DOWNLOAD MY CV

Mohamed's Works

Visit of Prime Minister Francois Fillon at the laboratory of computer vision CEA Nano Innov.

Mohamed's Research

Augmented reality application.


Mohamed Tamaazousti's picture
ABOUT
Mohamed Tamaazousti
Hi! My name is Mohamed and I am a French Ph.D. in Computer Vision.
I graduated at CEA LIST under the supervision of Michel Dhome.
I worked on exciting things such as augmented reality, 3d localization, 3d reconstruction and other computer vision subjects.
I'm now researcher at CEA LIST and I'm interested by challenging projects in computer vision...

Research

Constrained SLAM Localization for Augmented Reality Applications

My Ph.D. thesis is concerned with the problem of real time location of a monocular camera. In the literature, there are different methods which can be classified into two categories. The first category considers a camera moving in a completely unknown environment (SLAM). This method performs an online reconstruction of the observed primitives in the images and uses this reconstruction to estimate the location of the camera. The other categorie of method estimates the location of the camera with respect to a 3D object in the scene. The estimation is based on an a priori knowledge of a model of the object (Model-based). The method uses only the information of the 3D model of the object to locate the camera. Each of these methods has advantages and disadvantages. In the context of this thesis, we propose a solution in order to unify all these localization methods in a single framework referred to as the constrained SLAM, by taking parts of their benefits and limiting their disadvantages. We, particularly, consider that the camera moves in a partially known environment, i.e. for which a 3D model (geometric or photometric) of a static object in the scene is available. The objective is then to accurately estimate the pose (position and orientation) of the camera with respect to this object. The absolute information provided by the 3D model of the object is used to improve the localization of the SLAM by directly including this additional information in the bundle adjustment process. In order to manage a wide range of 3D objets and scenes, various types of constraints are proposed.

Key words: Augmented Reality, SLAM, Model-Based Tracking, Constrained SLAM, Constrained Bundle Adjustment
Optical-See-Through Augmented Reality

Augmented Reality could be of great help for critical applications such as driving or surgery assistance. However in these cases every millisecond counts and the user cannot afford to add any latency to reality. This dismisses all video see-through solutions for optical see-through ones, where virtual augmentations are layered onto the reality thanks to a semi-transparent display. This adds new constraints on the system for proper alignment with reality. We focused on a tablet-like system composed of a transparent LCD screen and two localization devices (one to compute the pose relative to the environment and the other to locate the user). We believe this kind of systems would be more practical to the user (well-delimited window, no heavy head-mounted device) and the designer (less constraint on the weight, slower motion) relative to current head-mounted displays.

Key words: Augmented Reality, Computer Vision

Publications

2017

Image-Based Models for Specularity Propagation in Diminished Reality

S. Hadj Said, M. Tamaazousti and A. Bartoli
Journal TVCG - IEEE Transactions on Visualization and Computer Graphics, accepted May 2017.

PDF BibTeX
A Geometric Model for Specularity Prediction on Planar Surfaces with Multiple Light Sources

A. Morgand, M. Tamaazousti and A. Bartoli
Journal TVCG - IEEE Transactions on Visualization and Computer Graphics, accepted February 2017.

PDF BibTeX
2016

An Empirical Model for Specularity Prediction with Application to Dynamic Retexturing

A. Morgand, M. Tamaazousti and A. Bartoli
ISMAR oral - Proceedings of the IEEE International Symposium on Mixed and Augmented Reality, Merida, Mexico, September 2016.

PDF BibTeX
EasyFlow: Increasing the Convergence Basin of Variational Image Matching with a Feature-based Cost

J. Braux-Zin, R. Dupont, A. Bartoli and M. Tamaazousti
Journal IET - IET Computer Vision, accepted September 2016.

PDF BibTeX
The Constrained SLAM Framework for Non-Instrumented Augmented Reality - Application to Industrial Training

M. Tamaazousti, S. Naudet-Collette, V. Gay-Bellile, S. Bourgeois, B. Besbes and M. Dhome
Journal MTAP - Multimedia Tools and Applications, 75(16): 9511-9547, August 2016.

PDF BibTeX
Modéle empirique de prédiction géométrique de spécularité : application au retexturing

A. Morgand, M. Tamaazousti and A. Bartoli
RFIA - Actes du Congrès Francophone de Reconnaissance des Formes et Intelligence Artificielle, Clermont-Ferrand, France, Juin 2016.

PDF BibTeX
2015

Applications of Augmented Reality for the Automobile Industry

V. Gay-Bellile, S. Bourgeois, D. Larnaout and M. Tamaazousti
Book Chapter - Fundamentals of Wearable Computers and Augmented Reality.

PDF BibTeX
Détection générique et temps réel des spécularités

A. Morgand, M. Tamaazousti and A. Bartoli
ORASIS - Journées francophones des jeunes chercheurs en vision par ordinateur, Amiens, France, Juin 2015.

PDF BibTeX
Reconstruction d'une source lumineuse modélisée par une quadrique à partir d'images multiples

A. Morgand, M. Tamaazousti and A. Bartoli
ORASIS - Journées francophones des jeunes chercheurs en vision par ordinateur, Amiens, France, Juin 2015.

PDF BibTeX
Image Processing in the Presence of Specularities (Procédé de traitement d'images avec spécularités)

M. Tamaazousti, A. Bartoli and A. Morgand
PATENT - Pending, filed 8-jun-2015.

PDF BibTeX
2014

SLAM contraint pour la localisation dans des environnements partiellement connus

S. Naudet, V. Gay-Bellile, S. Bourgeois, M. Tamaazousti, D. Larnaout and M. Dhome
RFIA - Actes du Congrès Francophone de Reconnaissance des Formes et Intelligence Artificielle, Rouen, France, Juillet 2014.

