Multimodal Vision Research Laboratory


teaching computer vision (UK CS 636)

01 January 2011

Course Summary

The goal of computer vision is to extract properties of the world from images. In this course, we will explore aspects of this challenging problem, ranging from motion estimation to object detection and from 3D shape reconstruction to scene understanding. Students will be exposed to both classical results and cutting-edge research. The aim of this graduate course is a better understanding of algorithms and modeling techniques useful for interpreting images and videos of the natural world. Many algorithms and theoretical results will be discussed, but the emphasis will be on build working prototypes. This hands-on emphasis will be reflected in the programming assignments, in which students will develop image analysis tools and evaluate their programs on standardized datasets.


Programming experience, multivariate calculus (MA 213) and linear algebra (MA 322). Previous experience with image processing and/or computer graphics will be very helpful but is not required. Please ask the instructor if you are unsure if you have sufficient experience.