Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search
Lecture notes in computer sciencePublished 1 January 2004
Bastian Leibe, Bernt Schiele
Citations146
SJR quartileQ2
SJR score0.35
SNIP0.55
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
This paper presents an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search, and presents an experimental comparison of the influence of different interest point operators and quantitatively shows the method's robustness to large scale changes.
Abstract
The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize objects at multiple scales. In this paper, we present an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search. The approach builds on the method from [12], which has been demonstrated to achieve excellent results for the single-scale case, and extends it to multiple scales. We present an experimental comparison of the influence of different interest point operators and quantitatively show the method's robustness to large scale changes.
Keywords
Computer ScienceEngineering
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.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMean shift: a robust approach toward feature space analysis
11,282 Citations2002Dorin Comaniciu, Peter Meer
It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
Pattern RecognitionGeneralizing the Hough transform to detect arbitrary shapes
4,348 Citations1981D.H. Ballard
It is shown how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space, which makes the generalized Houghtransform a kind of universal transform which can beused to find arbitrarily complex shapes.
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.
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).
International Journal of Computer VisionA Trainable System for Object Detection
1,282 Citations2000Constantine Papageorgiou, Tomaso Poggio
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 statistical method for 3D object detection applied to faces and cars
1,061 Citations2002Henry Schneiderman, Takeo Kanade
Using this method, this work has developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithms thatCan reliably detect passenger cars over a wide range of viewpoints.
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.
Combined Object Categorization and Segmentation With an Implicit Shape Model
816 Citations2004Bastian Leibe, Aleš Leonardis +1 more
Results for articulated objects, which show that the proposed method can categorize and segment unfamiliar objects in differ- ent articulations and with widely varying texture patterns, even under significant partial occlusion.
Mean-shift blob tracking through scale space
798 Citations2003Robert T. Collins
Lindeberg's theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking shows that a difference of Gaussian (DOG) mean- shift kernel enables efficient tracking of blobs through scale space.
Lecture notes in computer scienceUnsupervised Learning of Models for Recognition
599 Citations2000Markus Weber, Max Welling +1 more
A method to learn object class models from unlabeled and unsegmented cluttered cluttered scenes for the purpose of visual object recognition that achieves very good classification results on human faces and rear views of cars.
Lecture notes in computer scienceLearning a Sparse Representation for Object Detection
513 Citations2002Shivani Agarwal, Dan Roth
An approach for learning to detect objects in still gray images, that is based on a sparse, part-based representation of objects, that achieves high detection accuracy on a difficult test set of real-world images, and is highly robust to partial occlusion and background variation.
The variable bandwidth mean shift and data-driven scale selection
422 Citations2002Dorin Comaniciu, Makarand Velankar +1 more
The sample point estimator is used to define the Variable Bandwidth Mean Shift, prove its convergence, and show its superiority over the fixed bandwidth procedure.
Lecture notes in computer scienceClass-Specific, Top-Down Segmentation
370 Citations2002Eran Borenstein, Shimon Ullman
A novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images), which leads to markedly improved segmentation results and can deal with significant variation in shape and varying backgrounds.
Selection of scale-invariant parts for object class recognition
287 Citations2003Dorko, Schmid
The evaluation shows that local invariant descriptors are an appropriate representation for object classes such as cars, and it underlines the importance of feature selection.
Fusion of global and local information for object detection
31 Citations2003Aman Garg, Sugandha Agarwal +1 more
The strengths of the two detection algorithms are combined to form a more powerful detector that gives distinctly superior performance than each of the individual detectors, achieving a high detection accuracy on this difficult test set.