Computer Vision
Fall 2007
Tues/Thurs
12:30 – 2:00 pm
Parlin Hall 1 (PAR, down the
stairs from the front entrance)
CS 378, Unique # 56705 (undergrads)
CS 395T, Unique# 56850 (grads)
Instructor: Prof. Kristen Grauman
Email: grauman – put the at sign –
cs.utexas.edu
Office hours: Thurs 2:00-4:00 pm in TAY 4.118 (or by
appt)
TA : Sudheendra Vijayanarasimhan
Email:
svnaras – put the at sign -- cs.utexas.edu
Office hours : Mon 1 :00-2 :00 pm, Wed 12:00-1:00 pm in ENS 31NQ
The TA station is in the
basement of ENS inside room 31NR.
Directions to the TA stations are posted right outside the basement
elevator, and also outside room 31NR.
Announcements Overview Requirements Schedule Links Papers
This is the 2007 course website. The Fall 2008 Computer Vision
site is here.
Outline
of course topics for review.
Grad
student assignments due 12/6: submit hardcopy.
See
current reading assignments on the schedule.
Billions
of images are hosted publicly on the web---how can you find one that “looks like”
some image you are interested in? Could
we interact with a computer in richer ways than a keyboard and mouse, perhaps
with natural gestures or simply facial expressions? How can a robot identify objects in complex
environments, or navigate uncharted territory?
How can a video camera in the operating room help a surgeon plan a
procedure more safely, or assist a radiologist in more efficiently detecting a
tumor? Given some video sequence of a
scene, can we synthesize new virtual views from arbitrary viewpoints that make
a viewer feel as if they are in the movie?
Computer
vision is at the heart of many such questions: the goal is to develop methods
that enable a machine to “understand” or analyze images and videos. In this introductory computer vision course,
we will explore various fundamental topics in the area, including image
formation, feature detection, segmentation, multiple view geometry, recognition
and learning, and motion and tracking.
An outline of the syllabus is here.
This
course is cross-listed for upper-level undergraduate (CS 378) and graduate (CS
395T) students. Additional work is
required of graduate students (see below).
Basic knowledge of probability and linear algebra;
data structures, algorithms; programming experience.
Previous
experience with image processing, machine learning, and statistics will be
useful but is not required. Problem sets
will include some Matlab programming.
If you
are unsure if your background is a good match for this course, please come talk to me.
Problem sets: Problem
sets will be given approximately every two weeks, and will involve a
combination of concept questions and programming problems. The programming problems will provide
hands-on experience working with techniques covered in or related to the
lectures. Students are encouraged to
discuss the problem sets and brainstorm about solutions together, but all code
and written responses must be completed individually.
Due dates: All
problem sets are to be submitted before class on the day they are due. The instructions in each problem set will
designate which parts to submit electronically and which to submit via hard
copy.
Over
the course of the term you have an allowance of three free late days for
problem set turn-ins, meaning you can accrue up to three days in late
assignments with no penalty. Late
problem sets beyond this allowance lose 50% of the total possible credit per day
late. Please plan ahead so you can spend
your late days wisely. No late problem
sets will be accepted after solutions are given in class or posted online.
Exams: There is an
in-class midterm quiz and comprehensive final exam.
Participation: Regular attendance and participation in in-class
activities is expected. If for whatever
reason you are absent, it is your responsibility to find out what you missed
that day.
Additional requirements for graduate
students: In addition to the problem
sets and exams, graduate students will also be expected to complete one
research paper review and one problem set extension throughout the course of
the term. Details will be discussed in
class.
Grading policy: Grades will
be determined roughly as follows. For graduate
students, the additional problem set extension and paper review requirements
factor into the first component.
·
Problem sets (50%)
·
Midterm quiz (15%)
·
Final exam (20%)
·
Class
participation (15%)
Please read the UTCS code of conduct.
Midterm
exam: Tuesday Oct 9, in class
Last
class meeting: Thursday Dec 6
Final
exam: Thursday Dec 13, 9:00-12:00
The
recommended textbook is Computer Vision: A Modern Approach, by Forsyth and
Computer vision
: a modern approach, David A. Forsyth and Jean Ponce.
Computer
vision, Linda G. Shapiro and George C. Stockman.
Introductory
techniques for 3-D computer vision, Emanuele Trucco and Alessandro Verri.
Computer vision, Dana H. Ballard and Christopher M. Brown. (available online)
Multiple
view geometry in computer vision, Richard Hartley and Andrew Zisserman.
Pattern classification,
Richard O. Duda, Peter E. Hart, and David G. Stork.
Machine
learning, Tom M. Mitchell.
·
UTCS Computing
/ Facilities web page
·
OpenCV (open source computer vision library)
·
Weka
(Java data mining software)
·
Object
recognition databases (list compiled by Kevin Murphy)
·
Various
useful databases and image sources (list compiled by Alyosha
Efros)
·
Netlab
(matlab toolbox for data analysis techniques, written
by Ian Nabney and Christopher Bishop)
·
Oxford Visual Geometry
Group (contains links to data sets and feature extraction software)
·
Annotated
computer vision bibliography
·
Computer vision
research groups
·
Vision related
links on AAAI.org page
·
CS
395T Spring 2007 project ideas
·
Draft
chapters from Forsyth and Ponce book
·
Linear
algebra review / primer by Martial Hebert
·
Matlab tutorials and quick references:
Tutorial
code (from Stefan Roth)
Matlab image processing toolbox, getting started
Matlab: Getting Started (guide from Mathworks)