
Wang, L., Wang, H., & Xiao, B. (2015) · International Conference on Communications and Networking in China (ChinaCom) · doi:10.1109/chinacom.2015.7497981
“Most of the state-of-the-art image retrieval systems [1] are built upon local features [2], [3] and the Bag-of-Words (BoW) [4] representation because of their discrimination and efficiency.”
BackgroundReal-time panoramic background subtraction on GPU
Büyüksaraç, S., Akar, G. B., & Temizel, A. (2016) · doi:10.1109/siu.2016.7495914
Feature learning for RGB-D scene understanding
Wang, A. (2016) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/68538
“[7] described a feature learning approach which learns dictionaries from RGB-D data based on K-means clustering of local-patch features, where the image patches are extracted around the interest points detected by SURF features [6].”
Reconstruction and recognition of confusable models using three-dimensional perception
Bueno, J. G. (2016) · Dialnet (Universidad de la Rioja)
An Improved Harris-SIFT Algorithm Based on Rotation-invariant LBP Operator
Yang, L., Ren, Y., Cai, J., et al. (2016) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2016.9.6.14
Large-scale image collection cleansing, summarization and exploration
Jianping Fan, B., & Yang, C. (2012) · NC Digital Online Collection of Knowledge and Scholarship (The University of North Carolina at Greensboro)
Improving the accuracy of visual odometry from point features
Cumani, A. (2010)
Parallel Multimedia Algorithms in P2G
Olsen, P. N. (2011) · Duo Research Archive (University of Oslo)
Fast Image Search by Trees of Keypoint Descriptors
Najgebauer, P., & Scherer, R. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-19090-7_41
Image Descriptors in Angiography
Hofschen, K., Geissler, T., Rieke, N., zu Berge, C. S., Navab, N., & Demirci, S. (2016) · Informatik aktuell · doi:10.1007/978-3-662-49465-3_50
Improving the Performance of CBIR with Genetic Approach and Feedback
Bourass, Y., Bahri, A., & Zouaki, H. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-287-990-5_29
“The weight of each metric is obtained by implementing a query processor based on the entropy impurity method [17] to compute the dynamic weights for each descriptor vector.”
MethodBhavani, R., & Karthikeyan, A. (2014)
Ball Detection for Robotic Soccer: A Real-Time RGB-D Approach
Morais, A., Costa, P., & Lima, J. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-27149-1_44
“Also in [6] an improvement of the SIFT method techniques increasing the algorithm processing time with similar results.”
Light-weight binary code embedding of local feature distribution in image search
Wei, S., Zhao, Y., Li, J., & Zhang, Y. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.082
Cesaro, M. (2013) · Padua@research (University of Padova)
Arnesen, S. A. F. (2010) · NORA - Norwegian Open Research Archives
Highly Parallelizable Algorithm for Keypoint Detection in 3-D Point Clouds
Garstka, J., & Peters, G. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-31898-1_15
“We examined the mean Euclidean distances between n nearest neighbors of m randomly selected 3-D points, with n ∈ [2, 10] andm ∈ [1, 100].”
MethodHigh speed 3D object retrieval using skewness value
Sintunata, V., & Aoki, T. (2016) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tenconspring.2016.7519435
“In order to test the speed of our algorithm, the traditional SURF, where each image in the database is compared with the query image, is compared with our algorithm.”
InfluentialDevelopment of a Hover-capable AUV System for In-water Visual Inspection via Image Mosaicking
Hong, S., Park, J., Kim, T., et al. (2016) · Journal of Ocean Engineering and Technology · doi:10.5574/ksoe.2016.30.3.194
An Improved Algorithm Based on SURF for MR Infant Brain Image Registration
Du, K., Domas, S., Lenczner, M., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-42294-7_41
“In 2006, Herbert proposed the SURF algorithm [5], which is faster and more robust.”
