Dr. Julien de Siebenthal, HEIG-Vd, Switzerland

We will target a complete pipeline allowing to locate and identify passive markers used to overlay 3D objects.

(1) introduction to video camera :
  - basic optics, basic radiometry, geometric image formation
  - spatial sampling, noise estimation & filtering
  - camera parameters

(2)  image features :
  - edge detection
  - Hough transform for lines and curves
  - ellipse fitting

(3) recognition (identification) : 
  - interpretation trees
  - invariants

(4) locating image in space & 3D :
  - matching from intensity data (perspective, weak perspective)
  - 3D overlay

Laboratory environment
C/C++ code, OpenCV, OpenGL, ARToolkit

Laboratory exercices
  - image filtering : noise estimation
  - edge detection & Hough transform for lines
  - locating image in space : perspective model

Requirements:
Laptop, C compiler (Visual 9 Express)

Reference book
Introductory Techniques for 3-D Computer Vision, E. Trucco, A. Verri, 1998 Prentice Hall

Link: http://en.wikipedia.org/wiki/ARToolKit


Students

Michael Bertapelli
Pritha Narayanappa
Swati Singhi
Mitchel Vlentina Dsouza
Manoj Hosabettu Rao
John Blanche
Babak Goshtasbi 
Haney Williams
Volkan Aginlar
Sarah Wannamaker
Michael Haney
Andrew McCandless
Brandon Bass
Alexandre Kovar
Christian Masson
Cyprien Huissoud
Mohamed Regaya
Romain Cornaz
Lionel Gaillard
Aayush Chandra
Marjolaine Steiner