vendredi 24 janvier 2014

½ journƒe Ç  vision par ordinateur È

organisŽe par lÕIRIT-ENSEEIHT

 

PROGRAMME

 

 

 

9h10 Ç Sur l'histoire de la vision tridimensionnelle È

Peter STURM, DR INRIA Rh™ne-Alpes

 

Je prŽsenterai un aperu de l'histoire de quelques problmes en vision par ordinateur gŽomŽtrique, couvrant trois sicles : calcul de pose, reconstruction tridimensionnelle ˆ partir de silhouettes, gŽomŽtrie Žpistolaire, tenseur trifocal, reconstruction projective, auto-calibrage, reconstruction de surfaces de rŽvolution, reconstruction utilisant des miroirs, etc. Beaucoup de ces problmes ont ŽtŽ ŽtudiŽs au XIXe sicle, voire plus t™t É

 

10h00 Ç Shape-from-Template È

Adrien BARTOLI, Pr. ISIT - CENTI, Clermont-Ferrand

 

Imagine an object whose 3D shape -called template- is known. The object now undergoes a deformation, taking a deformed shape, and is imaged once by a digital camera. Under which hypotheses can the deformed shape be recovered from the template and the image? This is one of the fundamental questions arising in Shape-from-Template, the process of reconstructing the 3D shape of a specific object from a single image and a deformation prior. I will first present the models and algorithms proposed to study and solve Shape-from-Template over the last decade. I will then show how Shape-from-Template may facilitate augmented reality  in the specific case of laparoscopic myomectomy, and shall discuss the specific difficulties of this type of applications.É

 

10h50 Pause-cafŽ

 

11h10 Ç Riemannian manifolds, kernels and learning È

Richard HARTLEY, Pr. Research School of Engineering,  Australian National Univ.

 

I will talk about recent results from a number of people in my group on Riemannian manifolds in computer vision.  In many Vision problems Riemannian manifolds come up as a natural model.  Data related to a problem can be naturally represented as a point on a Riemannian manifold. This talk will give an intuitive introduction to Riemannian manifolds, and show how they can be applied in many situations. 

Manifolds of interest include the manifold of Positive Definite matrices and the Grassman Manifolds, which have a role in object recognition and classification, and the Kendall shape manifold, which represents the shape of 2D objects. Of particular interest is the question of when one can define positive-definite kernels on Riemannian manifolds.  This would allow the  application of kernel techniques of SVMs, Kernel FDA, dictionary learning etc directly on the manifold.

 

 

12h00 Ç Surveillance aŽrienne par systme de vision hybride È

David FOFI, Pr. Le2i - IUT Le Creusot

 

L'objectif principal de ces travaux est l'Žlaboration d'un systme de vision pour la surveillance aŽrienne mettant en Ïuvre des camŽras de types diffŽrents. Le systme de vision dit hybride est constituŽ d'une camŽra omnidirectionnelle (fish-eye), permettant une vision globale de la scne, et d'une camŽra PTZ, permettant la visŽe et le zoom sur une cible. Il devra pouvoir identifier et suivre des zones d'intŽrt au sol (cibles) et permettre une reconstruction tridimensionnelle de la scne ou de ses ŽlŽments par stŽrŽoscopie hybride.  Nous aborderons les problŽmatiques suivantes :

- suivi de cibles par vision omnidirectionnelle ;

- auto-calibrage de camŽra PTZ ;

- suivi prŽdictif par vision hybride.  

 

12h50  Cl™ture