CS 591 Seminar

Video-Based Human-Computer Interfaces

Fall 2001

Course Info - Course Objectives - Course Materials - Requirements - Reading List and Lecture Notes
Collaboration and Academic Integrity - Help - Tentative Schedule - Computer Vision Links -

Lectures: M3-5pm, W4-5pm in CAS 223
Instructor: Prof. Margrit Betke.
There are no graders or teaching fellows assigned to this course.
Class web page:
Class mailing list:
Contact Information:
Email Phone Office Hours Office
betke@cs.bu.edu   353-6412 (direct line)
  353-8919 (main office
          to leave message)
  M 2-3pm, W 1-2pm, Th 2:30-3:30pm   MCS 286

Seeing Me in My Office:
Please feel free to stop by my office anytime. My office is in MCS 286 (111 Cummington St). I am generally around every day. I may be in meetings, so the best time to reach me is during office hours. You can also make an appointment by email or by speaking with me before class (I don't have time after class, since I have to rush to another class). I'm happy to talk with you about the course, computer vision research, your plans for the future, or anything else. I hope that we will develop a good relationship as the term progresses. Check out my personal web page to get to know me a little.

Course Objectives

Our goal is to learn about computer systems that analyze images automatically, determine what the computer ``sees'' or ``recognizes,'' and thus provide new interfaces for human users.
We will read and discuss papers on video-based human-computer interfaces and maybe have some outside speakers and go for a field trip to a research lab in the area. The updated course syllabus and some handouts are made available on our course web page.
There are no formal prerequisites, but a computer vision or graphics background would be great. If you have not taken cs585 or cs480, you may want to pick up a textbook and do some extra reading (e.g., Robot Vision by BKP Horn, or Machine Vision by Jain, Kasturi, and Schunck, both books published by The MIT Press).

Course Materials

A textbook is not required. Reading materials will be handed out before lectures. If you need computer access, use the Computer Science Department's Undergraduate Lab located at 730 Commonwealth Ave, 3rd floor. Please add yourself to the course mailing list by typing csmail -a cs591a1 on your cs account. You can also use the Human-Computer Interface Laboratory at 64 Cummington St.


Class Participation: Come to class and participate regularly. Reading the assigned papers and listening in class will only give you a "passive understanding" of the material. I encourage discussions in class to help you acquire an "active understanding" of the material so that you can evaluate existing human-computer interfaces critically and learn to develop your own creative solutions.

Reading: To prepare for each class, you will be asked to read book chapters, conference articles, journal papers, and on-line publications. You can only achieve a good understanding and appreciation of the state-of-the-art of video-based human-computer interfaces if you read the assigned papers consistently and thoroughly.

Class Presentations: You will be asked to present a paper, a set of papers, or a project to the class and lead the discussion in class. You can follow the outline of the paper or choose your own. Introduce the topic of the work, explain the long-term and short-term goals, and discuss the authors' motivation. Explain the methods, algorithms, and techniques. How do they relate to previous work? You may need to discuss some additional background material. Report on the experiments and results. Are they satisfactory? What are the authors' conclusions? What are your own conclusions? Give a critical evaluation. Is this promising work? Has it been successful? What are the limitations?
See me in my office hours to discuss the paper well in advance of your presentation.

Voluntary Project: Students who enjoy programming and are interested in building video-based human-computer interfaces are encouraged to design or participate in a project. Projects are voluntary. You can substitute a research paper presentation in class with a write-up and presentation of your project. You can also use it to fullfill the project requirement in the BA/MA and MA programs. You can use the new Human-Computer Interface Laboratory in 64 Cummington Street to develop your project.

On-line Class Notes: You will be asked to prepare on-line class notes for one or two class presentations by other students. Notes taken during a Monday class are due the following Thursday in my 2:30-3:30 pm office hours. Notes taken during a Wednesday class are due the following Monday in my 2:00-3:00 pm office hours. During these office hours, I will go through the notes with you and maybe suggest changes. If you cannot come to the office hours, email me the source code before the deadline. After you have made the corrections (if needed), I will publish the notes on our course web page. Your timelyness is important. Late class notes will be levied a penalty of 20% per day (up to three days).

