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 12,801–12,900 of 14,752
Using Recognition to Guide a Robot's Attention
Thomas, A., Ferrari, V., Leibe, B., et al. (2009) · The MIT Press eBooks · doi:10.7551/mitpress/8344.003.0036
Self-citationAn automatic deformity path tracing and estimation technique for thoracic CT image sequences
Abidi, A. I., & Singh, S. K. (2015) · doi:10.1109/cgvis.2015.7449909
“The detector is based on Hessian matrix based on its good performance in accuracy [4].”
MethodGorokhovatsky, V. A., Gorokhovatskyi, O., & Berestovskyi, A. E. (2016) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2016-3-5
Towards a new approach to video copy detection using acoustic features
Roopalakshmi, R., & Reddy, G. R. M. (2011) · doi:10.1109/imsaa.2011.6156336
Reliability Pyramid Based Dense Corresponding between Facial Texture Images
Li, Z., Gong, W., Li, W., et al. (2008) · doi:10.1109/ipgc.2008.4781401
“Nowadays, some of the sparse matching algorithms, for instance, Scale Invariant Feature Transform (SIFT) [5], Gradient Location and Orientation Histogram (GLOH) [6], and Speeded Up Robust Features (SURF) [7], can intelligently detect the scale and affine invariant features from the texture images, and exactly locate t…”
BackgroundMulti-Modality Human Action Recognition
Zhu, Y. (2016) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.7054
A combined two-stage local-spatial interest point matching algorithm
Dehghani, A., & Sutherland, A. (2013) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/iranianmvip.2013.6779959
“Extract SURF descriptor for both IP sets.”
BackgroundInfluentialThe SURF algorithm on a FPGA-based platform
Hsu, Y.-P., & Kuo, C.-H. (2014) · doi:10.1109/cacs.2014.7097211
Detecting and Tracking Volunteers in Expo Videos
Liang, J., & Zhou, Y. (2013) · doi:10.1109/ita.2013.29
Matching Feature Points in 3D World
Avdiu, B. (2012) · Jonkoping University Library (Jönköping University)
Mobile robot localization technique using road surface images
Muramatsu, S. (2014) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2014.7049107
“In this research, we use SURF[13] as the method of extraction and correspod of feature points.”
Methodransform (HT) in in in R R obotic V V ision
Hamada, M., & Boutarfa, A. (2013)
OBJECT MODELLING, DETECTION AND LOCALISATION IN MOBILE VIDEO: A STATE-OF-THE-ARTPreprint
Manzanera, A. (2011) · HAL (Le Centre pour la Communication Scientifique Directe)
Image-based Fast 3D Reconstruction
Xia, J., Wang, F., & Zheng, X. (2016) · International Conference on Measurement, Instrumentation and Automation (ICMIA) · doi:10.2991/icmia-16.2016.149
“A substitution of SIFT is SURF [5], whose descriptor has only 64 dimensions, only half of SIFT descriptors, which can reduce the matching time.”
MethodStereoscopic Images Generation By Monocular Camera
Lonare, S., & Dhengre, S. (2015)
Reconstruction of Lightweight 3D Indoor Representations using Color-Depth Cameras
Mendonça, J. N. L. (2014)
Implement of Stereo Image Correction for 3D Optical Microscope and Design Hardware System
Yoon, J., Baek, N., Kim, C., et al. (2016) · International Conference on IT Convergence and Security (ICITCS) · doi:10.1109/icitcs.2016.7740344
Hardware-Directed Feature Detection for Video Stitching in Intelligent Transportation
Parmar, Y., Kalyan, P. S., Chandrasekhar, M. S., et al. (2015) · International Conference on Advanced Computing and Communications (ADCOM) · doi:10.1109/adcom.2015.8
Estimación de movimiento en secuencias de imágenes RGB y RGB-D
Fernández, G., & Roberto, F. F. (2016)
Xu, H. X., Ishida, M., & Wang, M. (2016) · Research Ideas and Outcomes · doi:10.3897/rio.2.e11065
Anagnostopoulos, N., Iakovidou, C., Chatzichristofis, S. A., et al. (2016) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2016.7738243
Robot skill learning through human demonstration and interaction
Gu, Y. (2015) · SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)
Detecting Moving Vehicles via a Moving Monocular Omnidirectional Side Camera
Raaijmakers, M. (2012) · TU/e Research Portal
Efficient Recognition of Planar Object Using Intensity Based Matching Evaluation
Lee, J., Kim, H. S., Gao, B., et al. (2016) · ACM International Conference on Research in Adaptive and Convergent Systems (RACS) · doi:10.1145/2987386.2987436
“In spired by the research, there have been similar line of approaches to achieve enhanced invariance which is robust in various transformation[11,12].”
