We introduce a novel approach to the problem of localizing objects in an image and estimating their fine-pose. Given exact CAD models, and a few real training images with aligned models, we propose to leverage the geometric information from CAD models and appearance information from real images to learn a model that can accurately estimate fine pose in real images. Specifically, we propose FPM,...

In this paper constrained contour models are applied for hand posture recognition in single color images. In particular, the proposed algorithm utilizes a class of physics-based modelling methods called Deformable Templates [1],[2],[3]. After colorbased image segmentation a contour hypothesis is detected and some features are extracted, suitable for comparison with the template’s geometric prop...

Most of today's medical simulation systems are based on geometric representations of anatomical structures that take no account of their physical nature. Representing physical phenomena and, more speci cally the realistic modeling of soft tissue will not only improve current medical simulation systems but will considerably enlarge the set of applications and the credibility of medical simulatio...

Surgical training systems based on virtual reality (VR) and simulation techniques may represent a more cost effective and efficient alternative to traditional training methods. Additionally, VR is a technology that can teach surgeons new procedures and can determine their level of competence before they operate on patients. At Forschungszentrum Karlsruhe, a virtual reality training system for m...

One of the major challenges in physically-based modeling is making simulations efficient. Adaptive models provide an essential solution to these efficiency goals. These models are able to self-adapt in space and time, attempting to provide the best possible compromise between accuracy and speed. This survey reviews the adaptive solutions proposed so far in computer graphics. Models are classifi...

In recent years, research efforts to extend linear metric learning models to handle nonlinear structures have attracted great interests. In this paper, we propose a novel nonlinear solution through the utilization of deformable geometric models to learn spatially varying metrics, and apply the strategy to boost the performance of both kNN and SVM classifiers. Thin-plate splines (TPS) are chosen...

In this paper, we introduce a real-time algorithm to render the rich visual effects of general non-height-field geometric details, known as mesostructure. Our method is based on a five-dimensional generalized displacement map (GDM) that represents the distance of solid mesostructure along any ray cast from any point within a volumetric sample. With this GDM information, we propose a technique t...

OBJECTIVES To develop and validate a prediction model for gestational diabetes mellitus (GDM) at 11-13 weeks' gestation based on maternal characteristics and history and to compare its performance with the method recommended by the National Institute of Health and Care Excellence (NICE) and five other published prediction models. METHODS A predictive logistic regression model for GDM was deve...

OBJECTIVE To determine the recurrence rate of gestational diabetes (GDM) during a subsequent pregnancy among women who had GDM during an index pregnancy and to identify factors associated with the probability of recurrence RESEARCH DESIGN AND METHODS A retrospective longitudinal study was performed in Nova Scotia, Canada, of women who were diagnosed as having GDM during a pregnancy between th...