A performance evaluation of local descriptors (2005)

by K Mikolajczyk, C Schmid
Venue:IEEE Trans. Pattern Anal. Mach. Intell
Add To MetaCart
Results 1 - 10 of 1,740

Histograms of Oriented Gradients for Human Detection

by Navneet Dalal, Bill Triggs - In CVPR , 2005
"... We study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of Histograms of Oriented Gradient (HOG) descriptors significantly out ..."
Abstract - Cited by 3678 (9 self) - Add to MetaCart
We study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of Histograms of Oriented Gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds. 1
(Show Context)

Video google: A text retrieval approach to object matching in videos

by Josef Sivic, Andrew Zisserman - In ICCV , 2003
"... We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, ill ..."
Abstract - Cited by 1621 (42 self) - Add to MetaCart
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion. The temporal continuity of the video within a shot is used to track the regions in order to reject unstable regions and reduce the effects of noise in the descriptors. The analogy with text retrieval is in the implementation where matches on descriptors are pre-computed (using vector quantization), and inverted file systems and document rankings are used. The result is that retrieval is immediate, returning a ranked list of key frames/shots in the manner of Google. The method is illustrated for matching on two full length feature films. 1.
(Show Context)

An affine invariant interest point detector

by Krystian Mikolajczyk, Cordelia Schmid - In Proceedings of the 7th European Conference on Computer Vision , 2002
"... Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of ..."
Abstract - Cited by 1455 (55 self) - Add to MetaCart
Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighbourhood of an interest point. Our approach allows to solve for these problems simultaneously. It is based on three key ideas: 1) The second moment matrix computed in a point can be used to normalize a region in an affine invariant way (skew and stretch). 2) The scale of the local structure is indicated by local extrema of normalized derivatives over scale. 3) An affine-adapted Harris detector determines the location of interest points. A multi-scale version of this detector is used for initialization. An iterative algorithm then modifies location, scale and neighbourhood of each point and converges to affine invariant points. For matching and recognition, the image is characterized by a set of affine invariant points; the affine transformation associated with each point allows the computation of an affine invariant descriptor which is also invariant to affine illumination changes. A quantitative comparison of our detector with existing ones shows a significant improvement in the presence of large affine deformations. Experimental results for wide baseline matching show an excellent performance in the presence of large perspective transformations including significant scale changes. Results for recognition are very good for a database with more than 5000 images.

Scalable Recognition with a Vocabulary Tree

by David Nistér, Henrik Stewénius - IN CVPR , 2006
"... A recognition scheme that scales efficiently to a large number of objects is presented. The efficiency and quality is exhibited in a live demonstration that recognizes CD-covers from a database of 40000 images of popular music CD's. The scheme ..."
Abstract - Cited by 1043 (0 self) - Add to MetaCart
A recognition scheme that scales efficiently to a large number of objects is presented. The efficiency and quality is exhibited in a live demonstration that recognizes CD-covers from a database of 40000 images of popular music CD's. The scheme

Visual categorization with bags of keypoints

by Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Willamowski, Cédric Bray - In Workshop on Statistical Learning in Computer Vision, ECCV , 2004
"... Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of im ..."
Abstract - Cited by 984 (14 self) - Add to MetaCart
Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches. We propose and compare two alternative implementations using different classifiers: Naïve Bayes and SVM. The main advantages of the method are that it is simple, computationally efficient and intrinsically invariant. We present results for simultaneously classifying seven semantic visual categories. These results clearly demonstrate that the method is robust to background clutter and produces good categorization accuracy even without exploiting geometric information. 1.
(Show Context)

SURF: Speeded Up Robust Features

by Herbert Bay, Tinne Tuytelaars, Luc Van Gool - ECCV
"... Abstract. In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Ro-bust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be comp ..."
Abstract - Cited by 842 (13 self) - Add to MetaCart
Abstract. In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Ro-bust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descrip-tors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF’s strong performance. 1
(Show Context)

Behavior recognition via sparse spatio-temporal features

by Piotr Dollár, Vincent Rabaud, Garrison Cottrell, Serge Belongie - In VS-PETS , 2005
"... A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatio ..."
Abstract - Cited by 705 (4 self) - Add to MetaCart
A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatio-temporal case. For this purpose, we show that the direct 3D counterparts to commonly used 2D interest point detectors are inadequate, and we propose an alternative. Anchoring off of these interest points, we devise a recognition algorithm based on spatio-temporally windowed data. We present recognition results on a variety of datasets including both human and rodent behavior. 1.
(Show Context)

Object Tracking: A Survey

by Alper Yilmaz, Omar Javed, Mubarak Shah , 2006
"... The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends. Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns o ..."
Abstract - Cited by 690 (8 self) - Add to MetaCart
The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends. Object tracking, in general, is a challenging problem. Difficulties in tracking objects can arise due to abrupt object motion, changing appearance patterns of both the object and the scene, nonrigid object structures, object-to-object and object-to-scene occlusions, and camera motion. Tracking is usually performed in the context of higher-level applications that require the location and/or shape of the object in every frame. Typically, assumptions are made to constrain the tracking problem in the context of a particular application. In this survey, we categorize the tracking methods on the basis of the object and motion representations used, provide detailed descriptions of representative methods in each category, and examine their pros and cons. Moreover, we discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.

Local features and kernels for classification of texture and object categories: a comprehensive study

by J. Zhang, S. Lazebnik, C. Schmid - International Journal of Computer Vision , 2007
"... Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations an ..."
Abstract - Cited by 644 (35 self) - Add to MetaCart
Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ 2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on four texture and five object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate the influence of background correlations on recognition performance via extensive tests on the PASCAL database, for which ground-truth object localization information is available. Our experiments demonstrate that image representations based on distributions of local features are surprisingly effective for classification of texture and object images under challenging real-world conditions, including significant intra-class variations and substantial background clutter.
(Show Context)

The 2005 pascal visual object classes challenge

by Mark Everingham, Andrew Zisserman, Christopher K. I. Williams, Luc Van Gool, Moray Allan, Christopher M. Bishop, Olivier Chapelle, Navneet Dalal, Thomas Deselaers, Gyuri Dorkó, Stefan Duffner, Jan Eichhorn, Jason D. R. Farquhar, Mario Fritz, Christophe Garcia, Tom Griffiths, Frederic Jurie, Daniel Keysers, Markus Koskela, Jorma Laaksonen, Diane Larlus, Bastian Leibe, Hongying Meng, Hermann Ney, Bernt Schiele, Cordelia Schmid, Edgar Seemann, John Shawe-taylor, Amos Storkey, Or Szedmak, Bill Triggs, Ilkay Ulusoy, Ville Viitaniemi, Jianguo Zhang , 2006
"... Abstract. The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and peop ..."
Abstract - Cited by 633 (24 self) - Add to MetaCart
Abstract. The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and people. Twelve teams entered the challenge. In this chapter we provide details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved. 1
(Show Context)