MethodGeometric indexing for recognition of places based on expanded delaunay triangulation
Lara-Álvarez, C. A., & Rojas‐Domínguez, A. (2016) · Intelligent Data Analysis · doi:10.3233/ida-160848
“Keypoint descriptors such as SIFT [20], SURF [2], MSER [21], etc. offer some degree of invariance to these phenomena, and have been successfully used in many applications.”
A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial StructurePreprint
Samanta, S., & Chanda, B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.00199
A Large Margin Learning Method for Matching Images of Natural Objects with Different Dimensions
Zhou, H., Zhou, J. W., Yang, H., et al. (2015) · Advances in environmental engineering and green technologies book series · doi:10.4018/978-1-4666-9435-4.ch015
Systematic Pattern Code Design on Kitchenware for Operable Activities in Tangible User Interface
Wu, F., Wang, P.-C., & Tan, S.-H. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-41983-1_57
SSI Modalities II: Articulation and Its Consequences
Freitas, J., Teixeira, A. J. S., Dias, M. S., & Silva, S. (2016) · Springer briefs in electrical and computer engineering · doi:10.1007/978-3-319-40174-4_3
Modeling Attention in Engineering
Mancaş, M. (2016) · Springer series in cognitive and neural systems · doi:10.1007/978-1-4939-3435-5_7
Object Classification and Tracking in Real Time: An Overview
Das, A. J., Saikia, N., & Sarma, K. K. (2017) · IGI Global eBooks · doi:10.4018/978-1-5225-1837-2.ch063
An Application of Robot Arm for Dynamic Field of View Expansion During Laparoscopy
Kumar, A., Wang, Y., Wu, C.-J., et al. (2016) · Computer Aided Surgery · doi:10.1007/978-4-431-55810-1_9
A Projectivity Diagnosis of Local Feature Using Template Matching
Ohki, H., Taniguchi, R.-I., Inoue, S., et al. (2016) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.136.1112
Views selection for SIFT based object modeling and recognition
Bruno, A., Greco, L., & Cascia, M. L. (2016) · Multidimensional Signal Processing Workshop · doi:10.1109/ivmspw.2016.7528176
The Research of an Image Retrieval Engine for Non-Standard Commodity Shopping
Chen, H., Li, X., & Pei-you, H. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-1-4614-3872-4_245
A TREE-CLIMBING ROBOT FOR INVASIVE INSECT DETECTION
Babu, B. P. W., Read, E. T., GOSTANIAN, J. A., et al. (2012) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789814415958_0085
Scene Text Detection and Tracking for Wearable Text-to-Speech Translation Camera
Goto, H., & Liu, K. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-41267-2_4
Toward Accurate Feature Detectors Performance Evaluation
Smirnov, P., Semenov, P., Redkin, A., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23968-7_6
Visual Human Tracking in Wireless Cameras Networks A SURF-Based Approach
Zhou, Y., Snoussi, H., Zheng, S., et al. (2011) · IGI Global eBooks · doi:10.4018/978-1-61350-153-5.ch008
A Color Constancy Algorithm Using Photodetector Characteristics of a Camera for Indoor Scenes
Kim, U.-H., & Kim, J.-H. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-31293-4_41
“Scale invariant features (SIFT) [3], speeded up robust features (SURF) [5], binary robust independent elementary features (BRIEF) [6] combine gradients and histograms of grey scale patches around the point of interest to generate illumination invariant features.”
