ECSE 6650 Computer Vision

Instructor: Dr. Qiang Ji,
Phone: 276-6440
Office: JEC 7004
Meeting Hours & Place : 12:30-1:50 pm, Tues and Fridays, Vorhes South
Office Hours:    Tues and Fridays 2:00pm - 3:00pm pm   or by Appointment
Lecture notes:

This course deals with the science and engineering of computer vision,
that is, the analysis of patterns in visual images of a 3D scene with the
goal of interpreting, understanding, and reconstructing the 3D scene.
The emphasis is on physical, mathematical, geometric and information processing aspects of vision.  Topics to be covered include image formation and representation, feature extraction, camera calibration, image noise representation and propagation, stereo vision, projective geometry, 3D reconstruction, structure from motion, tracking, and analytical performance characterization. In addition, the course will cover applications of computer vision techniques for face detection and recognition, facial feature tracking, eye tracking, facial expression understanding, and medical image segmentatation.  This course will be very useful for students interested in human computer interaction, robotics, photogrammetry, remote sensing, and medical imaging.

Prerequisites: A good background in linear algebra, statistics, programming in C++, and/or MATLAB

Required Text: Introductory Techniques for 3D Computer Vision Approach, Emanuele Trucco & Alessandro Verri.

The textbook is supplemented by frequent handouts and the materials from the following books.

Recommended Texts:

Three-Dimensional Computer Vision-a geometric viewpoint, Oliver
Faugeras, The MIT Press, 1993.

Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman, Cambridge, 2001.

Computer and Robot Vision, Robert M. Haralick and Linda G. Shapiro, Volumes 1 and 2, Addison-Wesley Publishing Company, 1993.

Method of Evaluation:
   Grading will be based on homework assignments, projects, a middle-term
exam, and the final project. There will be 4-5 projects, several assignments,
and a final project. The grade distribution is as follows:

Assignments: 15%
Projects: 50%
Midterm Exam: 20%
Final Project: 15%

Lecture Notes

Previous Projects