Selected Topics in Computer Vision
Course Summary
The goal of Computer vision is to process images acquired with cameras
in order to produce a representation of objects in the world. Although
there already exists a number of working systems that perform parts of
this task in specialized domains, the generic "Vision Problem" is far
from being solved. No existing system can come close to emulating the
capabilities of a human.
The aim of this course is to teach the students how to reason in
rigorous manner on Computer Vision related problems. We will focus on
a particular subset and study it in depth. We will try to understand
what makes it so hard, what is the current state-of-the-art, and what
are promising directions for future research.
Course Outline
The content will vary from year to year. Initially we will address the
following topics:
- Object Detection
- 2-D and 3-D object recognition
- Automated 3-D pose estimation
- Shape from X
- Stereo and beyond
- Shape from multiple contours
- Applications
- Augmented Reality
- Body tracking