|
|
Ahmed Gamal Eldin
PhD Student, ARIANA
 Keywords : Stochastic Geometry, Multiple object exctraction, Birth-and-death dynamics, Marked point process
 Contact :
| Mail : | | AhmeddotGamal_eldinatinriadotfr | | Phone : | | (33)4-92-38-75-66 | | Fax : | | (33)4-92-38-76-43 | | Postal adress : | | INRIA Sophia Antipolis
2004, route des Lucioles
06902 Sophia Antipolis Cedex
France | | Webpage : | | visit ! |
|
| Abstract :
Thesis title: Point process and graph cut applied to 2D and 3D object extraction
The accomplished work during the thesis can be presented in two parts:
The first part:
---------------
The aim of this part is to develop a novel approach for 3D object detection from a 2D image. This approach takes into consideration the occlusions and the perspective effects. This work has been embedded in a marked point process framework, proved to be efficient for solving many challenging problems dealing with high resolution images.
We propose a novel probabilistic approach to handle occlusions and perspective effects. The proposed method is based on 3D scene simulation on the GPU using OpenGL. It is an object based method embedded in a marked point process framework. We apply it for the size estimation of a penguin colony, where we model a penguin colony as an unknown number of 3D objects. The main idea of the proposed approach is to sample some candidate configurations consisting of 3D objects lying on the real plane. A Gibbs energy is define on the configuration space, which takes into account both prior and data information. The proposed configurations are projected onto the image plane, and the configurations are modified until convergence. To evaluate a proposed configuration, we measure the similarity between the projected image of the proposed configuration and the real image, by defining a data term and a prior term which penalize objects overlapping. We introduced modifications to the optimization algorithm to take into account new dependencies that exists in our 3D model.
The second part:
----------------
We propose a new optimization method which we call "Multiple Births and Cut" (MBC). It combines the recently developed optimization algorithm Multiple Births and Deaths (MBD) and the Graph-Cut. MBD and MBC optimization methods are applied for the optimization of a marked point process. We compared the MBC to the MBD algorithms showing that the main advantage of our newly proposed algorithm is the reduction of the number of parameters, the speed of convergence and the quality of the obtained results. We validated our algorithm on the counting problem of flamingos in a colony. |
Short Bio :
2012: Postdoc at LEAR team, INRIA Rhône Alpes, France
2008 - 2011 PhD at Ariana team, INRIA Sophia Antipolis, France
2007 - 2008 Masters in Image Processing and Computer Vision, ENSPS, University of Strasbourg, France
2004 - 2007 Masters of Electronics and Telecommunication, Egypt
2004 - 2007 Teacher assistant in faculty of engineering, UFE, Egypt
2003 : Unix System Administration certificat, Egypt
1997 - 2002 BSc. in Electronics and Telecommunication, Egypt
|
Last publications in Ariana Research Group :
Processus ponctuels et algorithmes de coupure minimal de graphe appliqués à l'extraction d'objets 2D et 3D.
A. Gamal Eldin. PhD Thesis, Universite de Nice Sophia Antipolis, October 2011.
Keywords : Multiple object detection, Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process, Stochastic geometry.
@PHDTHESIS{GamalPhdThesis,
|
| author |
= |
{Gamal Eldin, A.}, |
| title |
= |
{Processus ponctuels et algorithmes de coupure minimal de graphe appliqués à l'extraction d'objets 2D et 3D}, |
| year |
= |
{2011}, |
| month |
= |
{October}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| url |
= |
{http://tel.archives-ouvertes.fr/tel-00737988}, |
| keyword |
= |
{Multiple object detection, Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process, Stochastic geometry} |
| } |
Résumé :
L'objectif de cette thèse est de développer une nouvelle approche de détection d'objets 3D à partir d'une image 2D, prenant en compte les occultations et les phénomènes de perspective. Cette approche est fondée sur la théorie des processus ponctuels marqués, qui a fait ses preuves dans la solution de plusieurs problèmes en imagerie haute résolution. Le travail de la thèse est structuré en deux parties: En première partie: Nous proposons une nouvelle méthode probabiliste pour gérer les occultations et les effets de perspective. Le modèle propose est fondé sur la simulation d'une scène 3D utilisant OpenGL sur une carte graphique (GPU). C'est une méthode orientée objet, intégrée dans le cadre d'un processus ponctuel marqué. Nous l'appliquons pour l'estimation de la taille d'une colonie de manchots, là où nous modélisons une colonie de manchots comme un nombre inconnu d'objets 3D. L'idée principale de l'approche proposée consiste à échantillonner certaines configurations candidat composé d'objets 3D s'appuyant sur le plan réel. Une densité de Gibbs est définie sur l'espace des configurations, qui prend en compte des informations a priori et sur les données. Pour une configuration proposée, la scène est projetée sur le plan image, et les configurations sont modifiées jusqu'à convergence. Pour évaluer une configuration proposée, nous mesurons la similarité entre l'image projetée de la configuration proposée et l'image réelle, définissant ainsi le terme d'attache aux données et l'a priori pénalisant les recouvrements entre objets. Nous avons introduit des modifications dans l'algorithme d'optimisation pour prendre en compte les nouvelles dépendances qui existent dans notre modèle 3D. En deuxième partie: Nous proposons une nouvelle méthode d'optimisation appelée |
