Sequential Karhunen-Loeve basis extraction and its application to images
TL;DR: A new, sequential algorithm is presented, which is faster in typical applications and is especially advantageous for image sequences: the KL basis calculation is done with much lower delay and allows for dynamic updating of image databases.
Abstract: The Karhunen-Loeve (KL) transform is an optimal method for approximating a set of vectors or images, which was used in image processing and computer vision for several tasks such as face and object recognition. Its computational demands and its batch calculation nature have limited its application. Here we present a new, sequential algorithm for calculating the KL basis, which is faster in typical applications and is especially advantageous for image sequences: the KL basis calculation is done with much lower delay and allows for dynamic updating of image databases. Systematic tests of the implemented algorithm show that these advantages are indeed obtained with the same accuracy available from batch KL algorithms.
Citations
More filters
TL;DR: A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.
Abstract: Visual tracking, in essence, deals with non-stationary image streams that change over time. While most existing algorithms are able to track objects well in controlled environments, they usually fail in the presence of significant variation of the object's appearance or surrounding illumination. One reason for such failures is that many algorithms employ fixed appearance models of the target. Such models are trained using only appearance data available before tracking begins, which in practice limits the range of appearances that are modeled, and ignores the large volume of information (such as shape changes or specific lighting conditions) that becomes available during tracking. In this paper, we present a tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target. The model update, based on incremental algorithms for principal component analysis, includes two important features: a method for correctly updating the sample mean, and a forgetting factor to ensure less modeling power is expended fitting older observations. Both of these features contribute measurably to improving overall tracking performance. Numerous experiments demonstrate the effectiveness of the proposed tracking algorithm in indoor and outdoor environments where the target objects undergo large changes in pose, scale, and illumination.
3,151 citations
Cites methods from "Sequential Karhunen-Loeve basis ext..."
...More details and complexity analysis of the SKL algorithm are described in [22]....
[...]
...Here we extend one of these efficient update procedures—the Sequential Karhunen-Loeve (SKL) algorithm of Levy and Lindenbaum [22]—presenting a new incremental PCA algorithm that correctly updates the eigenbasis as well as the mean, given one or more additional training data....
[...]
...One way to moderate the balance between old and new observations is to incorporate a forgetting factor in the incremental eigenbasis update, as suggested by [22]....
[...]
...Numerous, more-sophisticated algorithms have been developed to efficiently update an eigenbasis as more data arrive [12] [14] [22] [7]....
[...]
01 Jan 2004
TL;DR: This work presents an analytic solution to the problem of estimating multiple 2-D and 3-D motion models from two-view correspondences or optical flow and proposes a novel motion segmentation algorithm that outperforms existing algebraic methods in terms of efficiency and robustness.
Abstract: We present an analytic solution to the problem of estimating multiple 2-D and 3-D motion models from two-view correspondences or optical flow. The key to our approach is to view the estimation of multiple motion models as the estimation of a single multibody motion model. This is possible thanks to two important algebraic facts. First, we show that all the image measurements, regardless of their associated motion model, can be fit with a real or complex polynomial. Second, we show that the parameters of the motion model associated with an image measurement can be obtained from the derivatives of the polynomial at the measurement. This leads to a novel motion segmentation algorithm that applies to most of the two-view motion models adopted in computer vision. Our experiments show that the proposed algorithm outperforms existing algebraic methods in terms of efficiency and robustness, and provides a good initialization for iterative techniques, such as EM, which is strongly dependent on correct initialization.
909 citations
Cites background or methods from "Sequential Karhunen-Loeve basis ext..."
...In particular, we use a cascaded Adaboost algorithm [18] to learn models of the hockey players....
[...]
...Figure 5 shows a comparative study among the space carving method [15], the level set method [18] and our propagation approach....
[...]
...Global minimization methods that can deal with complex cost functions are necessary [18]....
[...]
...We adopt the cascaded Adaboost algorithm of Viola and Jones [18], originally developed for detecting faces....
[...]
...We do not follow this path as it very often results in an over-smoothed surface [18] due to high order derivatives involved in the dynamic surface evolution....
[...]
TL;DR: A detailed review of the existing 2D appearance models for visual object tracking can be found in this article, where the authors decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling.