Methoddos Santos, J. M., da Silva, J. R., de Moura, E. S., et al. (2016) · Brazilian Symposium on Multimedia and the Web · doi:10.1145/2976796.2988178
Kirillov, S. N., Kostkin, I. V., & Elyutin, A. V. (2016) · Vestnik of Ryazan State Radio Engineering University · doi:10.21667/1995-4565-2016-57-3-88-93
Sekikawa, Y., Ikuro, S. A. T. O., Suzuki, K., et al. (2016) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.82.1054
Feature tracking using epipolar geometry for ego-motion estimation
Huang, T., Zhuang, Z.-Q., Chen, C., Chang, B. R., & Kuo, C.-C. (2015) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2015.7761563
Fast Template Matching with Pixel-Based Multi-Class Pattern Classification
Hiroki, O. H. N. O., & Hashimoto, M. (2016) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.82.1092
Metric and appearance based visual SLAM for mobile robots
Şahin, C. (2013) · Sabanci University
Introduction of a human based attention model for robotic navigation
Williams, H. A., Naqvi, S. S., Browne, W. N., & Hollitt, C. (2015) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2015.7761508
“Many place recognition techniques rely on common feature finding approaches such as SIFT [5] and SURF [6] which can handle scaling and rotations of images.”
MethodComparison of Feature Extraction Techniques in Cotton Leaf Disease Classification using CBIR
Palwe, S., Budkule, C., Sonawane, U., et al. (2015)
Short-term people re-identification using image classification
Ramakić, A., & Lenac, K. (2016) · International Conference on Smart Systems and Technologies (SST) · doi:10.1109/sst.2016.7765677
“In order to detect features in tested images, BRISK (Binary Robust Invariant Scalable Keypoints) [23], FAST (Features from Accelerated Segment Test) [24], Harris (Harris– Stephens) [25], MSER (Maximally Stable Extremal Regions) [26], MinEigen (Minimum eigenvalue algorithm) [27], and SURF [28] are used.”
MethodInfluentialEmbodied Visual Object Recognition
Wallenberg, M. (2016) · Linköping studies in science and technology. Dissertations · doi:10.3384/diss.diva-132762
Development of Bundle Adjustment with Constraint Conditions Using Line Segments of Vector Data
Fuse, T., & Kamiya, K. (2014) · Journal of the Japan society of photogrammetry and remote sensing · doi:10.4287/jsprs.53.173
Robustly Modeling The World From Photos
Wilson, K. L. (2016) · ProQuest Demo Repository · doi:10.7298/x40p0wx1
Dense 3D Mapping Using Volume Reigstration from Monocular View
Lincoln, L., & Gonzalez, R. (2016) · ... International Conference on Complex, Intelligent and Software Intensive Systems · doi:10.1109/cisis.2016.99
“Beall et al [8] proposed an underwater SLAM method which uses both SIFT and SURF [9] feature matching with bundle adjustment.”
MethodScene Adaptive Object Tracking Combining Local Feature and Color Feature
Miao, Q., & Cheng, G. (2016) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/3007669.3007675
“Miao et al. [6,7] employed the scale and rotation information of SURF features [8,9] to guide the on-line classifier learning process.”
BackgroundVideo object search and discovery
Meng, J. (2016) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/69414
“Alternatively, an object or a sub-image can be represented based on local features [8, 9], which are popular for matching object instances [21–23].”
