Speeded-Up Robust Features (SURF)
Computer Vision and Image UnderstandingPublished 7 January 2008
Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool
Citations13,237
SJR quartileQ1
SJR score0.86
SNIP1.50
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Abstract
Кваліфікаційна робота присвячена розробці програмного засобу для визначення та розпізнавання дорожніх знаків на основі згорткової нейромережі.. \nВиконано аналітичний огляд існуючих систем реалізації та готових алгоритмів детектування та розпізнавання дорожніх знаків на зображення реальних сцен. Представлені їх основні переваги та недоліки. Здійснено огляд технічних параметрів готових систем розпізнавання знаків. Для вирішення поставленого завдання в роботі найкраще використовувати разом два алгоритми – пошуку за формою за допомогою фільтра Габора та метод максимально стабільних екстремальних областей. Також описано процес розпізнавання дорожніх знаків за допомогою штучних та згорткових нейромереж. \nНаведено особливості використання навчальних вибірок GTSRB та GTSDB для вирішення завдання. Запропонована програмна реалізація (на основі бібліотек Kerаs і OpenCV) з достатньо високим відсотком ідентифікації дорожніх знаків.
Keywords
Computer ScienceEngineering
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Rapid object detection using a boosted cascade of simple features
18,097 Citations2005Paul Viola, Michael Jones
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Object recognition from local scale-invariant features
16,195 Citations1999David Lowe
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Lecture notes in computer scienceSURF: Speeded Up Robust Features
14,471 Citations2006Herbert Bay, Tinne Tuytelaars +1 more
A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
A Combined Corner and Edge Detector
12,478 Citations1988Chris Harris, Matthew J. Stephens
The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA performance evaluation of local descriptors
6,692 Citations2005Krystian Mikolajczyk, C. Schmid
Visual categorization with bags of keypoints
4,147 Citations2004G. Csurka
Image and Vision ComputingRobust wide-baseline stereo from maximally stable extremal regions
3,664 Citations2004Jiřı́ Matas, Ondřej Chum +2 more
The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.
Scalable Recognition with a Vocabulary Tree
3,612 Citations2006D. Nistér, Henrik Stewénius
A recognition scheme that scales efficiently to a large number of objects and allows a larger and more discriminatory vocabulary to be used efficiently is presented, which it is shown experimentally leads to a dramatic improvement in retrieval quality.
International Journal of Computer VisionScale & Affine Invariant Interest Point Detectors
3,395 Citations2004Krystian Mikolajczyk, Cordelia Schmid
A comparative evaluation of different detectors is presented and it is shown that the proposed approach for detecting interest points invariant to scale and affine transformations provides better results than existing methods.
PCA-SIFT: a more distinctive representation for local image descriptors
3,210 Citations2004Ke Yan, Rahul Sukthankar
This paper examines (and improves upon) the local image descriptor used by SIFT, and demonstrates that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe design and use of steerable filters
2,934 Citations1991William T. Freeman, Edward H. Adelson
The authors present an efficient architecture to synthesize filters of arbitrary orientations from linear combinations of basis filters, allowing one to adaptively steer a filter to any orientation, and to determine analytically the filter output as a function of orientation.
International Journal of Computer VisionA Comparison of Affine Region Detectors
2,921 Citations2005Krystian Mikolajczyk, Tinne Tuytelaars +6 more
A snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions to establish a reference test set of images and performance software so that future detectors can be evaluated in the same framework.
Locality-sensitive hashing scheme based on p-stable distributions
2,917 Citations2004Mayur Datar, Nicole Immorlica +2 more
A novel Locality-Sensitive Hashing scheme for the Approximate Nearest Neighbor Problem under lp norm, based on p-stable distributions that improves the running time of the earlier algorithm and yields the first known provably efficient approximate NN algorithm for the case p<1.
International Journal of Computer VisionFeature Detection with Automatic Scale Selection
2,487 Citations1998Tony Lindeberg
It is shown how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation and how it can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.
Biological CyberneticsThe structure of images
2,406 Citations1984Jan J. Koenderink
It is shown that any image can be embedded in a one-parameter family of derived images (with resolution as the parameter) in essentially only one unique way if the constraint that no spurious detail should be generated when the resolution is diminished, is applied.
Object class recognition by unsupervised scale-invariant learning
2,035 Citations2003Rob Fergus, Pietro Perona +1 more
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Efficient Non-Maximum Suppression
1,978 Citations2006Alexander Neubeck, Luc Van Gool
This work scrutinize a low level computer vision task - non-maximum suppression (NMS) - and derive several algorithms ranging from easy-to-implement to highly-efficient.
Robust Wide Baseline Stereo from Maximally Stable Extremal Regions
1,345 Citations2002Jiřı́ Matas, Ondřej Chum +2 more
Lecture notes in computer scienceAn Affine Invariant Interest Point Detector
1,300 Citations2002Krystian Mikolajczyk, Cordelia Schmid
A novel approach for detecting affine invariant interest points that can deal with significant affine transformations including large scale changes and shows an excellent performance in the presence of large perspective transformations including significant scale changes.
International Journal of Computer VisionSaliency, Scale and Image Description
1,201 Citations2001Timor Kadir, Michael Brady
A multiscale algorithm for the selection of salient regions of an image is introduced and its application to matching type problems such as tracking, object recognition and image retrieval is demonstrated.
Indexing based on scale invariant interest points
1,090 Citations2002Krystian Mikolajczyk, C. Schmid
The method is based on two recent results on scale space: interest points can be adapted to scale and give repeatable results (geometrically stable) and local extrema over scale of normalized derivatives indicate the presence of characteristic local structures.
