Mean shift: a robust approach toward feature space analysis
01 May 2002-IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE Computer Society)-Vol. 24, Iss: 5, pp 603-619
TL;DR: 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.
Abstract: A general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern recognition procedure: the mean shift. For discrete data, we prove 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. The relation of the mean shift procedure to the Nadaraya-Watson estimator from kernel regression and the robust M-estimators; of location is also established. Algorithms for two low-level vision tasks discontinuity-preserving smoothing and image segmentation - are described as applications. In these algorithms, the only user-set parameter is the resolution of the analysis, and either gray-level or color images are accepted as input. Extensive experimental results illustrate their excellent performance.
Citations
More filters
TL;DR: A new superpixel algorithm is introduced, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels and is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
Abstract: Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
7,849 citations
Cites background from "Mean shift: a robust approach towar..."
...Superpixels are created by minimizing a cost function defined over the graph....
[...]
07 Jul 2001
TL;DR: In this paper, the authors present a database containing ground truth segmentations produced by humans for images of a wide variety of natural scenes, and define an error measure which quantifies the consistency between segmentations of differing granularities.
Abstract: This paper presents a database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties.
6,505 citations
TL;DR: This paper introduces selective search which combines the strength of both an exhaustive search and segmentation, and shows that its selective search enables the use of the powerful Bag-of-Words model for recognition.
Abstract: This paper addresses the problem of generating possible object locations for use in object recognition. We introduce selective search which combines the strength of both an exhaustive search and segmentation. Like segmentation, we use the image structure to guide our sampling process. Like exhaustive search, we aim to capture all possible object locations. Instead of a single technique to generate possible object locations, we diversify our search and use a variety of complementary image partitionings to deal with as many image conditions as possible. Our selective search results in a small set of data-driven, class-independent, high quality locations, yielding 99 % recall and a Mean Average Best Overlap of 0.879 at 10,097 locations. The reduced number of locations compared to an exhaustive search enables the use of stronger machine learning techniques and stronger appearance models for object recognition. In this paper we show that our selective search enables the use of the powerful Bag-of-Words model for recognition. The selective search software is made publicly available (Software: http://disi.unitn.it/~uijlings/SelectiveSearch.html ).
5,843 citations
Cites background from "Mean shift: a robust approach towar..."
...Bottom-up grouping is a popular approach to segmentation [6, 13], hence we adapt it for selective search....
[...]
...Research on this topic has yielded tremendous progress over the past years [3, 6, 13, 26]....
[...]
TL;DR: The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends to discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
Abstract: 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.
5,318 citations
Cites background or methods from "Mean shift: a robust approach towar..."
...Mean-shift clustering is scalable to various other applications such as edge detection, image regularization [Comaniciu and Meer 2002], and tracking [Comaniciu et al. 2003]....
[...]
...Use of concentric circles implicitly encodes the spatial information which in regular histogram is only possible when the spatial (x, y) coordinates are included in the observation vector [Comaniciu and Meer 2002]....
[...]
...Use of concentric circles implicitly encodes the spatial information which in regular histogram is only possible when the spatial (x, y) coordinates are included in the observation vector [Comaniciu and Meer 2002]....
[...]
...Mean-shift clustering is scalable to various other applications such as edge detection, image regularization [Comaniciu and Meer 2002], and tracking [Comaniciu et al....
[...]
TL;DR: This paper investigates two fundamental problems in computer vision: contour detection and image segmentation and presents state-of-the-art algorithms for both of these tasks.
Abstract: This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.
5,068 citations
Cites background or methods from "Mean shift: a robust approach towar..."
..., fitting mixture models [7], [44], mode-finding [34], or graph partitioning [32], [45], [46], [47]....
[...]
...The Mean Shift algorithm [34] offers an alternative clustering framework....
[...]
...Paired with our gPb contour detector as input, our hierarchical segmentation algorithm gPb-owt-ucm [4] produces regions whose boundaries match ground truth better than those produced by other methods [7], [29], [30], [31], [32], [33], [34], [35]....
[...]
...To provide a basis of comparison for the OWT-UCM algorithm, we make use of the region merging (Felz-Hutt) [32], Mean Shift [34], Multiscale NCuts [33], and SWA [31], [52] segmentation methods reviewed in Section 2....
[...]
...To provide a basis of comparison for the OWT-UCM algorithm, we make use of the region merging (Felz-Hutt) [32], Mean Shift [34], Multiscale NCuts [33], and SWA [31], [52] segmentation methods reviewed in Section 2.2....
[...]
References
More filters
TL;DR: This book make understandable the cluster analysis is based notion of starsmodern treatment, which efficiently finds accurate clusters in data and discusses various types of study the user set explicitly but also proposes another.
Abstract: The Wiley-Interscience Paperback Series consists of selected books that have been made more accessible to consumers in an effort to increase In both the increasingly important and distribution we show how these methods. Our experiments demonstrate that together can deal with most applications technometrics. In an appropriate visualization technique is to these new. The well written and efficiently finds accurate clusters in data including. Of applied value for several preprocessing tasks discontinuity preserving smoothing feature clusters! However the model based notion of domain knowledge from real data repositories in data. Discusses various types of study the user set explicitly but also propose another. This book make understandable the cluster analysis is based notion of starsmodern treatment.
7,423 citations
"Mean shift: a robust approach towar..." refers background in this paper
...The objective function typically compares the inter- versus intra-cluster variability [30, 28] or e valuates the isolation and connectivity of the delineated clusters [43]....
[...]
TL;DR: The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.
Abstract: The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.
6,527 citations
Book•
01 Dec 1967
TL;DR: An encyclopedic survey of color science can be found in this article, which includes details of light sources, color filters, physical detectors of radiant energy, and the working concepts in color matching, discrimination, and adaptation.
Abstract: An encyclopedic work which collects into a ready-reference volume the concepts, methods, quantitative data and formulas on color science. Includes details of light sources, color filters, physical detectors of radiant energy, and the working concepts in color matching, discrimination, and adaptation. For the colorimetrist, research worker, physicist, physiologist and psychologist concerned with color problems in industry. Tables; diagrams; ten-page bibliography. First author is head, radiation optics section, National Research Council, Canada. Contents, abridged: Basic radiometric concepts and units. Optical filters. Physical detectors of radiant energy. Parts of the human eye: nomenclature; dimensions. Factors in the eye that control the internal stimulus. The Troland values of retinal illuminance. Light losses in the eye. Quantum fluctuations and visual stimuli. Conversion factors related to the eye. Trichromatic generalization. The CIE colorimetric system. Complementary colors. Object colors, object. color solid, optimal colors. Counting metameric object colors. Degree of metamerism. Propagation of spectrophotometric errors. The photometric principle. Preamble. Factors modifying matching. Chromatic adaptation. Lightness scales. Combined lightness and chromaticness scales. Discrimination data under special conditions. Color reversal at long wavelengths: Brindley isochromes. Abney and Bezold-Brucke effects. Dark adaptation and absolute thresholds. Uniform equivalent fields (equivalent background luminance). Visual response curves: their comparison with the spectral properties of pigments. References. Author index. Subject index. -- AATA
4,441 citations
Book•
01 Sep 19904,384 citations
TL;DR: In this paper, the primary goal of pattern recognition is supervised or unsupervised classification, and the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been used.
Abstract: The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical ap...
4,307 citations