BackgroundDistance learning between image and class for object recognition
Wang, Z. (2013) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/54819
Animal call segregation using self organizing map with speeded up robust features
Pelzers, K., & Mladenov, V. (2016) · Symposium on Neural Networks and Applications (NEUREL) · doi:10.1109/neurel.2016.7800139
“Rotation in spectrogram data leads to entirely different sounds, thus U-SURF is used.”
BackgroundMethodInfluentialInvariant human pose feature extraction for movement recognition and pose estimation
Qian, G., & Peng, B. (2011)
Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis
Long, X., Qiang, C. H. E. N., Xiaoya, G. A. O., et al. (2014) · DOAJ (DOAJ: Directory of Open Access Journals)
Using Multi-Target Tracking and Identification TLD Algorithm for Intelligent Mobile Robot
Guo, J.-H., Hsia, K.-H., & Su, K.-L. (2016) · Journal of Robotics Networking and Artificial Life · doi:10.2991/jrnal.2016.3.3.2
Dimensional Object Recognition using SVM -KNN augmented by local and global feature
Chandrasekar, C. (2012)
A Survey on Medical Image Analysis using Image Descriptors Methods
Patil, J., Pradeepini, G., & Mane, S. (2016) · The Internet of Things
Planar PØP: Feature-less pose estimation with applications in UAV localization
Amor-Martinez, A., Santamaria‐Navarro, À., Herrero, F., et al. (2016) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2016.7784271
Dense Matching Based on Subspace Learning for Non-Rigid Object
Zhang, Q. (2016) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/3007669.3007684
Keyframe-based online object learning and detection
Lee, S., Lim, J., & Suh, I. H. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759775
Intuitive Appliance Identification using Image Matching in Smart Buildings
Chen, K., Kolb, J., Fürst, J., Hong, D., Culler, D., & Katz, R. H. (2015) · UC Berkeley
A System for Camera-Based Retrieval of Heterogeneous-Content Complex Linguistic Map
Dang, B. Q., Viet, P. L., Luqman, M. M., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-52159-6_7
Unsupervised face analysis from multi-view
Seyed, M. H. A. (2014) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/59221
Recognition and Location Tracking System of Moving Object in the Virtual Space
Ahmed, R. W., Ko, K., & Kim, S. (2016) · Advanced science and technology letters · doi:10.14257/astl.2016.141.36
Developing Two-Armed Robot Assistant: Intelligent Tutoring Skills Based System
Krechetov, I. V. (2016) · Indian Journal of Science and Technology · doi:10.17485/ijst/2016/v9i47/108700
Schott, G. R., & Marczak, R. (2016) · Future Technologies Conference · doi:10.1109/ftc.2016.7821657
“…and measured automatically with the aid of algorithms that were initially developed to detect the presence of specific objects within moving-image (Bay et al., 2008), automatically segment moving-image into sub-scenes (Huang & Liao, 2001; Saraceno & Leonardi, 1997) or extract symbolic information…”
MethodPixel-based pipeline hardware architecture for high-performance Haar-like feature extraction
Fujita, Y., An, F., Luo, A., et al. (2016) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas.2016.7804044
“In order to improve the processing speed of the feature extraction, the Speeded Up Robust Features (SURF) method [2] has contributed to reducing processing time.”
MethodHigh performance system-on-chip implementation for object recognition of mobile robot
Jang, S., Lee, S.-S., Hwang, Y., et al. (2016) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia.2016.7804829
“[2-4] However, SURF as well as SIFT requires a huge memories and bandwidth.”
MethodInterest points based collaborative tracking
Zeng, X., Xu, L., Ma, L., & Zhao, R. (2016) · Visual Communications and Image Processing · doi:10.1109/vcip.2016.7805528
“In [17], Kloihofer and Kampel detected interest points and calculated the SURF [18] descriptors of interest points for object tracking.”
BackgroundLarge-Scale Generic Image Recognition and Image Representation
Harada, T. (2011) · IEICE Technical Report; IEICE Tech. Rep.
