Wyniki wyszukiwania - Biblioteka Nauki

1

Ellipsoid Fourier Descriptor : hierarchical shape representation and deformable model

100%

Dufrenois F.

Machine Graphics and Vision

|

2000

|

tom Vol. 9, No. 1/2

103-113

EN

This paper describes a new model-based segmentation and motion analysis technic combining Euler-Lagrange formalism and shape representation by Fourier decomposition. First, we propose to extend the concept of the 2D Fourier representation for closed curves to a new 3D hierarchical descriptor for closed surfaces. To study the shape deformation during motion, we establish also, the dynamic equations of motion of the Fourier parameters. Finally, some results on 2D data traking, 3D reconstructions and 3D data fitting are presented.

2

3D graphical models for vascular-stent pose simulation

86%

Flórez-Valencia L. , Montagnat J. , Orkisz M.

Machine Graphics and Vision

|

2004

|

tom Vol. 13, No. 3

235-248

EN

Stents are playing an increasing role in the treatment of arterial stenoses and aneurysms. The goal of this work is to help the clinician in the pre-operative choice of the stent length and diameter. This is done by embedding a model of the stent within a real 3D vascular image. Two models are used. First, a simple geometrical model, composed of a set of circles or polygons stacked along the vessel centerline, is used to simulate the introduction and the deployment of the stent. Second, a simplex-mesh model with an adapted cylindrical constraint is used to represent the stent surface. Another axially constrained simplex-mesh deformable model is used to reconstruct a 3D vessel wall. We simulate the interaction between the vessel wall and the stent by imposing the condition that the model of the vessel locally fits the shape of the deployed stent model. Preliminary quantitative results of the vessel reconstruction accuracy are given.

3

Robust 4D segmentation of cells in confocal images

86%

Mischler D. , Romaniuk B. , Benassarou A. , Bittar E.

Machine Graphics and Vision

|

2006

|

tom Vol. 15, No. 3/4

515-524

EN

We present a method to automatically extract the evolution of the cell envelope in 4D confocal images. Our method is based on 4D ReAM, a tracking system consisting of a previously presented deformable surface model, which can change its topology. The process consists in attracting the model for each volume of a 4D series towards an iso-surface of interest, and towards the image gradients. We then statistically estimate the characteristics of the cell surface on the nodes of the model, and reconstruct it. We show detailed results on the segmentation of the cell envelope during the mitosis.

4

Multiresolution representation techniques of 3D objects from range data

72%

Espadero J. M. , Rincon L. , Pastor L. , Rodríguez A.

Journal of Applied Computer Science

|

2001

|

tom Vol. 9, nr 2

19-30

EN

The advances realised during the last years in 3D object digitization technology have resulted in a considerable increase in the number and importance of applications that handle 3D spatial information, and in the amount of interest shown by the scientific community to the different problems involved in 3D data processing. This paper presents a comparison between two techniques for computing multiresolution shape models of 3D objects acquired as clouds of 3D points. Both of these techniques deform a mesh template over the input data, constructing the multiresolution representations using wavelet transforms. The first technique is based on a facet-based approach, while the second one uses a vertex-based approximation. The procedure is fully automated and can process data from any object with a genus equivalent to that of a sphere. An important feature of these methods is that they do not impose any restrictions on the input data. which can be provided by any type of 3D sensor. Advantages and disadvantages of both approaches are also analysed, and some experimental results are shown.

5

Generating personalized anatomy-based 3D facial models from scanned data

72%

Zhang Y. , Sim T. , Tan C. L.

Machine Graphics and Vision

|

2005

|

tom Vol. 14, No. 1

3-28

EN

This paper presents a new method for reconstructing animatable, anatomy-based human facial models from scanned range data. Our method adapts a prototype model that is suitable for physically-based animation to the geometry of a specific person's face with minimal user intervention. The prototype model has a known topology and incorporates a multi-layer structure of the skin, muscles, and skull. Based on the series of measurements between a subset of anthropometric landmarks specified on the prototype model and the scanned surface, an automated global alignment adapts the size, position, and orientation of the prototype model to align it with the scanned surface. In the skin layer adaptation, The generic skin mesh is represented as a dynamic deformable model which is subjected to internal force stemming from the elastic properties of the surface and external forces generated by the scanned data points and features. We automatically deform the underlying muscle layer consisting of three types of muscle models. A set of automatically generated skull feature points is then transformed based on the deformed external skin and muscle layers. The new positions of these feature points are used to drive volume morphing applied to the skull template for skull fitting. With the adapted multi-layer anatomical structure, the reconstructed model not only resembles the shape of the individual's face but can also be animated instantly using the muscle and jaw parameters.