Exams: There will be two in-class exams on the reading materials assigned and discussed in the class. The exams will be quite easy for students who kept up with assigned readings, paper presentations, and discussions. The dates of the exams are Monday, October 15, and Wednesday, December 5. You are allowed to use one double-sided page of notes in each exam. There will be no make-up exams. There is no final exam.

Grading Policy: Your final grade will be determined roughly as follows:

Collaboration and Academic Integrity

You are encouraged to collaborate with classmates on the preparation class presentations, lecture notes, and projects. If you do, you must acknowledge your collaborators. Cheating during exams is not worthy of Boston University students. I expect you to abide by the standards of academic honesty and computer ethics policy described in http://www.bu.edu/computing/ethics/ .


CS591 is an elective seminar course that will introduce you to an exciting topic in computer science. It should be fun and not too much of a struggle for you. If you do not understand the material, ask questions in class. If one student is confused about something, then maybe others are also confused and grateful that someone asked. Also, come and see me for help or send me email.

Course Schedule

The syllabus may change depending on the time spent on different topics and whether or not new or alternative papers are discussed. Topic and paper suggestions are welcome. We will schedule a field trip after a discussion in class about possible destinations.

Dates Topics and Notes
W 9/5, M 9/10, W 9/12 Introduction. Smart Rooms. Assistive Technology for People with Severe Disabilities.
M 9/17, W 9/19, M 9/24 Tracking Faces and Expressions
Monday 9/17 is the last day to ADD classes,
W 9/26, M 10/1 Interfacing through Visual Pointers. Infrared-based Interfaces.
W 10/3, Tu 10/9, W 10/10 Face Recognition
Friday 10/5 is the last day to DROP classes (without a 'W' grade). No class on Monday 10/8 (holiday), Tuesday schedule instead.
M 10/15 Exam 1
W 10/17 Body Modeling and Tracking
M 10/22 Hidden Markov Models
W 10/24, M 10/29 Recognizing Human Action
W 10/31, M 11/5, W 11/7, W 11/14 Gesture Recognition and Interpretation
M 11/12 Field trip
M 11/19 American Sign Language
M 11/26 Audiovisual Interfaces
Thursday 11/29 is the last day to DROP classes (with a 'W').
W 11/28 Interfaces for Surgeons
M 12/3 Wearable Computers
W 12/5 Exam 2
M 12/10 No class.

Reading List

M 9/10 -- Instructor

W 9/12 -- Instructor M 9/17 -- Bill Mullally and Yannis Minadakis W 9/19 -- John Magee M 9/24 -- Evelina Prokupets and Jason Ruel W 9/26 -- Witold Stankiewicz M 10/1 -- Harrison Hong and Jonathan Lombardi W 10/3 - Instructor Tu 10/9 -- Anna Karpovsky W 10/10 -- Instructor W 10/17 -- Guest Lecturer: Romer Rosales M 10/22 -- Instructor W 10/24 Bevan Lew M 10/29 Walter Chang + Jason Peterson W 10/31 Robyn Cloud M 11/5 Chekema Prince + Seema Shah + Dan Hoeweler W 11/7 Yannis Minadakis + Instructor M 11/12 W 11/14 Stephen Crampton M 11/19 Joo-Hee Kim + George Valavanis M 11/26 - Jingbin Wang + Raymond Peng W 11/28 -- Bill Mullally M 12/3 Johanna Brewer + instructor

Computer Vision Links

Check out http://www.cs.bu.edu/faculty/betke/links.html. You will find a list of links to computer vision conferences, journals, research groups, and companies.

Margrit Betke, Assistant Professor
Computer Science Department
Boston University
111 Cummington Street ( campus map )
Boston, MA 02215
Email: betke@cs.bu.edu
URL: http://www.cs.bu.edu/faculty/betke
Phone: 617-353-6412
Fax: 617-353-6457

Last updated: November 26, 2001