A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models and problems with changes of topology. Using exemplars in place of a parameterized model poses several challenges, addressed here with what we call the "Metric Mixture" (M # ) approach. The M # model has several valuable properties. Principally, it provides alternatives to standard learning algorithms by allowing the use of metrics that are not embedded in a vector space. Secondly, it uses a noise model that is learned from training data. Lastly, it eliminates any need for an assumption of probabilistic pixelwise independence. Experiments demonstrate the effectiveness of the M # model in two domains: tracking walking people using chamfer distances on binary edge images and tracking mouth movements by means of a shuffle distance. 1

. Most segmentation algorithms are composed of several procedures: split and merge, small region elimination, boundary smoothing, : : : , each depending on several parameters. The introduction of an energy to minimize leads to a drastic reduction of these parameters. We prove that the most simple segmentation tool, the "region merging" algorithm, made according to the simplest energy, is enough to compute a local energy minimum belonging to a compact class and to achieve the job of most of the tools mentioned above. We explain why "merging" in a variational framework leads to a fast multiscale, multichannel algorithm, with a pyramidal structure. The obtained algorithm is O(n ln n), where n is the number of pixels of the picture. We apply this fast algorithm to make grey level and texture segmentation and we show experimental results. Key words. variational methods, nonnumerical algorithm, image processing, texture discrimination AMS(MOS) subject classifications. 68Q20,68U10, 1. Int...

Abstract. We describe a new form of energy functional for the modelling and identification of regions in images. The energy is defined on the space of boundaries in the image domain, and can incorporate very general combinations of modelling information both from the boundary (intensity gradients,...), and from the interior of the region (texture, homogeneity,. We describe two polynomial-time digraph algorithms for finding the global minima of this energy. One of the algorithms is completely general, minimizing the functional for any choice of modelling information. It runs in a few seconds on a 256 × 256 image. The other algorithm applies to a subclass of functionals, but has the advantage of being extremely parallelizable. Neither algorithm requires initialization. 1.

In many applications of image analysis, simply connected objects are to be located in noisy images. During the last 5-6 years active contour models have become popular for finding the contours of such objects. Connected to these models are iterative algorithms for finding the minimizing energy curves making the curves behave dynamically through the iterations. These approaches do however have several disadvantages. The numerical algorithms that are in use constraint the models that can be used. Furthermore, in many cases only local minima can be achieved.

A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of raw training data, used here to represent probabilistic mixture distributions of object configurations. Their use avoids tedious hand-construction of object models, and problems with changes of topology. Using exemplars

In the past several years, the speed of standard processors has reached the point where interesting problems requiring visual tracking can be carried out on standard workstations. However, relatively little attention has been devoted to developing visual tracking technology in its own right. In this article, we describe X Vision, a modular, portable framework for visual tracking. X Vision is designed to be a programming environment for real-time vision which provides high performance on standard workstations outfitted with a simple digitizer. X Vision consists of a small set of image-level tracking primitives, and a framework for combining tracking primitives to form complex tracking systems. Efficiency and robustness are achieved by propagating geometric and temporal constraints to the feature detection level, where image warping and specialized image processing are combined to perform feature detection quickly and robustly. Over the past several years, we have used X Vision to constr...

We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.

This paper presents a new method to segment brain parenchyma and cerebrospinal #uid spaces automatically in routine axial spin echo multispectral MR images. The algorithm simultaneously incorporates information about anatomical boundaries #shape# and tissue signature #grey scale# using a priori knowledge. The head and brain are divided into 4 regions and 7 di#erent tissue types. Each tissue type c is modeled by a multivariate Gaussian distribution N## c ; # c #. Each region is associated with a #nite mixture density corresponding to its constituent tissue types. Initial estimates of tissue parameters f# c ; # c g c=1;:::;7 are obtained from k-means clustering of a single slice used for training. The #rst algorithmic step uses the EM-algorithm for adjusting the initial tissue parameter estimates to the MR data of new patients. The second step uses a recently developed model of dynamic contours to detect three simply closed, non-intersecting curves in the plane, constituting the arachno...

The classical active contour model has two basic internal forces: tension and curvature. These forces are included to provide cohension, equal control point spacing, and locally smooth shape. These classical internal forces have undesirable attributes that am in conflict with these original desired characteristics. Tension evenly spaces the control points, but also causes the models to collapse in weak image gradients. Curvature produces locally smooth curvature, but it does so by foming the model toward a straight line. This paper roturns to the original active contour model motivations to reformulate these internal forces. The desired properties am achieved without the introduction of unwanted model behavior A new spacing force and a new constant change in curvature force am introduced and their performance characteristics am discussed. The paper includes experimental results that demonstrate the efficacy and performance of the proposed re formulations.

This paper is an attempt to review the state-of-the-art cortical segmentation techniques in 2-D and 3-D using brain magnetic resonance imaging (MRI), their applications and new challenges