6

Program do analizy obrazów za pomocą deformowalnych modeli

72%

Szczypiński P. , Materka A.

Elektronika : prace naukowe

|

2000

|

tom nr 5

33-50

PL

W artykule przedstawiono techniki analizy obrazów z zastosowaniem deformowalnych modeli. Przedstawiono model aktywnego konturu służący do wyznaczania linii brzegowych i segmentacji obrazu oraz deformowalny wzorzec, model służący do wyznaczania położenia i rozpoznawania obiektów przedstawionych w obrazie cyfrowym. Omówiono również oryginalne modyfikacje modeli wprowadzone przez pierwszego z autorów. W dalszej części przedstawiono oryginalny program komputerowy „Siatki". Program ten jest narzędziem analizy obrazów wykorzystującym modele aktywnego konturu i deformowalnego wzorca. Opisano jak obsługiwać program oraz jak prowadzić analizy obrazów z jego wykorzystaniem. Prace nad deformowalnymi modelami są wspomagane przez KBN — projekt nr 8T11C02017.

EN

This article presents techniques for image analysis with deformable models. The active contour model for image edges detection and image segmentation is presented. Also, a deformable grid is introduced, a model for finding object position within the image and for object recognition. Furthermore, first author original modifications to these models are presented. Finally, an original computer program "Siatki" is introduced. "Siatki" is a tool for digital image analysis with active contour model and deformable grid. It is described how to operate and how to perform an image analysis with the program. Research into deformable models is supported by the grant KBN no. 8T11C02017.

7

3D face reconstruction with region based best fit blending using mobile phone for virtual reality based social media

58%

Anbarjafari G. , Haamer R. E. , Lüsi I. , Tikk T. , Valgma L.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2019

|

tom Vol. 67, nr 1

125--132

EN

The use of virtual reality (VR) has been exponentially increasing and due to that many researchers have started to work on developing new VR based social media. For this purpose it is important to have an avatar of the user which look like them to be easily generated by the devices which are accessible, such as mobile phones. In this paper, we propose a novel method of recreating a 3D human face model captured with a phone camera image or video data. The method focuses more on model shape than texture in order to make the face recognizable. We detect 68 facial feature points and use them to separate a face into four regions. For each area the best fitting models are found and are further morphed combined to find the best fitting models for each area. These are then combined and further morphed in order to restore the original facial proportions. We also present a method of texturing the resulting model, where the aforementioned feature points are used to generate a texture for the resulting model.

8

Application of cellular neural networks and deformable models to object recognition

58%

Korbiel P.

Zeszyty Naukowe. Elektryka / Politechnika Łódzka

|

2007

|

tom z. 111

65-72

EN

The following paper presents an idea of deformable grid object-recognition paradigm implementation within a framework of Cellular Neural Network Universal Machine (CNN-UM). A method for parallel representation of deformable grid, as well as a method for parallel modelling of grid matching process has been proposed. The proposed object recognition method has been verified by means of computer simulations and experimentally by using actual hardware CNN-UM implementations. The main advantage of the method is a fast realisation of the recognition task.

PL

Podstawowym celem pracy było wykazanie możliwości efektywnej implementacji metody rozpoznawania obrazów, bazującej na wykorzystaniu siatek deformowalnych, w strukturze równoległego, macierzowego procesora obrazu, jaki stanowi uniwersalna sieć neuronowa komórkowa (USNK). W wyniku przeprowadzonych badań opracowano sposób reprezentacji deformowalnej siatki dostosowany do architektury procesorów USNK. Opracowana została metoda równoległego modelowania mechanizmów decydujących o przemieszczaniu węzłów siatki deformowalnej w procesie analizy obrazu. Opracowany w wyniku badań algorytm rozpoznawania został pomyślnie zweryfikowany w drodze symulacji komputerowych. Zweryfikowana została także możliwość realizacji opracowanego algorytmu przy użyciu współczesnych platform sprzętowych zbudowanych w oparciu o strukturę uniwersalnej sieci neuronowej komórkowej. Sformułowana w wyniku przeprowadzonych badań metoda pozwala na istotne poszerzenie możliwości funkcjonalnych współczesnych układów inteligentnych sensorów informacji wizyjnej, pozwalając na realizację złożonej analizy obrazu już na poziomie przetwarzania wstępnego. W konsekwencji, zaproponowane rozwiązanie pozwala na znaczące zwiększenie efektywności pracy szerokiej klasy systemów automatycznego monitorowania i nadzoru, korzystających z rozproszonych źródeł informacji wizyjnej.