Forensic Video Analysis
or
Who Shot JFK?
Fall 2010
CS0296 S04, Wednesday 3:00- 5:20 PM (N Hour), location CIT 506
Professor: Michael J. Black
Office hours, CIT 521: Mondays 11-12 and Fridays 1-2
If you are taking the class but are not on the mailing list, please let me know.
Note that there is now information about the grading policy on this site.
This is the third installment of the forensic video analysis course. In previous years we worked on an on-going murder investigation. This year we'll work on a much older and more famous case.
As in the past the video of the murder will be used to motivate and study of advanced topics in computer vision and image processing. In particular we will study
Motion deblurring
Video mosacing
Video stabilization
Tracking
3D camera tracking
Photogrammetry
Denoising
SuperresolutionA novel aspect of this course is that it will be done in cooperation with the director Robert Stone and the National Geographic Society. They will be supporting the class and providing us with data that nobody has ever had before. This is a rare opporunity.
Students will have the option of particiapting in the documentary or not. Given the potential for media attention and the sensitivity of the topics, students should consider this decision carefully. Participating in the class of course implies no obligation to be part of the documentary.
A computer vision course, e.g. CS143 (Introduction to Computer Vision) or an equivalent course.I'll assume good familiarity with linear algebra, calculus, probability, statistics, (e.g. CS155, AM0040, AM165, AM169, or AM264).
You need a background in vision to be part of this. If you want to be part of the course, email me explaining why you have the background and want to particpate.
Michael Black
Office: CIT 521
Email: black<at>cs<dot>brown<dot>edu
Office Hours: by appointment
There will be few if any formal lectures by me. This is a project-oriented coures that will be both open-ended and messy. It will resemble research more than a traditional classroom environment. It may be highly collaborative. You will be responsible for reading recent papers on vision, implementing the methods, testing them on video sequences, analyzing the results, and making presentations in class.
Class participation will be critical and part of the grade.
Participation 10%.
Assignment 1 10% (analysis of conspriacy theories)
Assignment 2 10% (class presentation)
Assignment 3 10% (deblurring)
Assignment 4 10% (project proposal and presentation)
Project 50% (includes presentations, writeup, experiments, etc.)