Abstract: Visual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties in handling complex object appearance changes caused by factors such as illumination variation, partial occlusion, shape deformation, and camera motion. Therefore, effective modeling of the 2D appearance of tracked objects is a key issue for the success of a visual tracker. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we contribute this survey, which provides a detailed review of the existing 2D appearance models. In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking. In this survey, we first decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling. Then, different 2D appearance models are categorized and discussed with respect to their composition modules. Finally, we address several issues of interest as well as the remaining challenges for future research on this topic. The contributions of this survey are fourfold. First, we review the literature of visual representations according to their feature-construction mechanisms (i.e., local and global). Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative. Third, each type of visual representations or statistical modeling techniques is analyzed and discussed from a theoretical or practical viewpoint. Fourth, the existing benchmark resources (e.g., source codes and video datasets) are examined in this survey.
653 citations
Posted Content•
TL;DR: This survey provides a detailed review of the existing 2D appearance models for visual object tracking and takes a module-based architecture that enables readers to easily grasp the key points ofVisual object tracking.
Abstract: Visual object tracking is a significant computer vision task which can be applied to many domains such as visual surveillance, human computer interaction, and video compression. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we contribute this survey, which provides a detailed review of the existing 2D appearance models. In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking. In this survey, we first decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling. Then, different 2D appearance models are categorized and discussed with respect to their composition modules. Finally, we address several issues of interest as well as the remaining challenges for future research on this topic. The contributions of this survey are four-fold. First, we review the literature of visual representations according to their feature-construction mechanisms (i.e., local and global). Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative. Third, each type of visual representations or statistical modeling techniques is analyzed and discussed from a theoretical or practical viewpoint. Fourth, the existing benchmark resources (e.g., source code and video datasets) are examined in this survey.
605 citations
28 May 2002
TL;DR: In computer vision, the incremental SVD is used to develop an efficient and unusually robust subspace-estimating flow-based tracker, and to handle occlusions/missing points in structure-from-motion factorizations.
Abstract: We introduce an incremental singular value decomposition (SVD) of incomplete data. The SVD is developed as data arrives, and can handle arbitrary missing/untrusted values, correlated uncertainty across rows or columns of the measurement matrix, and user priors. Since incomplete data does not uniquely specify an SVD, the procedure selects one having minimal rank. For a dense p × q matrix of low rank r, the incremental method has time complexity O(pqr) and space complexity O((p + q)r)--better than highly optimized batch algorithms such as MATLAB's svd(). In cases of missing data, it produces factorings of lower rank and residual than batch SVD algorithms applied to standard missing-data imputations. We show applications in computer vision and audio feature extraction. In computer vision, we use the incremental SVD to develop an efficient and unusually robust subspace-estimating flow-based tracker, and to handle occlusions/missing points in structure-from-motion factorizations.
564 citations
References
More filters
Book•
01 Jan 1972
TL;DR: This completely revised second edition presents an introduction to statistical pattern recognition, which is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field.
Abstract: This completely revised second edition presents an introduction to statistical pattern recognition Pattern recognition in general covers a wide range of problems: it is applied to engineering problems, such as character readers and wave form analysis as well as to brain modeling in biology and psychology Statistical decision and estimation, which are the main subjects of this book, are regarded as fundamental to the study of pattern recognition This book is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field Each chapter contains computer projects as well as exercises
10,526 citations
03 Jun 1991
TL;DR: An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject's head and then recognizes the person by comparing characteristics of the face to those of known individuals is described.
Abstract: An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject's head and then recognizes the person by comparing characteristics of the face to those of known individuals is described. This approach treats face recognition as a two-dimensional recognition problem, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. Face images are projected onto a feature space ('face space') that best encodes the variation among known face images. The face space is defined by the 'eigenfaces', which are the eigenvectors of the set of faces; they do not necessarily correspond to isolated features such as eyes, ears, and noses. The framework provides the ability to learn to recognize new faces in an unsupervised manner. >
5,489 citations
Book•
01 May 1981
TL;DR: This book will be most useful to applied mathematicians, communication engineers, signal processors, statisticians, and time series researchers, both applied and theoretical.
Abstract: This book will be most useful to applied mathematicians, communication engineers, signal processors, statisticians, and time series researchers, both applied and theoretical. Readers should have some background in complex function theory and matrix algebra and should have successfully completed the equivalent of an upper division course in statistics.
3,231 citations
Additional excerpts
...The KL transform has found many applications in traditional fields such as statistics [2] and communication [3]....
[...]
TL;DR: In this article, a method for the representation of (pictures of) faces is presented, which results in the characterization of a face, to within an error bound, by a relatively low-dimensional vector.
Abstract: A method is presented for the representation of (pictures of) faces. Within a specified framework the representation is ideal. This results in the characterization of a face, to within an error bound, by a relatively low-dimensional vector. The method is illustrated in detail by the use of an ensemble of pictures taken for this purpose.
2,089 citations