Spring 2007
CSc 83029
Topics in Computer Vision: 3-D Computer Vision
CUNY Graduate Center
Prof. Ioannis Stamos

Day/Time: Wednesdays 4:15 - 6:15

Classroom: 4421

Office hours: Wed. 12-2 (1090F Hunter North)

istamos@hunter.cuny.edu

http://www.cs.hunter.cuny.edu/~ioannis

Schedule and notes




 

                                                                                                                                                   


(Left) Mesh-based models of Thomas Hunter Building, NYC.  (Right) Texture-mapped point-based model of same building (camera locations shown).

       


Course Overview


This course will provide an introduction to the rapidly growing field of computer vision. This field deals with the analysis of images of various forms (regular color images, 3-D range images, etc.) and video. The output of vision processes provide an interpretation of the images in the form of 3-D reconstruction, or object representation. This technology has a wide variety of applications including image retrieval in digital libraries, image search, face recognition, photorealistic 3-D modeling, medical image analysis, digital cinematography, mobile robot navigation, industrial inspection, etc. A recent convergence between the fields of computer vision (inverse rendering) and computer graphics (rendering) opens new avenues of exploration.

List of topics to be covered:

  • Camera models.
  • Camera calibration.
  • Edge detection.
  • Radiometry.
  • Stereopsis.
  • Optical flow.
  • Segmentation.
  • Registration.
  • Shape from Shading.
  • Photometric Stereo.
  • 3-D images (range data).



Course Format


There will be a weekly class, with presentations by the instructor. The presentations will introduce the basic concepts and techniques of the field.  
The grade will be based upon the following: 60% for programming and theoretical assignments,  30% for final project, and 10% for class participation.


Prerequisites

Linear algebra, data structures and algorithms, and C/C++ or Java programming. No prior knowledge of vision is assumed. Courses such as image processing, computer graphics, and digital tomography are helpful but are not required for the understanding of the material.



Textbook

  • Required: Computer Vision A Modern approach.  David S. Forsyth, Jean Ponce. Prentice Hall 2003.
  • Suggested: Robot Vision. B. K. P. Horn, The MIT Press, 1998 (12th printing).
  • Other vision books:
    • Introductory Techniques for 3-D Computer Vision. EmanueleTrucco and Alessandro Verri. Prentice Hall, 1998. 
    • Three-Dimensional Computer Vision: A Geometric Viewpoint. Olivier Faugeras, The MIT Press, 1996. 
    • An Invitation to 3-D Vision. Yi Ma, Stefano Soatto, Jana Kosecka, S. Shankar Sastry. Springer-Verlag, 2004.

 

References/Links

Computer Vision sites:

Computer Vision and Graphics Journals:

International Journal on Computer Vision.
Computer Vision and Image Understanding.
IEEE Trans. on Pattern Analysis and Machine Intelligence.
SIGGRAPH (http://www.siggraph.org).