Computer Vision Fundamentals - Autumn 2004-05

Intructor:

 Dr Sohaib A. Khan

 sohaib at lums dot edu dot pk
 http://web.lums.edu.pk/~sohaib

 

  Instructor Office hrs: (Rm 405 Lib)
Tue 0830-0955
Thu 0830-0955
 

TA:
Mohsen Ali

http://cc.domaindlx.com/mohsenali/Index.htm

 

TA Office hrs:

Tue 1145-1300
Thu 1145-1300
Computer Vision Lab on 4th floor (near Dr Sohaib's room)

People having other engagements during my office hours shall email me.

Any one emailing me should have CS436 in their email-subject


Course Outline [PDF, 101 KB]

Useful Vision Links

Video And Image Processing Group at LUMS

Computer Vision Homepage
Compendium of Computer Vision

Visionary: A Dictionary of terminology in Vision Research
Keith Price Computer Vision Bibliography
Computer Vision Handbook

VisList: Archive of comp.ai.vision

What's New!

*Assignment 2: uploaded : Dead-Line: 3:30pm on Oct 13 Tuesday

*Computer Vision Fundamentals Forum

 * Complete Module 1 lectures available

 

Resources

*Assignment Link: assign.html

*Assignment 0: Some material that might be helpful

 

Reading Material

*Mubarak Shah's  Book "Fundamentals of Computer Vision"

(available at Photocopier and 3 Copies at Library Course Reserve)

*A comprehensive reading material is also available at the Photocopier and Library Course Reserve.

 

 


Date Lecture Content
Slides are available from \\badar\common\cs436, and are not accessible from outside LUMS.
Material in these slides (including images, data etc.) must not be used for commercial benefit without instructor's written permission.
Notes
6 Sep 2005
Monday
Lecture 1 [download]:
  • Course introduction and policies
  • Introduction of Computer Vision area
  • The complexity of high-level vision tasks
  • Human perception, and cues that aid in perception
     
  • Modules of the course
  • Image Representation
    Image coordinates
    Homogeneous coordinates
    Binary, Gray-scale and Color images
    Example operations on images
  • Image Histogram (gray-scale histogram, color histogram)

 

8 Sept 2005 Thursday Lecture 2 [6 slides per page, 2 slides per page]:
  • Image Representation
    Image coordinates
    Homogeneous coordinates
    Binary, Gray-scale and Color images
    Example operations on images
  • Image Histogram (gray-scale histogram, color histogram)
  • Cameras
    Aperture
    Shutter speed
    Digital cameras
    Video cameras
    Interlacing, progressive scan
    Human eye
  • Portable Bit Map Formats
    PGM, PPM file formats
    Reading/Writing binary pgm/ppm files
  • Transformations
    Example Application: Image Registration
  • Transformations in 2D
    Scaling
    Rotation
    Translation
    Shear in x- and y-direction

 

Assignment 0 (no credit)
Write functions ReadBinPGM, ReadBinPPM, WriteBinPGM, WriteBinPPM in C/C++

 

Example PPM/PGM Files:

mecca06.pgm, mecca06.ppm, owl.pgm, owl.ppm

(Owl is taken from Dr Soahib's http://web.lums.edu.pk/~sohaib/photographs/birds/index.htm )

 

One of the good viewer is Irfanview. Download from http://www.irfanview.com/ or Locally

(You can convert images from other formats to the pgm or ppm format by opening them in Irfanview and then saving in the desired format)

Format specification:
[pbm.txt][pgm.txt][ppm.txt]
[Thanks to Numan Sheikh for sending us. See www.wotsit.org for these and more format specs]

Reading

Shah's Book: Section 1.1, 1.2, 1.3

 

13 Sept 2005 Tuesday  Lecture 3 [6 slides per page, 2 slides per page]:
  • Transformations
  • Inverse transformations
  • Concatenation of transformations
    Rotation about arbitrary point
    Importance of order
  • Affine Transformation
  • Rigid Body Transformation
  • Recovering the best affine transformation from correspondences
    Least Squared Error solution
    Pseudo Inverse
  • 2D Displacement Models
  • Projective Transformation

Reading:

 

 Steve Mann's paper on video orbits [web] [local] contains a nice introduction to these transformations (see sections I and II of this paper)

15 Sept 2005 Thursday Lecture 4 [6 slides per page, 2 slides per page]:
  • 2D Displacement models
  • Other Displacement Models

    Bi-quadratic

    Bilinear

    Pseudo-perspective

  • 2D Affine Warping
    Bilinear Interpolation
  • Assignment 1: Basic Task

 

 

Assignment 1: Full Text uploaded
Due: 27 Sept 2005, Tuesday, 17:00

Reading: Shah 1.1-1.3

Look at the problems of the Dr Shah's Book Chapter 1

 

till 6th Oct.2005 Lecture 5,6 and 7

[ 8 slides per page , 4 slides per page]:

Rest of Module 1 

[6 slides per page, 2 slides per page]:

  • 3D Translation and Scaling
  • 3D Rotation
    Rotations about principal axes
    Small angle approximation
    Rotation about arbitrary axis
  • Rodrigues' Formula
  • Eigenvalues and Eigenvectors of Rotation Matrix
  • Frames of Reference
  • Pinhole Camera
  • Perspective Transform
  • Camera Models
  • Orthographic Projection
  • Interpretation of Projective and Affine Projections
  • Camera Calibration
  • Stereo (introduction)
  • Concept of Disparity
    Epipolar Constraint
    Basic Stereo Derivations
    Results
Assignment 2 : Problems, Module 1 [handout]

You will find the related topics in the reading material.

Have a look at the Exercises of Chapter 1 (Dr.Shah)

"Computer Vision A Modern Approach" has more rigorous material on the Stereo