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...

. We present a new framework for interpreting face images and image sequences using an Active Appearance Model (AAM). The AAM contains a statistical, photo-realistic model of the shape and grey-level appearance of faces. This paper demonstrates the use of the AAM's efficient iterative matching scheme for image interpretation. We use the AAM as a basis for face recognition, obtain good results for difficult images. We show how the AAM framework allows identity information to be decoupled from other variation, allowing evidence of identity to be integrated over a sequence. The AAM approach makes optimal use of the evidence from either a single image or image sequence. Since we derive a complete description of a given image our method can be used as the basis for a range of face image interpretation tasks. 1 Introduction There is currently a great deal of interest in model-based approaches to the interpretation of images [17] [9] [15] [14][8]. The attractions are two-fold: robust interpr...

This thesis establishes a stochastic framework for tracking curves in visual clutter, using a Bayesian random-sampling algorithm. The approach is rooted in ideas from statistics, control theory and computer vision. The problem is to track outlines and features of foreground objects, modelled as curves, as they move in substantial clutter, and to do it at, or close to, video frame-rate. The algorithm, named Condensation, for Conditional density propagation, has recently been derived independently by several researchers, and is generating signi cant interest in the statistics and signal processing communities. This thesis contributes to the literature on Condensation-like lters by presenting some novel applications of and extensions to the basic algorithm, and contributes to the visual motion estimation literature by demonstrating high tracking performance in cluttered environments. Despite its power the Condensation algorithm has a remarkably simple form and this allows the use of non-linear motion models which combine characteristics of discrete Hidden Markov Models with the continuous Auto-Regressive Process motion models traditionally used in Kalman lters. These mixed discrete-continuous models have promising applications to the emerging eld of perception of action. This thesis also implements two algorithms to smooth the output of the Condensation lter which improves the accuracy of motion estimation in a batch-mode procedure after tracking is complete.

Abstract—We propose a new image segmentation technique called strings. A string is a variational deformable model that is learned from a collection of example objects rather than built from a priori analytical or geometrical knowledge. As opposed to existing approaches, an object boundary is represented by a one-dimensional multivariate curve in functional space, a feature function, rather than by a point in vector space. In the learning phase, feature functions are defined by extraction of multiple shape and image features along continuous object boundaries in a given learning set. The feature functions are aligned, then subjected to functional principal components analysis and functional principal regression to summarize the feature space and to model its content, respectively. Also, a Mahalanobis distance model is constructed for evaluation of boundaries in terms of their feature functions, taking into account the natural variations seen in the learning set. In the segmentation phase, an object boundary in a new image is searched for with help of a curve. The curve gives rise to a feature function, a string, that is weighted by the regression model and evaluated by the Mahalanobis model. The curve is deformed in an iterative procedure to produce feature functions with minimal Mahalanobis distance. Strings have been compared with active shape models on 145 vertebra images, showing that strings produce better results when initialized close to the target boundary, and comparable results otherwise. Index Terms—Machine learning, deformable models, energy minimization, multivariate statistics, shape analysis, functional data analysis, chemometrics, active shape models. 1

The interaction between man and machines has become an important topic for the robotics community as it can generalise the use of robots. One of the requirements for this interaction is that a robot be able to detect and analyse the motion of a person in its vicinity. This paper describes a Monte-Carlo based method for human head/hand detection and tracking in video streams. The tracked part is modelled by a spline. The pose estimation consists in fitting the model to the current image gradient taking into account with motion measurements. Results of detection and tracking using these combined criteria are illustrated. The limits of the method are also discussed. Finally, future extensions are proposed, based on colour segmentation, to improve the robustness of the method.