An offline autonomous vehicular actuator control system
Ramotsoela, T. D., & le Roux, J. L. (2016) · International Conference on Industrial Informatics · doi:10.1109/indin.2016.7819343
An Elaborated Survey on Mobile based Augmented Reality System
Gaffar, S. A., & Nyamathulla, S. (2014)
Improved BOF Method for Person Re-Identification
Zhang, L., & Li, K. (2016) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2016.0116
“(1) SURF feature extraction SURF algorithm [17] is used for feature extraction instead of SIFT, which can reduce the calculation complexity.”
MethodCollaborative localization for autonomous robots in structured environments
Guerra, E., Munguía, R., Bolea, Y., & Grau, A. (2016) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin.2016.7819162
Efficient Feature Matching by Progressive Candidate SearchPreprint
Lee, S., Lim, J., & Suh, I. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.05676
“In this ex-periment, SIFT [17], SURF [2], and KAZE [1] features in OpenCV 3.0 are tested.”
BackgroundMethodInfluentialNon-Iterative SLAM: A Fast Dense Method for Inertial-Visual SLAM.Preprint
Wang, C., Yuan, J., & Xie, L. (2017) · arXiv (Cornell University)
Robot coordination to create collaborative panoramic images
Arauz, T., Maestre, J. M., Romero, A., et al. (2017) · International Conference on Control and Automation · doi:10.1109/icca.2017.8003171
“Many distinctive features can be selected to this end, but two of them are the most wellknown in this field: scale-invariant feature transform (SIFT Features) [2] and speeded up robust features (SURF) [3].”
BackgroundA modified descriptor for blob detection in nonlinear scale space
Zhao, L., Ding, Y., & Xu, H. M. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2265512
“} i j i i j j L I A L L i M j n (3) Where (L ) i A matrix is encoded from the conductivity function c.”
A Hybrid Approach to Wide-Baseline Image Matching.Preprint
Mitra, R., Zhang, J., Chandran, S., et al. (2017) · arXiv (Cornell University)
Scale-adaptive Local Patches for Robust Visual Object Tracking
Sun, K., & Li, X. (2014) · DOAJ (DOAJ: Directory of Open Access Journals)
Photo-Quality Evaluation based on Computational Aesthetics: Review of Feature Extraction TechniquesPreprint
Spathis, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06259
“In literature [25], the Speeded Up Robust Features (SURF) framework [2] is used, which is based on Haar wavelets.”
MethodIntelligent electronic lock with user-defined graphical key
Yunjiang, H., Cheng, J. S., Feng, W., et al. (2016) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2016.7832091
A combined visual tracker based on global appearance and local features
Tianyang, Y., Jin, L., Li, Y., et al. (2016) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2016.7831892
“Bay et al. proposed SURF (Speeded Up Robust Features) [2], compared to the widely used and effective local feature SIFT (Scale-invariant feature transform) algorithm [11], with the comparable performance but about 3 times faster in calculation [12].”
Method徐, 飞. (2015) · Journal of Image and Signal Processing · doi:10.12677/jisp.2015.44013
Effective Registration for Multiple Users AR System
Chen, W., Chen, C., Wang, J., et al. (2016) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar-adjunct.2016.0092
“In the proposed system flow, the descriptor is built using the speeded up robust features (SURF) [6], the matching algorithm is the fast library for approximate nearest neighbors (FLANN) [7], and the transformation matrix is derived from RANSAC.”
MethodImproved local ternary pattern features with application to pedestrian detection
Song, J., Wang, W., Yao, T., et al. (2016) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2016.7832032
“To speed up the feature calculation, some new features such as SURF [4] and Daisy [5] were proposed, which work efficiently in appearance description objects.”
