Previous approaches to deformable model shape estimation and tracking have assumed a fixed class of shapes representation (e.g., deformable superquadrics), initialized prior to tracking. Since the shape coverage of the model is fixed, such approaches do not directly accommodate incremental representation discovery during tracking. As a result, model shape coverage is decoupled from tracking, th...

An integrated system for the acquisition, normalisation and recognition of moving faces in dynamic scenes is introduced. Four face recognition tasks are deened and it is argued that modelling person-speciic probability densities in a generic face space using mixture models provides a technique applicable to all four tasks. The use of Gaussian colour mixtures for face detection and tracking is a...

Convolutional neural networks (CNNs) have demonstrated their ability object detection of very high resolution remote sensing images. However, CNNs have obvious limitations for modeling geometric variations in remote sensing targets. In this paper, we introduced a CNN structure, namely deformable ConvNet, to address geometric modeling in object recognition. By adding offsets to the convolution l...

In this paper we propose a technique for 3-D segmentation of abdominal aortic aneurysm (AAA) from computed tomography angiography (CTA) images. Output data (3-D model) form the proposed method can be used for measurement of aortic shape and dimensions. Knowledge of aortic shape and size is very important in planning of minimally invasive procedure that is for selection of appropriate stent graf...

Deformable models often vary in object boundary representation and the external force field used. Conventional methods, i.e. geodesic active contour model [1], have difficulties in dealing with boundary concavities, weak edges and image noise. Some approaches such as the generalized gradient vector flow (GGVF) [3] showed some improvements but have convergence issues caused by saddle or stationa...

Goals The basic objective of VIDAS was that of approaching the problem of facial animation from a combined audio-video point of view, for both the analysis and the synthesis. The main goal was the consolidation of advanced technologies for synthetic/natural representation and coding of facial sequences. In particular, a generic face-to-face communication has been modelled as a multimodal inform...

An e cient computational model for the dynamics of a deformable robot ngertip is presented. The dynamic model is based on a discretization of the ngertip's volume into a lattice of masses locally interconnected by damped springs. The lattice's parameters are adjusted in correspondence with bulk properties of the ngertip's deformable material (rubber). In the task studied, the ngertip moves towa...

This paper presents the design of an expandable animation system in which rigid and deformable multi-body systems are animated from the high-level model of physical objects. This new model called dream (Deformable and Rigid objects EEcient for Animation Modelling) makes the simulation of rigid and de-formable interconnected objects easy to design and to implement. dream is based on a uniied abs...

We present a novel approach, based on local image histograms, for statistically characterizing the appearance of deformable models. In deformable model segmentation, appearance models measure the likelihood of an object given a target image. To determine this likelihood we compute pixel intensity histograms of local object-relative image regions from a 3D image volume near the object boundary. ...

An integrated system for the acquisition, normalisation and recognition of moving faces in dynamic scenes is introduced. Four face recognition tasks are deened and it is argued that modelling person-speciic probability densities in a generic face space using mixture models provides a technique applicable to all four tasks. The use of Gaussian colour mixtures for face detection and tracking is a...