G22.2271-001, Computer Vision,
Davi Geiger,
Graduate Division, Computer Science


 

Classes: Thursday, 5pm-7pm.
Class Room: WWH102.
Instructor
Davi Geiger, geiger@cs.nyu.edu
Office: 715 Broadway, 714.
Phone: +1 (212) 998-3235
Office Hours: Thursday 2pm-4pm.

Course Description

This course will look at basic ideas on Computer Vision and how they work. Students will be encouraged to understand well the material as well as develop software that works on images. The course will cover basic Image Processing tools (convolution, filtering, and multiscale representation of images), Edge detection, Contour Detection/Segmentation, Skeletonization, Stereo Vision, Motion (Optial Flow and 3D Structure), Shape From Shading and Color, Recognition.

Evaluation Process

There will be homeworks, about every two weeks, with programming assignments and written assignments. The student will have a choice of having a more experimental experience (more programming) or a more teoretical experience (more written homeworks).
There will be a course project, starting at the beginning of the course (by the third lecture it starts). There will be a choice of different projects. The project will "substitute the exams".

Books

Introductory Techniques for 3-D Computer Vision.
Emanuele Trucco and Alessandro Verri.
Publisher: Prentice Hall.

Complement (not required)

Wavelet Tour of Signal Processing.
Stephane Mallat.
Publisher: Academic Press (2nd Edition is coming).

Syllabus

Class 1: Introduction

Class 2: Convolution (invited Lecture: Prof. Jack Schwartz)

Reading
  • S. Mallat, Wavelet Tour of Signal Processing. Chapter 2.

    Class 3: Derivatives and Edge detection. Problem set 1. 2 pages postscript .

    Class 4: Edge Grouping and Dynamic Programming. Course Material. 3 pages word document .

    Class 5: Stereo Vision: Camera Calibration and Epipolar Geometry. Problem Set 2 and Project Suggestion. 1 page word document .

    Class 6: Stereo Vision: Cooperative Stereo.

    Class 7: Optical Flow and the Aperture Problem.

    Class 8: Contour grouping revisited (Projects) 6 pages postscript .

    Class 9: Motion.

    Under construction. Please see instructor for more details regarding this course