COMP-558 Fall 2008-2009: Fundamentals of Computer Vision

Schedule

Instructor: Kaleem Siddiqi
Schedule: Tuesday/Thursday, 16:05 pm. - 17:25 pm.
Class Room: ENGTR 0060
Office: ENGMC 420
Office Hrs: Thursday, 9:00 am. - 10:00 am. (or by appt.)
E-mail: siddiqi "at" cim "dot" mcgill "dot" ca
TA: Maxime Boucher
Office Hrs: W: 1:00 pm. - 3:00 pm, TR 3106.
E-mail: maxime.boucher "at" mcgill "dot" ca
Maxime's COMP 558 web page .

Overview

Computer vision involves the development of machine algorithms which have the potential to mimic a biological organism's ability to ``see''. Though the sense of vision is immediate for most people, the complexity of the task that the human visual system accomplishes is enormous. In general, the inference of properties of the three-dimensional world from two-dimensional images is very challenging.

Nevertheless, this has been a rich area for investigation for the past several years. To date the field has advanced to the point where a core of algorithms and techniques have been developed for specific visual tasks in constrained settings, with a solid mathematical foundation. Several international research laboratories now exist and applications of computer vision techniques in industry, robotics, and bio-medicine abound. This course seeks to present the fundamentals of computer vision at an advanced undergraduate/beginning graduate level.

The mathematical background for the course includes calculus and linear algebra. Fundamentals of other areas, such as linear systems and partial differential equations, will be covered as necessary. It will also be assumed that students have practical experience with programming in a Unix environment using C, as well as a solid theoretical grasp of computer science algorithms and data structures. This computer science background will be necessary to carry out assignments and projects which involve the design and implementation of computer vision techniques.


Calendar


News

  • Assignment 1 is posted here . Please visit Maxime's COMP 558 web page for updates and answers to questions.
  • Please note that there is NO CLASS on thursday Sept 18th. I will be in my office though that day for office hours.
  • There are 3 typographical errors in Assign 1 (thanks to Anqi for pointing this out): 1e) g(x) should be f(x), 2d) l_8 should be l_2, 2e) |l^_8|^2 should be |l^_2|^2. Please download assign1.pdf again, since the most recent version fixes these problems.
  • Assignment 2 is posted here . Please visit Maxime's COMP 558 web page for updates and answers to questions.
  • Assignment 3 is posted here . Please visit Maxime's COMP 558 web page for updates and answers to questions.
  • The due date for Assign 3 has been extended to Monday Nov. 24th, but, I'll accept assignments turned in by 6pm Tuesday Nov 25th. (Spread the word about the extension).

  • Content

    The course will cover a number of topics ranging from low level to high level vision, with a focus on both the mathematical formulation of vision tasks, and the development and implementation of algorithms to solve them. Lecture topics, subject to revision, are listed below.
  • biological vision and early vision
  • linear systems and convolution
  • image formation and features
  • projective geometry and camera modeling
  • shape from shading and texture
  • stereo vision
  • motion analysis and optical flow
  • object representation and recognition
  • pdes, level set and variational methods

  • Student prepared course notes

    The following is a list of student prepared course notes, summarizing aspects of the material presented in class, or in reference material and texts. It is provided here, in uneditted form.
  • Biological Vision (pdf) James Yap
  • Biological Vision (pdf) Louis Simard
  • Linear Systems and Convolution (pdf) Simon Wong
  • Shape From Shading (pdf) Craig Jerusalim
  • Shape From Shading (pdf) Mani Ghasemlou
  • Stereo (pdf) Andrew Chang
  • Stereo (pdf) Daniel Scheidig
  • Optical Flow (pdf) Irina Kezele
  • Motion (doc.gz) (pdf) Karl Nyberg
  • Motion (html) Malvika Rao
  • Object Representation (pdf) Olivier Dubois
  • Recognition (pdf) Mathieu Lamarre

  • Useful Links

  • The Computer Vision Home Page
  • Annotated Computer Vision Bibliography
  • CVonline Compendium of Computer Vision

  • Prerequisites

  • 189-222 (Calculus III)
  • 189-223 (Linear Algebra)
  • COMP-206 (Programming Techniques)
  • COMP-360 (Algorithm Design Techniques)

  • Text Books

  • Introductory Techniques for 3D Computer Vision'', by Emanuele Trucco and Alessandro Verri, Prentice-Hall, 1998. REQUIRED
  • ``Three-Dimensional Computer Vision: A Geometric Viewpoint'', by Olivier Faugeras, MIT Press, 1996. RECOMMENDED
  • ``Robot Vision'', by Berthold Horn, MIT Press/McGraw-Hill, 1986. ON RESERVE
  • ``A Guided Tour of Computer Vision'', by V. Nalwa, Addison-Wesley, 1993. ON RESERVE
  • ``Computer Vision: A Modern Approach'', by David Forsyth and Jean Ponce, 2003. ON RESERVE

  • Evaluation

  • Assignments: 40%
  • Course Project: 30%
  • Mid-term Examination: 30%
  •        Student Guide to Avoid Plagiarism


    Sample past Student Projects

    The following are links to some of the final projects from a previous year, in cases students made their presentations or material available over the web.
  • Vision-Based Object Tracking. Daniel Scheidig
  • Marr & Poggio's Cooperative Stereopsis (ps.gz). Mani Ghasemlou
  • Automatic Camera Tracking From An Uncalibrated Motion Sequence. Toulouse de Margerie
  • The Perception of Apparent Motion. Craig Jerusalim