198:534 Computer Vision

Fall 2007

Instructor: Ahmed Elgammal -- email: elgammal - cs

Office: Core 316

Office hours: Friday 2:30-4:30pm

Regular class time: Wed 6:40-9:30pm HLL-254

Lectures’ slides and other materials are at the “…/materials.htm” web page.

Overview:

This is a basic graduate-level computer vision course that intends to cover a variety of fundamental computer vision topics to get you acquainted with the field.

Topics: [Course outlines]

Image Formation: Cameras, Geometric camera models, Calibration, Radiometry, Color.

Early Vision: Linear filters, Edge detection, Texture, Geometry of multiple views.

Mid-level Vision: Motion, Segmentation, and Tracking.

High-Level Vision: Model-based vision, Object recognition, Pose estimation.

Recommended Background:

Linear algebra and basic statistics.

Familiarity with Matlab programming

Textbook

"Computer Vision: A Modern Approach"

By David Forsyth and Jean Ponce

Prentice Hall 2002

ISBN 0-13-085198-1

Other references:

L. Shapiro, G. C. Stockman “Computer Vision”, Prentice Hall.
O. Faugeras “Three-Dimensional Computer Vision: A Geometric View Point”, MIT press.
Horn “Robot Vision”, MIT press.
D. Marr “Vision”, Freeman.

Course Load

§ Homework assignments: (70%) 4-6 assignments, which might contain some Matlab programming.

§ Exams: Midterm (30%) in the second half of the semester.

Homework assignments:

HW 1 due in class Oct 3^rd 2007.