PDF BibTeX
Constrained PatchMatch for Image Completion

G. Chican and M. Tamaazousti
ISVC - Proceedings of the 10th International Symposium on Visual Computing, Las Vegas, Nevada, USA, December 2014.

PDF BibTeX
Caméras virtuelles pour l'étalonnage d'un système de réalité augmentée sur affichage semi-transparent

J. Braux-zin, A. Bartoli, R. Dupont, M. Tamaazousti
Journal TS - Traitement du Signal (revue du GRETSI CNRS), édition spéciale ORASIS 2013, 31(1-2):175-195, 2014.

PDF BibTeX
Generic and Real-time Detection of Specular Reflections in Images

A. Morgand, M. Tamaazousti
VISAPP - Proceedings of the IEEE International Conference on Computer Vision Theory and Applications, pp. 274-282, vol. I.

PDF BibTeX
2013

Modeling, Tracking, Annotating and Augmenting a 3D Object in less than 5 Minutes

S. Bourgeois, B. Meden, V. Gay-Bellile, M. Tamaazousti, S. Knödel
ISMAR Workshop - IEEE ISMAR Joint Workshop on Tracking Methods & Applications and TrakMark, Adelaide, South Australia, October 2013.

PDF BibTeX
L'ajustement de faisceaux contraint comme cadre d'unification des méthodes de localisation: application à la réalité augmentée sur des objets 3D

M. Tamaazousti
PhD Thesis - (in French) Thèse de doctorat - Université Blaise Pascal-Clermont-Ferrand II, Mars 2013.

PDF BibTeX
A Region Driven and Contextualized Pedestrian Detector

T. Chesnais, T. Chateau, N. Allezard, Y. Dhome, B. Meden, M. Tamaazousti, A Chan-Hon-Tong
VISAPP - Proceedings of the IEEE International Conference on Computer Vision Theory and Applications, pp. 796-799, vol. I.

PDF BibTeX
2012

An interactive Augmented Reality system: A prototype for industrial maintenance training applications

B. Besbes, S. Naudet-Collette, M. Tamaazousti, S. Bourgeois, V. Gay-Bellile
ISMAR - Proceedings of the IEEE International Symposium on Mixed and Augmented Reality, pp. 269-270, Atlanta, GA, USA, November 2012.

PDF BibTeX
A mobile markerless Augmented Reality system for the automotive field

V. Gay-Bellile, S. Bourgeois, M. Tamaazousti, S. Naudet Collette, S. Knodel
ISMAR Workshop - IEEE ISMAR Workshop on Tracking Methods and Applications (TMA), Atlanta, GA, USA, November 2012.

PDF BibTeX
Localisation précise et temps réel dans un environnement partiellement connu : application au suivi d'objet 3D peu texturé

M. Tamaazousti, V. Gay-Bellile, S. Naudet Collette, S. Bourgeois, M. Dhome
RFIA - Actes du Congrès Francophone de Reconnaissance des Formes et Intelligence Artificielle, Lyon, France, Janvier 2012.

PDF BibTeX
2011

Real-Time Accurate Localization in a Partially Known Environment:Application to Augmented Reality on textureless 3D Objects

M. Tamaazousti, V. Gay-Bellile, S. Naudet Collette, S. Bourgeois, M. Dhome
ISMAR Workshop - The 2nd International Workshop on AR/MR Registration, Tracking and Benchmarking (TrakMark), Basel, Switzerland, October 2011.

PDF BibTeX
Raffinement non linéaire d'une reconstruction de type SfM dans un environnement partiellement connu

M. Tamaazousti, V. Gay-Bellile, S. Naudet Collette, M. Dhome.
ORASIS - Actes du treizième congrès francophone des jeunes chercheurs en vision par ordinateur, Praz-sur-Arly, France, Juin 2011.

PDF BibTeX
NonLinear refinement of structure from motion reconstruction by taking advantage of a partial knowledge of the environment

M. Tamaazousti, V. Gay-Bellile, S. Naudet-Collette, S. Bourgeois, M. Dhome
CVPR - Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Colorado Springs, Colorado, June 2011.

PDF BibTeX
Method for Locating a Camera and for 3D Reconstruction in a Partially Known Environment

M. Tamaazousti, V. Gay-Bellile, S. Naudet Collette, S. Bourgeois, M. Dhome
PATENT - Filed June 2011.

PDF BibTeX
2010

A Vision-Based Hybrid System for Real-time Accurate Localization in an Indoor Environment

V. Gay-Bellile, M. Tamaazousti, R. Dupont, S. Naudet-Collette
VISAPP - Proceedings of the IEEE International Conference on Computer Vision Theory and Applications, pp. 216-222, vol. I.

PDF BibTeX
2009

Localisation temps réel par stéréovision : détection, mise en correspondance et reconstruction de points d'intérêt.

M. Tamaazousti
MSc Thesis - (in French) - Université d'Orléans and CEA (Commissariat à l'énergie atomique), September 2009

PDF BibTeX

SUPERVISING AND COLLABORATORS

Post-doc

- Frédéric Bousefsaf (since 2015, with Rémi Michel)


PhD students

- Souheil Hadj Said (since 2015, with Adrien Bartoli)
- Alexandre Morgand (since 2014, with Adrien Bartoli)
- Jim Braux-Zin (graduated in 2014, with Adrien Bartoli)


Master students (M2)

- Lucas Morlet (2016)
- Daniel Brooks (2015)
- Guillaume Chican (2014)
- Tarek Awwad (2014)
- Alexandre Morgand (2013)
- Jonathan Gault (2013)
- Antoine Moevus (2012)
- Angélique Loesch (2012)
- Sylvain Botto (2011)