Overview

CS223B will introduce students to the rich field of computer vision. This graduate-level course of interest to anyone seeking to process camera images or video, or to acquire a general background in issues related to real-world perception and computational geometry.

Activities

The course involves three types of activities:

• Interactive classroom sessions, where students explore the basic mathematical foundations behind a range of popular algorithms, guided by the instructor.

• Homework assignments, which will provide an opportunity to deepen the problem solving skills acquired in class.

• An in-depth class project, through which groups of students learn to solve real-world computer vision problems.

Prerequisites

CS223B is an introductory graduate level course. Familiarity with basic statistical concepts (Bayes rule, PDFs, projective geometry, Kalman filters, continuous distributions...) and linear algebra (eigenvalues, singular value decomposition) will be extremely helpful for this course, as will be hands-on experience with software development in C or C++ and Matlab. Intro tutorials will be given into Matlab and the vision library OpenCV. But the most important prerequisite will be creativity and enthusiasm.