198:534 Computer Vision

Spring 2015

Instructor: Ahmed Elgammal -- email: elgammal - cs

Office: Core 316

Office hours: Friday noon-1pm

Regular class time: Monday 1:40-4:40pm CBIM 22

CBIM is located: http://rumaps.rutgers.edu/location/cbim-modular-building

Class TA: Polina Yanovich – email yanovich as cs.rutgers.edu

TA office hours: Tuesday 10:30am-11:30am at Hill 266

Detailed Syllabus

Lectures’ slides and other materials

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:

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

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

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

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

Recommended Background:

Linear algebra and basic statistics.

Familiarity with Matlab programming

Textbooks

Most of the topics of the class are covered comprehensively in the following two textbooks

"Computer Vision: A Modern Approach" - Second Edition

By David Forsyth and Jean Ponce

Prentice Hall 2012

“Computer Vision Algorithms and Application”

By Richard Szeliski

Springer 2010

http://szeliski.org/Book/

Other references:

• G. Medioni, S.B. Kang “Emerging Topics in Computer Vision”, Prentice Hall
• L. Shapiro, G. C. Stockman “Computer Vision”, Prentice Hall.
• Y. Ma, S. Soatto, J. Koseca, S. S. Sastry “An Invitation to 3D Vision, From Images to Geometric Models” Springer
• 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: (60%) 4 assignments, which contain Matlab programming.

§ Quizzes (15%)

• Exams: Midterm (25%)