BackgroundA Review of Registration Methods on Mobile Robots
Morell, V., Orts‐Escolano, S., García‐Rodríguez, J., Cazorla, M., & Viejo, D. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-2672-0.ch009
Duda, P., Jaworski, M., Pietruczuk, L., et al. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-19090-7_40
Rectification for fronto-parallel camera movement in 3D reconstruction of printed circuit boards
Breier, M., Kusters, P., Konig, A., et al. (2016) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc.2016.7520359
Orientierung großer Bildverbände
Mayer, H., & Michelini, M. (2017) · Springer eBooks · doi:10.1007/978-3-662-47094-7_39
Feature Extraction for Effective Content-Based Cloth Image Retrieval in E-Commerce
Li, L., & Li, J. (2016) · Communications in computer and information science · doi:10.1007/978-981-10-2053-7_33
Using invariant feature descriptors for an efficient image retrieval
Hbali, S., Sadgal, M., & Fazziki, A. E. (2015) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa.2015.7507156
A Visual Attention Algorithm Designed for Coupled Oscillator Acceleration
Thomas, C., Kovashka, A., Chiarulli, D. M., & Levitan, S. P. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.108
“Every time one of the SURF descriptors associated with a segment matches a SURF descriptor in another bounding box of the same class, a counter associated with the segment is increased by 1.”
MethodInfluential3D Camera Tracking for Mixed Reality using Multi-Sensors Technology
Ababsa, F., Zendjebil, I., & Didier, J.-Y. (2011) · IGI Global eBooks · doi:10.4018/978-1-61350-326-3.ch027
Image matching based on multiscale increment sign correlation and iterative correction
Yan, L., Yang, S., Li, S., et al. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7553968
A method of visual sensor employment planning for UAV target detection
Yifeng, N., Zhong, Z., Daibing, Z., et al. (2016) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2016.7531091
“[12] Bay, H., Tuytelaars, T., Gool, L.V. SURF: Speeded up robust features.”
MethodGorokhovatsky, V. A., Berestovskyi, A. E., & Peredrii, O. (2016) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2016-2-11
“Разностное группирование (РГ) наиболее эффективно в применении к векторам большой размерности, которая для структурных признаков SURF равна 64 и выше [4].”
A Comparative Study of Local Image Feature Description
Zhou, L., & Tao, Y. (2016) · International Conference on Sensor Network and Computer Engineering (ICSNCE) · doi:10.2991/icsnce-16.2016.66
Selectively Aggregated Fisher Vectors of Query Video for Mobile Visual Search
Xiaohe, Z., Wang, Y., Liu, Z., et al. (2016) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2016.45
Indoor robot 3D scene reconstruction optimization using planar features
Lv, Z., Zheng, J., & Liu, Y. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2244965
“[19] We take Euclidean distance as similarity measure.”
MethodTREAT: Terse Rapid Edge-Anchored Tracklets
Trichet, R., & O'Connor, N. E. (2016) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2016.7738078
“Efficient computation of similar features is proposed by SURF [5].”
MethodMulti-sensor image fusion and target classification for improved maritime domain awareness
Pothitos, M., Tummala, M., Scrofani, J. W., & McEachen, J. (2016) · Cited by 3
MOTION COMPENSATION FOR HAND HELD CAMERA DEVICES
Patel, D. (2015) · International Journal of Research in Engineering and Technology · doi:10.15623/ijret.2015.0402107
An efficient mechanism for storing photo albums on cloud storage
Evangeline, D. P., Edward, V. C. P., & Anandhakumar, P. (2015) · International Conference on Advanced Computing · doi:10.1109/icoac.2015.7562802
Hybrid visual servoing for tracking multiple targets with a swarm of mobile robots
Alemu, G. M. (2016) · International Journal Of Engineering And Computer Science · doi:10.18535/ijecs/v4i11.36
A User Interaction Bug Analyzer based on Imaging Processing
Méndez-Porras, A., Alfaro-Velásco, J., Jenkins, M., et al. (2016) · CLEI electronic journal · doi:10.19153/cleiej.19.2.3
“We used the interest point detector and descriptor SURF [18] to get interest points in each image.”
