Welcome to CS296-4!
This course will cover current topics in computer vision with an emphasis on motion estimation, learning methods, and probabilistic models. Readings will be from recent research papers. Computational techniques such as Expectation-Maximization, Hidden Markov Models, and Belief Propagation will be introduced. Applications to tracking, recognition, image enhancement, and human motion analysis will be considered. Prerequisites: basic probability, linear algebra, and calculus.
Each year this course will focus on a different area of computer vision. This year we focus on a very real problem - solving a murder. If you know about the previous version of this class (Spring '06), the murder remains the same as the suspect is still at large. The problem however this year is different. The focus will be on recovering a high-resolution mug shot of the suspect from a low-resolution video sequence. The entire class will be focused on this one problem. To solve it will require learning about many current problems in vision and graphics including but not limited to:
- 3D face modeling
- super-resolution
- tracking
- optical flow
- camera calibration, radial distortion
- lighting and illumination
- skin modeling
I believe this is doable and I believe we can produce evidence to help the police solve this case. Regardless, we'll all learn something.l
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).
Michael Black
Office: CIT 521
Email: black<at>cs<dot>brown<dot>edu
Office Hours: Thursday 2:00-3:00 and Friday: 11:00-12:00.
This is not a "normal" class. It will be messy and hard. There will be no lecture, textbooks, toy assignments, etc. The goal is to solve a real problem that people care deeply about. We have the full support of the Henrico Co. police in this effort. The problem we are trying to solve is new and we may fail. My role is to lead us all through this process to hopefully a successful outcome.Participation (10%) – absolutely necessary. If you don’t come to meetings you won’t get anything out of this course.
Paper presentations (20%) – We'll read a lot of papers. Everyone will present several papers and must be prepared to discuss the others.
Paper summaries (10%) – everyone must email me a paragraph describing each reading and point out at least one problem with it.
Project (60%) – This will be broken into pieces and I will give you bits and pieces of the solution. There is no one right answer or approach. Everyone will present their methods in class as they are developed.
You may use any materials you can find (e.g. code from the web) and you may talk with anyone in the class. You must do your own work (e.g. programming and experimentation) but I encourage you to talk with and learn from each other. You may also seek help from outside the class but you must ask permission before sharing the data. I expect you must uphold the highest standards of scientific conduct which includes the proper assignment of credit.