Résumé 
Cours  : Analyse de séquences vidéo 
Position : M2 Informatique parcours Image et Plurimédia

Cette ECUE est assurée par l'équipe SIP du laboratoire LIPADE.
Contact : nicolas.lomenie@mi.parisdescartes.fr
Prérequis : Algèbre linéaire, programmation C++, Java ou éventuellement Matlab et équivalent.
Objectifs : donner les outils théoriques et algorithmiques pour concevoir des systèmes d'analyse de séquence vidéo.
Domaines d'applications : jeux, réalité virtuelle, robotique, avatars 3D pour le web, industrie cinématographique et postproduction, imagerie médicale, télésurveillance
Chapitres :
- Calibration de caméra et concept de caméra intelligente
- Principe du flot optique et du calcul du mouvement
- Le problème de la mise en correspondance
- Détection de mouvement, de changement de plans et indexation vidéo
- Algorithmes d'estimation du mouvement dans une séquence vidéo
- Recalage / Registration 
- Estimation du fond et des objets mobiles
- Segmentation d'images par le mouvement
- Compression vidéo MPEG et H2XX
- Algorithmes de reconstruction de monde 3D à partir d'une séquence vidéo 2D

Des ressources importantes pour creuser/se remettre à nveau : http://homepages.inf.ed.ac.uk/ 

1) video lectures - 15 hours of video in c. 10 minute blocks. 
   See: http://homepages.inf.ed.ac.uk/rbf/AVINVERTED/main_av.htm

   Including PDF slides, links to supplementary reading, a drill question for each video
   The site contains a set of video lectures on a subset of computer vision. It is 
   intended for viewers who have an understanding of the nature of images and some 
   understanding of how they can be processed. The course is more like 
   Computer Vision 102, introducing a range of standard and acccepted 
   methods, rather than the latest research advances.

   Similarly, there are are about 8 hours of introductory image processing lectures at:
     http://homepages.inf.ed.ac.uk/rbf/IVRINVERTED/main_ivr.html
   with similar resources

================================================================

2) CVonline is a free WWW-based set of introductions to topics in computer vision. 

    http://homepages.inf.ed.ac.uk/rbf/CVonline/

   Because of the improvements in the content available in Wikipedia, 
   it is now possible to find content for more than 50% of CVonline's 2000 topics.
   CVonline groups together the topics into a sensible topic hierarchy, but tries
   to exploit the advancing quality and breadth of wikipedia's content.

================================================================

3) CVonline has a variety of supplemental information useful to students and researchers,
   namely lists of:

   online and hardcopy books: http://homepages.inf.ed.ac.uk/rbf/CVonline/books.htm
   datasets for research and student projects: http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm
   useful software packages: http://homepages.inf.ed.ac.uk/rbf/CVonline/SWEnvironments.htm
   list of over 300 different image analysis application areas: http://homepages.inf.ed.ac.uk/rbf/CVonline/applic.htm

================================================================

4) The education resources of the Int. Assoc. for Pattern Recognition
   
   http://homepages.inf.ed.ac.uk/rbf/IAPR/

contain many links to Tutorials and Surveys, Explanations, Online Demos, 
Datasets, Books, Code for:
  Symbolic pattern recognition, Statistical pattern recognition, Machine learning, 
  1D Signal pattern recognition and 2D Image analysis and computer vision.

================================================================

5) HIPR2: free WWW-based Image Processing Teaching Materials with JAVA

  http://homepages.inf.ed.ac.uk/rbf/HIPR2/

  HIPR2 is a free www-based set of tutorial materials for the 50 most commonly
  used image processing operators. It contains tutorial text, sample results
  and JAVA demonstrations of individual operators and collections.

================================================================

6) CVDICT: Dictionary of Computer Vision and Image Processing

  http://homepages.inf.ed.ac.uk/rbf/CVDICT/

  This are the free view terms A..G from the the first version of the
  Dictionary, published by John Wiley and Sons. (Note there there a second
  edition currently on sale).