|
|
|
|
Who is this for? This is a senior level undergraduate course for those interested in computer vision. It is also open to graduate students who need a solid undergraduate grounding before taking the graduate version (CS7495).
Prerequisites
· Data structures you’ll be writing code that builds representation of images, features, and geometric constructions.
· A good working knowledge of Matlab or C and C++ programming. The course will use Matlab in lecture demonstrations.
· This course has more math than many CS courses: Linear algebra, vector calculus, and linear algebra (that is not a typo).
· No prior knowledge of vision is assumed though any experience with Signal Processing is helpful
Textbooks
This is hard.
The Szeliski book is a great reference but really
more of a modern review of the state of the art methods – more appropriate for
a graduate class. Also, highly reflective of the author’s
work in Computer Vision. The Forsyth and Ponce book handles some basic
topics quite clearly but is missing whole swaths of computer vision that many
of us here at GT think is essential. There is a (legal!) on-line PDF of the Szeliski book so we will strongly recommend buying the Forsyth
and Ponce.
SZ: Richard Szeliski, Computer Vision:
Algorithms and Applications (book Web
site )
FP: Forsyth & Ponce, Computer Vision: A Modern
Approach, Pearson, 2002, ISBN 0130851981
Administrative
· T-square: The usual stuff. There is a web page under resources that points to this class web page.
· Slides: Will be posted on T-square and maybe also linked to the calendar.
· Matlab access: if you dont know how to get Matlab access, first ask a friend. Then come see Tucker
Grading
Finalizing now. The grade is mostly based on a variety of projects really more like problem sets. Currently scheduled to be 8, thought the first one (project zero – we’re so CS) is really just to make sure you can read in an image, do something to it and get some results. Projects are due Sunday at 11:59pm unless otherwise stipulated.
· Project 0: 5%
· Projects 1 – 7: 95%
Honesty
and Integrity Policy
Projects are to be
done individually but you may collaborate at the white board level help each
other with algorithms and general computation, but your code must be your own.
Last modified: 8/24/2011