Abstract :
The topic of this thesis is to develop a novel approach for 3D object detection from a 2D image. This approach takes into consideration the occlusions and the perspective effects. This work has been embedded in a marked point process framework, proved to be efficient for solving many challenging problems dealing with high resolution images. The accomplished work during the thesis can be presented in two parts: First part: We propose a novel probabilistic approach to handle occlusions and perspective effects. The proposed method is based on 3D scene simulation on the GPU using OpenGL. It is an object based method embedded in a marked point process framework. We apply it for the size estimation of a penguin colony, where we model a penguin colony as an unknown number of 3D objects. The main idea of the proposed approach is to sample some candidate configurations consisting of 3D objects lying on the real plane. A Gibbs energy is define on the configuration space, which takes into account both prior and data information. The proposed configurations are projected onto the image plane, and the configurations are modified until convergence. To evaluate a proposed configuration, we measure the similarity between the projected image of the proposed configuration and the real image, by defining a data term and a prior term which penalize objects overlapping. We introduced modifications to the optimization algorithm to take into account new dependencies that exists in our 3D model. Second part: We propose a new optimization method which we call |
Extraction et caractérisation de régions saines et pathologiques à partir de micro-tomographie RX du système vasculaire cérébral.
X. Descombes and A. Gamal Eldin and F. Plouraboue and C. Fonta and S. Serduc and G. Le Duc and T. Weitkamp. In Proc. GRETSI Symposium on Signal and Image Processing, Bordeaux, France, September 2011.
@INPROCEEDINGS{XavierGRETSI11,
|
| author |
= |
{Descombes, X. and Gamal Eldin, A. and Plouraboue, F. and Fonta, C. and Serduc, S. and Le Duc, G. and Weitkamp, T.}, |
| title |
= |
{Extraction et caractérisation de régions saines et pathologiques à partir de micro-tomographie RX du système vasculaire cérébral}, |
| year |
= |
{2011}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. GRETSI Symposium on Signal and Image Processing}, |
| address |
= |
{Bordeaux, France}, |
| url |
= |
{http://hal.inria.fr/inria-00625525/fr/}, |
| keyword |
= |
{} |
| } |
Abstract :
In this paper, we consider X-ray micro-tomography representing the brain vascular network. We define the local vascular territories as the regions obtained after a watershed algorithm applied on the distance map. The obtained graph is then regularized by a Markov random field approach. The optimization is performed using a graph cut algorithm. We show that the resulting segmentation exhibits three classes corresponding to normal tissue, tumour and an intermediate region. |
A fast multiple birth and cut algorithm using belief propagation.
A. Gamal Eldin and X. Descombes and Charpiat G. and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, September 2011.
Keywords : Multiple Birth and Cut, multiple object extraction, Graph Cut, Belief Propagation.
@INPROCEEDINGS{MBC_ICIP11,
|
| author |
= |
{Gamal Eldin, A. and Descombes, X. and G., Charpiat and Zerubia, J.}, |
| title |
= |
{A fast multiple birth and cut algorithm using belief propagation}, |
| year |
= |
{2011}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Brussels, Belgium}, |
| url |
= |
{http://hal.inria.fr/inria-00592446/fr/}, |
| keyword |
= |
{Multiple Birth and Cut, multiple object extraction, Graph Cut, Belief Propagation} |
| } |
Abstract :
In this paper, we present a faster version of the newly proposed Multiple Birth and Cut (MBC) algorithm. MBC is an optimization method applied to the energy minimization of an object based model, defined by a marked point process. We show that, by proposing good candidates in the birth step of this algorithm, the speed of convergence is increased. The algorithm starts by generating a dense configuration in a special organization, the best candidates are selected using the belief propagation algorithm. Next, this candidate configuration is combined with the current configuration using binary graph cuts as presented in the original version of the MBC algorithm. We tested the performance of our algorithm on the particular problem of counting flamingos in a colony, and show that it is much faster with the modified birth step. |
|
All publications in Ariana Research Group
|
|
New demo webpage