A performance evaluation of local descriptors
952 Citations2003Krystian Mikolajczyk, C. Schmid
It is observed that the ranking of the descriptors does not depend on the point detector and that SIFT descriptors perform best and steerable filters can be considered a good choice given the low dimensionality.
Reliable feature matching across widely separated views
624 Citations2002Adam Baumberg
A robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints that is optimised for a structure-from-motion application where it wishes to ignore unreliable matches at the expense of reducing the number of feature matches.
IEEE Transactions on Pattern Analysis and Machine IntelligenceScale-space for discrete signals
614 Citations1990Tony Lindeberg
The proper way to apply the scale-space theory to discrete signals and discrete images is by discretization of the diffusion equation, not the convolution integral.
Invariant Features from Interest Point Groups
607 Citations2002Matthew Brown, David Lowe
This work introduces a family of features which use groups of interest points to form geometrically invariant descriptors of image regions to ensure robust matching between images in which there are large changes in viewpoint, scale and illumi- nation.
Lecture notes in computer scienceMulti-view Matching for Unordered Image Sets, or “How Do I Organize My Holiday Snaps?”
525 Citations2002F. Schaffalitzky, Andrew Zisserman
This paper invests how a combination of image invariants, covariants, and multiple view relations can be used in concord to enable efficient multiple view matching and produces a matching algorithm which is linear in the number of views.
Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
448 Citations2000Tinne Tuytelaars, Luc Van Gool
This work presents an alternative method for extracting invariant regions that does not depend on the presence of edges or corners in the image but is purely intensity-based, and demonstrates the use of such regions for another application, which is wide baseline stereo matching.
Five Balltree Construction Algorithms
415 Citations2009Stephen M. Omohundro
This report compares 5 different algorithms for constructing ball trees from data and finds that the bottom up approach usually produces the best trees but has the longest construction time.
Computer Vision and Image UnderstandingMoment invariants for recognition under changing viewpoint and illumination
237 Citations2003Florica Mindru, Tinne Tuytelaars +2 more
Although the generalised color moment invariants are extracted from planar surface patches, it is argued that invariant neighbourhoods offer a concept through which they can also be used to deal with 3D objects and scenes.
Machine Vision and ApplicationsWeb-based 3D Reconstruction Service
222 Citations2006Maarten Vergauwen, Luc Van Gool
A web-based 3D reconstruction service, developed to relieve those needs of the cultural heritage field, consisting of a pipeline that starts with the user uploading images of an object or scene(s) he wants to reconstruct in 3D.
Lecture notes in computer scienceFast Approximated SIFT
209 Citations2006Michael Grabner, Helmut Gräbner +1 more
A considerably faster approximation of the well known SIFT method by using efficient data structures for both, the detector and the descriptor and an analysis of the computational costs.
Scale-invariant shape features for recognition of object categories
190 Citations2004Frédéric Jurie, C. Schmid
A new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image are introduced, which are invariant to scale changes and rotations, and robust against clutter, occlusions and spurious edge detections.
Journal of Mathematical Imaging and VisionGeneral intensity transformations and differential invariants
141 Citations1994Luc Florack, Bart M. ter Haar Romeny +2 more
A generating equation is proposed for a complete set of differential gray-value invariants up to any order that describe the image's geometrical structure independent of how its gray-values are mapped.
Boxlets: A Fast Convolution Algorithm for Signal Processing and Neural Networks
130 Citations1998Patrice Simard, Léon Bottou +2 more
The approach consists of approximating regions of the signal with low degree polynomials, and then differentiating the resulting signals in order to obtain impulse functions (or derivatives of impulse functions) and yields substantial speed up in feature extraction.
Interactive museum guide : fast and robust recognition of museum objects
106 Citations2006Hoang Van Bay, Beat Fasel +1 more
It is demonstrated that both the object recognition performance as well as the speed of the SURF algorithm surpasses the results obtained with SIFT, its main contender.
Multi-scale phase-based local features
105 Citations2003Gustavo Carneiro, Allan D. Jepson
The results show that the phase-based local features lead to better performance than the other two approaches when dealing with common illumination changes, 2D rotation, and sub-pixel translation.
Lecture notes in computer scienceReal-Time Scale Selection in Hybrid Multi-scale Representations
86 Citations2003Tony Lindeberg, Lars Bretzner
A framework for how the computation of such scale descriptors can be performed in real time on a standard computer is presented, expressed within a novel type of multi-scale representation, referred to as hybrid multi- scale representation, which aims at integrating and providing variable trade-offs between the relative advantages of pyramids and scale-space representation.
Lecture notes in computer scienceRetina Mosaicing Using Local Features
72 Citations2006Philippe C. Cattin, Herbert Bay +2 more
This paper presents a core image processing element of a fully automatic laser photocoagulation system, namely a novel approach for retina mosaicing, which relies on recent developments in region detection and feature description to automatically fuse retina images.
55th International Astronautical Congress of the International Astronautical Federation, the International Academy of Astronautics, and the International Institute of Space LawVision Based Modeling and Localization for Planetary Exploration Rovers
72 Citations2004Stephen Se, Ho-Kong Ng +2 more
Lecture notes in computer scienceRedundant Bit Vectors for Quickly Searching High-Dimensional Regions
23 Citations2005Jonathan Goldstein, John C. Plat +1 more
Redundant Bit Vectors is proposed: a novel method for quickly solving applications such as audio fingerprinting that approximate the high-dimensional regions/distributions as tightened hyperrectangles as well as partition the query space to store each item redundantly in an index.