Method3D SLAM for Scenes with Repetitive Texture Inside Tokamak Chamber
Liu, W., Zheng, Z., Odbal, O., et al. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-48036-7_78
Automatic and adaptable registration of live RGBD video streams sharing partially overlapping views
Rafighi, A. (2015) · Memorial University Research Repository (Memorial University)
Vision-based traversability estimation in field environments
Ross, P. (2016) · Queensland University of Technology · doi:10.5204/thesis.eprints.96033 · Cited by 2
1P1-I03 RGB-D Camera based 3D Environmental Mapping for Mobile vehicle(Localization and Mapping (2))
Okada, N., Suzuki, S., Ishii, T. M., et al. (2013) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2013._1p1-i03_1
Review on Corner Detection Algorithms
Zhang, X.-F., Li, Y., & Song, J.-F. (2017) · doi:10.2991/icwcsn-16.2017.79
“SURF algorithm [4] is the improvement of SIFT algorithm, which uses the box filter to replace the two order Gauss filter and uses the haar wavelet instead of the histogram.”
MethodCompact and Distinctive Visual Vocabularies for Efficient Multimedia Data Indexing
Kastrinakis, D., Papadopoulos, S., & Vakali, A. I. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40683-6_8
“In recent years, the performance of CBIR systems has substantially improved thanks to the development of rich image representations based on local descriptors (e.g. SIFT [8], SURF [2], etc.) and the use of full-text search technologies that formulate query-by-example as a text retrieval problem [11, 15].”
BackgroundInfluentialBockholt, U. (2016) · Springer eBooks · doi:10.1007/978-3-662-49317-5_5
A stereo camera-equipped quadrotor platform for vision based nonlinear control
Dai, F., Wang, K., & Lin, P. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866600
“The SURF feature points [12] in the left and right images of the stereo camera, are matched and respectively tracked, for the position estimation.”
MethodBroadband World Modeling and Scene Reconstruction
Goldman, B. J. (2013) · VTechWorks (Virginia Tech)
Biologically-inspired place recognition with neural networks
Chen, Z. (2016) · Queensland University of Technology · doi:10.5204/thesis.eprints.98550
Efficient Local Image Descriptors
Lukianitsa, A. A. (2017) · Computational Mathematics and Modeling · doi:10.1007/s10598-017-9360-7
ReduxGO: Context-Aware Mobile Recommender Application for Reducing Stop-and-Go Scenario
Haron, N. S. (2016) · International Conference on Intelligent Systems, Modelling and Simulation · doi:10.1109/isms.2016.83
Implementing a Stereo Image Processing for Medical 3D Microscopes with Wireless HMD
Kim, C., Yoon, J., Lee, Y.-J., et al. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-4154-9_16
Informativity estimation technique of template geophysical field data
Mukhina, M. P., & Yeremeieva, T. A. (2016) · Electronics and Control Systems · doi:10.18372/1990-5548.48.11201
Adaptive Differential Evolution and its Application to Machine Vision
Dawar, D. (2016) · NDSU Repository (North Dakota State University)
Li, D., Shi, R., Zhao, X., et al. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-3530-2_32
Mukhina, M. P., Prymak, A. P., & Babeniuk, A. N. (2016) · Electronics and Control Systems · doi:10.18372/1990-5548.47.10292
Expert estimations for informativeness and recognition of selected terrain
Mukhina, M. P., Mladentseva, K. S., & Barkulova, I. V. (2016) · Electronics and Control Systems · doi:10.18372/1990-5548.50.11383
System inteligentny rozpoznawania znaków drogowych
Matuszewski, J. (2016) · PRZEGLĄD ELEKTROTECHNICZNY · doi:10.15199/48.2016.01.10
“Wymiar deskryptora ma bezpośredni wpływ na szybkość metody i jej dokładność [1].”
BackgroundInfluentialЕкспертне оцінювання інформативності та розпізнавання обраного рельєфу місцевості
Mukhina, M. P., Mladentseva, K. S., & Barkulova, I. V. (2016) · Electronics and Control Systems · doi:10.18372/1990-5548.50.11382
An Image Wherever You Look! Making Vision Just Another Sensor for AI/Robotics Projects
Zhang, A., Lee, J., Jones, C., et al. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10551
“SURF, Speeded-up Robust Features (Bay et al. 2008) 4.”
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.