Syllabus

 

CS 7495

Graduate Computer Vision


Fall 2011

Klaus 1456

Tue-Th 4:35pm - 5:55pm


Coordinator Frank Dellaert

TA:              Duy-Nguyen Ta

Taught by:   Aaron Bobick, Tucker Balch, Frank Dellaert,

                    Irfan Essa, Jim Rehg, Grant Schindler


Prerequisites

This is a graduate class. Having taken an introductory machine vision or computer vision class will help, but we expect graduate students to do well without this. Rather, you will be asked to review or self-study the basic material prior to each module (see below). More essential is good math skills, esp. linear algebra.


Communication about the class:

All communication from the teaching staff will be done through T-square. Please read all announcements and email promptly. If you want to email an instructor, please use “CS7495” in the subject line.


Class Goals

The desired learning outcomes for the students are:


  1. Foundation: Having a strong foundation in computer vision techniques

  2. Skills: Being able to propose, evaluate, and implement solutions to computer vision problems

  3. Integration: Being able to bring in/suggest the use of signal processing, AI, machine learning where needed

  4. Self-Assessment: Exposure to different flavors of problems and solutions


Text

The textbook we will be using is

  1. -Computer Vision: A Modern Approach. David Forsyth and Jean Ponce. Prentice Hall.


Two other good books that might come in handy are

  1. -Multiple View Geometry in Computer Vision, by Richard Hartley and Andrew Zisserman. Cambridge University Press.

  2. -Computer Vision: Algorithms and Applications, by Richard Szeliski at Microsoft Research.


Structure and Sequence of Class Activities

This course is probably different from many other courses you have taken at Georgia Tech, in that it does not follow the usual lectures/midterm/final pattern. Instead, while there are also conventional lectures, the course is different in two major aspects:


  1. 1)You are expected to review or study the foundational material outside class time. You will be asked to (re-)read the chapters in the textbook before the start of each module, as indicated on the schedule. Reading textbook material can be tedious, but it is necessary for you to acquire this foundation. To motivate you (and at the same time reward you with a grade for your hard work) an assignment based on this reading material is due the day we start with the in-depth discussions needing those foundational chapters.


  1. 2)The lectures will be reserved for advanced topics and active learning activities. Research has shown that students are happier and retain material better if they participate actively in the learning rather than simply taking notes in lectures. In this course, in particular, we built in three mini-projects described here that will have substantial in-class activities associated with them. In particular, on the due date of each project proposal, we will assemble review panels in class to review and give feedback on each proposal. On the due date of the project paper, we will similarly form mini area chair meetings in which the best papers are singled out for presentation in class.


Out-of-class Work

There are several activities designed to achieve the learning outcomes above:


  1. Foundation: there will be 6 assignments on foundational material, due at the beginning of each module. The assignments are more frequent in the beginning of the course, and tail off towards the project-based part (see below).

  2. Skills: There are three mini-projects in which you will choose, propose and research a problem that you might encounter in your future career (be it in academia, industry, or government), propose a solution, implement it, and describe it in a mini-conference paper. Projects should be done in teams of 2 to 3 students. Details here.

  3. Integration: The second mini-project is expected to be larger in scope and include a non-trivial AI or machine learning component, or has to be implemented on a robotics platform.

  4. Self-Assessment: instead of a final, you will prepare a learning portfolio in which you discuss what you have learned throughout the course, where you describe your activities, findings, how you did, and what impact it had on you.


There is a page with more details about the projects, including grading criteria and standards.


Schedule

A detailed schedule, subject to change, can be found on the schedule page.


Collaboration Policy

Collaboration on assignments is encouraged at the "white board interaction" level. That is, share ideas and technical conversation, but write your own code. Students are expected to abide by the Georgia Tech Honor Code. Honest and ethical behavior is expected at all times. All incidents of suspected dishonesty will be reported to and handled by the office of student affairs.


Grading

  1. Class Participation: 10%

  2. Foundation: Assignments 30%

  3. Skills: Mini-Projects 1 and 3: 30%

  4. Integration: Second Mini-Project: 20%

  5. Self-Assessment: Learning Portfolio 10%