MethodGhost-free dual-exposure HDR for dynamic scenes
Bouzaraa, F., Halfaoui, I., & Urfalıoǧlu, O. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532656
Emergency Light Detection inTunnel Environment by Combining Motion and Appearance Information
Wang, Z., Kagesawa, M., Ono, S., et al. (2012) · doi:10.11188/seisankenkyu.64.219
EasyFlow: increasing the convergence basin of variational image matching with a feature‐based cost
Braux-Zin, J., Dupont, R., Bartoli, A., et al. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2016.0090
“We use the public C++ implementation from [47] reusing the same SURF [11] as input of our algorithm for a fair comparison.”
InfluentialImage retrieval by geological proximity using deep neural network
Jia, D., Su, Y., & Li, C. (2016) · International Symposium on Innovations in Intelligent SysTems and Applications · doi:10.1109/inista.2016.7571859
“Descriptor extraction algorithms like SIFT and SURF are not reliable for photos with motion blur or various illumination.”
InfluentialFischer, D. (2013) · UWSpace (University of Waterloo)
Blind Facial Image Quality Enhancement Using Non-Rigid Semantic Patches
Hait-Fraenkel, E., & Gilboa, G. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2686003
The comparision of different visual features on RGB-D mapping
Li, Y., Wang, J., Zhong, C., et al. (2016) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2016.7578758
Correlation filters and feature extraction for facial image analysis
Zhou, L. (2014) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/59211
A framework for associated news story retrieval
Younessian, E. (2013) · doi:10.32657/10356/54903
Monocular Vision-Based Obstacle Detection for Unmanned Systems
Wang, C. (2011) · UWSpace (University of Waterloo)
Impact of Neuroscience in Robotic Vision Localization and Navigation
Siagian, C., & Itti, L. (2016) · Cognitive science and technology · doi:10.1007/978-981-10-0213-7_11
Cooperative simultaneous localization and mapping framework
Nasir, A. K. (2014) · Recherche und Kataloge (Universitätsbibliothek Siegen) · Cited by 2
Transfer learning for visual recognition and text categorization
Duan, L. (2012) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/48658
Robust Feature Detection for a Mobile Robot using a Multi-View Single Camera
Ryu, J., Zhang, D., & Nishimura, T. (2008) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/si.2008.4770435
Recursive Estimation of Structure and Motion from Monocular Images
Fakih, A. H. (2010) · UWSpace (University of Waterloo)
Spatio-Temporal Co-Occurrence Characterizations For Human Action Classification
Sabri, A. Q. M., Boonært, J., Abdullah, E. R. M. F., et al. (2017) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol30no3.1
Piecewise Planar Region Matching for High-Resolution Aerial Video Tracking
Yi, M., & Sui, L. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-48499-0_10
3D pooling on local space-time features for human action recognition
Hadibarhaghtalab, N., & Azimifar, Z. (2013) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/iranianmvip.2013.6779992
Zhang, H., Lin, Y., & Xiao, F. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2240637
“For the method based on Laplacian scale- space theory given in [25], target detection is archived by tuning and maximizing SCR in Laplacian scale-space.”
MethodAn automated workflow for observing track data in 3-dimensional geo-accurate environments
Walvoord, D. J., Blose, A. C., & Brower, B. V. (2014) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2014.7041895
“Speeded-Up Robust Feature (SURF) [1], Oriented FAST and Rotated BRIEF (ORB) [14], and Daisy [16] are useful alternatives that offer various advantages and disadvantages.”
BackgroundGazeVideoAnalyser: A Modular Software Approach Towards Automatic Annotation of Gaze Videos
Essig, K., Abashidze, D., Manjunath, P., & Schack, T. (2019) · PUB – Publications at Bielefeld University (Bielefeld University) · doi:10.2390/biecoll-saga2015_2
Vidula, T. V., & Nair, V. V. (2014) · doi:10.1109/compsc.2014.7032640
Active system for hand motion recognition
Viada, A., Ortega, M., & Carrasco, M. (2012) · doi:10.1109/clei.2012.6427127
An implementation of image statiching based on binocular cameras
Wu, S., Yu, S., Chen, W., et al. (2011) · doi:10.1109/ivsurv.2011.6157031
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.