Professors
David Fleet
(fleet@cs.toronto.edu)
Office: Pratt 391
Office hours: Thursdays, 3-4pm (or send email for appointments)
Allan Jepson
(jepson@cs.toronto.edu)
Office: Pratt 283D
Office hours: TBA (or send email for appointments)
Synopsis
Introduction to vision, visual processes, and image understanding.
Scene lighting and reflectance models. Camera system geometry and
image acquisition. The robust estimation of edges, lines, and regions.
Perceptual organization. View-based image models. Image matching and
the estimation of motion in image sequences. Multi-view geometry.
Projective and metric reconstructions. Markov random fields.
Object recognition.
The main course web site will maintain a calendar to specify when specific
topics will be covered.
Required Background
The student is also expected to be comfortable with elementary probability
and statistics, linear algebra, elementary geometry, and vector calculus
(including partial differentiation).
It is also assumed that the student is comfortable programming, and will
be expected to rapidly learn to use Matlab.
Course Texts
The majority of the course material will be provided as a collection of
course lecture notes that will be posted on the course web site each week.
There is a recommended textbook for the course:
D. Forsyth and J. Ponce, Computer Vision, A Modern Approach, Prentice Hall, 2003.
This book is not required for the course per se, but it is a
reasonable book to buy for anyone serious about vision, and it complements
the course notes.
Grading
The grading for the course will be based on assignments (worth 60%
in total), and a three (3) hour final exam (worth 40%).
Exams from previous years are available
here.
Assignments
Assignments involve both theoretical problems as well as programming
problems. The programming will be done in the well-known Matlab language.
We will arrange for you to get accounts which provide you access to Matlab.
Descriptions of the different assignments will be provided on the main course
web site as they become available.
Late Assignments:
will be penalized 10% of the available
marks per day up to a maximum of three days. Beyond this, no extensions
will be granted on homework assignments, except in extreme cases
(e.g.
medical reasons). Please plan ahead.