Abstract not found

... alternative to pure automatic segmentation in many applications. While automatic segmentation can be very challenging, a small amount of user input can often resolve ambiguous decisions on the part of the algorithm. In this work, we devise a graph cut algorithm for interactive segmentation which incorporates shape priors. While traditional graph cut approaches to interactive segmentation are often quite successful, they may fail in cases where there are diffuse edges, or multiple similar objects in close proximity to one another. Incorporation of shape priors within this framework mitigates these problems. Positive results on both medical and natural images are demonstrated.

This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instant, and learn a model of facial deformation. Time-varying shape is modeled as a rigid transformation combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deformations are allowed, and thus additional assumptions about deformations are required. We first suggest restricting shapes to lie within a lowdimensional subspace, and describe estimation algorithms. However, this restriction alone is insufficient to constrain reconstruction. To address these problems, we propose a reconstruction method using a Probabilistic Principal Components Analysis (PPCA) shape model, and an estimation algorithm that simultaneously estimates 3D shape and motion for each instant, learns the PPCA model parameters, and robustly fills-in missing data points. We then extend the model to model temporal dynamics in object shape, allowing the algorithm to robustly handle severe cases of missing data.

This paper presents an algorithm for learning the time-varying shape of a non-rigid 3D object from uncalibrated 2D tracking data. We model shape motion as a rigid component (rotation and translation) combined with a non-rigid deformation. Reconstruction is ill-posed if arbitrary deformations are allowed. We constrain the problem by assuming that the object shape at each time instant is drawn from a Gaussian distribution. Based on this assumption, the algorithm simultaneously estimates 3D shape and motion for each time frame, learns the parameters of the Gaussian, and robustly fills-in missing data points. We then extend the algorithm to model temporal smoothness in object shape, thus allowing it to handle severe cases of missing data.

The segmentation of deformable objects from three-dimensional (3-D) images is an important and challenging problem, especially in the context of medical imagery. We present a new segmentation algorithm based on matching probability distributions of photometric variables that incorporates learned shape and appearance models for the objects of interest. The main innovation over similar approaches is that there is no need to compute a pixelwise correspondence between the model and the image. This allows for a fast, principled algorithm. We present promising results on difficult imagery for 3-D computed tomography images of the male pelvis for the purpose of image-guided radiotherapy of the prostate.

We consider the problem of learning how a person’s face behaves in a long video sequence, with the aim of synthesising convincing sequences demonstrating the same behaviours. We describe a novel approach to segment a sequence into short sections, each representing a distinct action (or a part of an action). These sections are grouped and a model of the variability of the action learnt. A variable length Markov model is trained on the sequence of such actions to learn the temporal relationships. The result is a system that can generate realistic sequences of an individual face.

This report provides an analysis of 37 annotated frontal face images. All results presented have been obtained using our freely available Active Appearance Model (AAM) implementation. To ensure the reproducibility of the presented experiments, the data set has also been made available. As such, the data and this report may serve as a point of reference to compare other AAM implementations against. In addition, we address the problem of AAM model truncation using parallel analysis along with a comparable study of the two prevalent AAM learning methods; principal component regression and estimation of fixed Jacobian matrices. To assess applicability and efficiency, timings for model building, warping and optimisation are given together with a description of how

In this paper we investigate the problem of integrating the complementary audio and visual modalities for speech separation. Rather than using independence criteria suggested in most blind source separation (BSS) systems, we use the visual feature from a video signal as additional information to optimize the unmixing matrix. We achieve this by using a statistical model characterizing the nonlinear coherence between audio and visual features as a separation criterion for both instantaneous and convolutive mixtures. We acquire the model by applying the Bayesian framework to the fused feature observations based on a training corporus. We point out several key exisiting challenges to the success of the system. Experimental results verify the proposed approach, whichoutperformstheaudioonlyseparationsystemina noisy environment, and also provides a solution to the permutation problem. 1.

Earlier work has demonstrated generative models capable of synthesising near photo-realistic grey-scale images of objects. These models have been augmented with colour information, and recently with edge information. This paper extends the Active Appearance Model framework by modelling the appearance of both derived feature bands and an intensity band. As a special case of featureband augmented appearance modelling we propose a dedicated representation with applications to face segmentation. The representation addresses a major problem within face recognition by lowering the sensitivity to lighting conditions. Results show that localisation accuracy of facial features is considerably increased using this appearance representation under diuse and directional lighting and at multiple scales. Keywords| Generative models, Active Appearance Models, Lighting Invariance, Face Recognition, Segmentation.

Abstract — We consider the problem of recognizing the configuration of clothing articles when crudely spread out on a flat surface, prior to and during folding. At the core of our approach are parametrized shape models for clothing articles. Each clothing category has its own shape model, and the variety in shapes for a given category is achieved through variation of the parameters. We present an efficient algorithm to find the parameters that provide the best fit when given an image of a clothing article. The models are such that, once the parameters have been fit, they provide a basic parse of the clothing article, allowing it to be followed by autonomous folding from category level specifications of fold sequences. Our approach is also able to recover the configuration of a clothing article when folds are being introduced—an important feature towards closing the perception-action loop. Additionally, our approach provides a reliable method of shape-based classification, simply by examining which model yields the best fit. Our experiments illustrate the effectiveness of our approach on a large set of clothing articles. Furthermore, we present an end-to-end system, which starts from an unknown spread-out clothing article, performs a parametrized model fit, then follows a category-level (rather than article specific) set of folding instructions, closing the loop with perceptual feedback by re-fitting between folds. I.