Overview

Description

CALENDAR DESCRIPTION:

Computational approaches to image understanding will be discussed in relation to theories about the operation of the human visual system and with respect to practical applications in robotics. Topics will include edge detection, shape from shading, stereopsis, optical flow, Fourier methods, gradient space, three-dimensional object representation and constraint satisfaction.

COURSE DETAILS:

Computational vision addresses the problem of programming computers to "see", recognize objects, navigate through space and so on. It is easy to capture digital images and videos, but how can the image data be used? The course provides an introduction to computer vision, but note that it's only a one-semester introduction---students will not suddenly become experts in this rapidly evolving field. Computer vision has many connections to machine learning, computer graphics, and multimedia, so some of the techniques covered in this course are relevant to those fields as well. The course also introduces related mathematical techniques, which are useful in many other fields besides computer vision.
Although the only math prerequisite for the course is Math 152, computer vision is quite a mathematical field, so it will help if you generally feel comfortable with mathematical approaches to problems.
Note that, unfortunately, there is no textbook that directly matches the material covered in this course. This means that it's very important to attend almost all lectures (even if you find them boring). If you have a job or some other reason that will prevent you from attending the vast majority of classes you'll find it very hard to do well in the course.
For additional information please see http://www.cs.sfu.ca/~funt/

Topics

• Surface reflectance and illumination models.
• Colour perception.
• Motion and optical flow.
• Fundamentals of 2D Fourier transforms.
• Image enhancement.
• Object recognition.
• Binocular vision.
• Machine learning applied to computer vision

Grading

Materials

MATERIALS + SUPPLIES:

• Computer Vision: A Modern Approach, 2nd Edition, David Forsyth & Jean Ponce, Prentice Hall, 2002, 9780136085928
• Robot Vision, B.K.P. Horn, MIT Press, 1988, 9780262081597
• Digital Image Processing Using MATLAB , Gonzalez, Woods, and Eddins, Prentice Hall , 2004, 9780130085191
• Digital Image Processing 3rd Edition, Gonzalez and Woods, Prentice Hall, 2008, 9780131687288
• Computer Vision Models, Learning and Inference, Simon J. D. Prince, Cambridge University Press, 2012, 9781107011793
• Computer Vision: Algorithms and Applications, Richard Szeliski,, Springer, 2011, 9781848829343, (Note it's downloadable as PDF from: http://szeliski.org/Book/drafts/SzeliskiBook_20100903_draft.pdf )