The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses "factored sampling", previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set. Condensation uses learned dynamical models, together with visual observations, to propagate the random set over time. The result is highly robust tracking of agile motion. Notwithstanding the use of stochastic methods, the algorithm runs in near real-time. Contents 1 Tracking curves in clutter 2 2 Discrete-time propagation of state density 3 3 Factored sampling 6 4 The Condensation algorithm 8 5 Stochastic dynamical models for curve motion 10 6 Observation model 13 7 Applying the Condensation algorithm to video-streams 17 8 Conclusions 26 A Non-line...

This article surveys deformable models, a promising and vigorously researched computer-assisted medical image analysis technique. Among model-based techniques, deformable models offer a unique and powerful approach to image analysis that combines geometry, physics, and approximation theory. They have proven to be effective in segmenting, matching, and tracking anatomic structures by exploiting (bottom-up) constraints derived from the image data together with (top-down) a priori knowledge about the location, size, and shape of these structures. Deformable models are capable of accommodating the significant variability of biological structures over time and across different individuals. Furthermore, they support highly intuitive interaction mechanisms that, when necessary, allow medical scientists and practitioners to bring their expertise to bear on the model-based image interpretation task. This article reviews the rapidly expanding body of work on the development and application of deformable models to problems of fundamental importance in medical image analysis, includingsegmentation, shape representation, matching, and motion tracking.

This paper presents a novel variational framework to deal with frame partition problems in Computer Vision. This framework exploits boundary and region-based segmentation modules under a curve-based optimization objective function. The task of supervised texture segmentation is considered to demonstrate the potentials of the proposed framework. The textured feature space is generated by filtering the given textured images using isotropic and anisotropic filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by unifying region and boundary-based information as an improved Geodesic Active Contour Model. The defined objective function is minimized using a gradient-descent method where a level set approach is used to implement the obtained PDE. According to this PDE, the curve propagation towards the final solution is guided by boundary and region-based segmentation forces, and is constrained by a regularity force. The level set implementation is performed using a fast front propagation algorithm where topological changes are naturally handled. The performance of our method is demonstrated on a variety of synthetic and real textured frames.

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.

Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. Problems associated with initialization and poor convergence to concave boundaries, howevel; have limited their utility. This paper develops a new external force for active contours, largely solving both problems. This external force, which we call gradient vector flow (GVF), is computed as a dijhsion of the gradient vectors of a gray-level or binary edge map derived from the image. The resultant field has a large capture range and forces active contours into concave regions. Examples on simulated images and one real image are presented. 1

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

There has been considerable research interest recently, in the areas of real time contour tracking and active shape models. This paper demonstrates how dynamic filtering can be used in combination with a flexible shape model to track an articulated non-rigid body in motion. The results show the method being used to track the silhouette of a walking pedestrian across a scene in real time. The active shape model used was generated automatically from real image data and incorporates variability in shape due to orientation as well as object flexibility. A Kalman filter is used to control spatial scale for feature search over successive frames and for contour refinement on an individual frame. Iterative refinement allows accurate contour localisation where feasible, although there is a trade-off between speed and accuracy. The shape model incorporates knowledge of the likely shape of the contour and speeds up tracking by reducing the number of system parameters. A further increase in speed ...

Active contours, or snakes, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. A new type of external force for active contours, called gradient vector flow (GVF) was introduced recently to address problems associated with initialization and poor convergence to boundary concavities. GVF is computed as a di#usion of the gradient vectors of a gray-level or binary edge map derived from the image. In this paper, we generalize the GVF formulation to include two spatially varying weighting functions. This improves active contour convergence to long, thin boundary indentations, while maintaining other desirable properties of GVF, such as an extended capture range. The original GVF is a special case of this new generalized GVF (GGVF) model. An error analysis for active contour results on simulated test images is also presented. # 1998 Elsevier Science B.V. All rights reserved. Zusammenfassung Aktive Umrisse, oder Schlangen, we...

We develop a simple and very fast method for object tracking based exclusively on color information in digitized video images. Running on a Silicon Graphics R4600 Indy system with an IndyCam, our algorithm is capable of simultaneously tracking objects at full frame size (640 \Theta 480 pixels) and video frame rate (30 fps). Robustness with respect to occlusion is achieved via an explicit hypothesis-tree model of the occlusion process. We demonstrate the efficacy of our technique in the challenging task of tracking people, especially tracking human heads and hands. 1. Introduction A variety of problems of current interest in computer vision require the ability to track moving objects [2], whether for purposes of surveillance [9], manufacturing, video compression [6], visually "aware" information kiosks [19], etc. The fundamental challenges that drive much of the research in this field are the enormous data bandwidths implied by high resolution frames at high frame rates, a desire for ...

The performance of Active Contours in tracking is highly dependent on the availability of an appropriate model of shape and motion, to use as a predictor. Models can be hand-built, but it is far more effective and less time-consuming to learn them from a training set. Techniques to do this exist both for shape, and for shape and motion jointly. This paper extends the range of shape and motion models in two significant ways. The first is to model jointly the random variations in shape arising within an object-class and those occuring during object motion. The resulting algorithm is applied to tracking of plants captured by a video camera mounted on an agricultural robot. The second addresses the tracking of coupled objects such as head and lips. In both cases, new algorithms are shown to make important contributions to tracking performance.