CPSC 505 Home Page

This is World Wide Web home page for UBC course CPSC 505 Image Understanding I: Image Analysis, as taught by Jim Little, 2011.

Lectures: Monday and Wednesday 1100-1230, DMP 201 (Dempster Pavillon

Instructor: Jim Little, little AT cs.ubc.ca, 2-4830

Office hours:CISR/CS 117
  1. Tue: 1pm
  2. Fri: 1pm

Final Exam: TBD


Course Description

The current UBC calendar description for the course is:

(3) Image Understanding I: Image Analysis - Image formation constraints and the processing of digital images in order to extract information about the world being imaged. Computational methods for image analysis. [3--0; 0--0].


Course Outline

We will study image formation constraints and techniques for analyzing digital images to determine information about the world being imaged. This course provides the basic tools for later research presented in CPSC 525. Understanding digital images requires a combination of physics, electronics, mathematics, and computational theory. During this course we develop the necessary tools for analysis of images and for understanding what is possible to determine from an image. We will cover topics from image formation (optics), image structures (geometry and computational theory), binocular stereo and motion (mathematics -- analysis and geometry), the relation of computational vision to human vision (psychology), and finally the computational techniques for analyzing images and recovering scene properties (signal processing and computer science).

My current intent is to follow as closely as possible, the early parts of the course text (see next). But that intention is changing daily. More certainty soon.


Course Text

The recommended textbook is Computer Vision: Algorithms and Applications by Richard Szeliski, which you can find at Computer Vision: Algorithms and Applications. The book Computer Vision: A Modern Approach by Forsyth and Ponce will also be on reserve.

Additional texts used in the course (these are all on reserve in the Reading Room):


Evaluation


The grades for the course will depend on a mixture of a number of assignments, usually one per week, plus a written comprehensive final exam. The assignments will be a mixture of problem solution and Matlab programming problems.


Sample Final Exam

The December 96 final exam is at: December 96. Dec 96 PDF

But the course has been reorganized with a new textbook since then. However the focus and tenor of the course remain the same.

Discussion about 96 final.

Discussion about 2004 final.


Course Assignments

For information about the assignments, see 505 Assignments.


Topics

Forsyth and Ponce = FP
Horn = H
Lecture note = LN

  1. Overview
    FP 1 Intro, LN intro, H 1,2
  2. Projective geometry: perspective and orthographic projection
    FP 1.1.1 + general reading of the rest of Chapter 1
    FP 2.1, 2.2 (not 2.2.3)
  3. Cameras: intrinsic and extrinsic geometry
    FP 2.1, 2.2 (not 2.2.3), H 13
  4. Images, sampling, tesselations, quantization, noise, The adequacy of digital images: bandlimited signals
    LN image, sampling, H 3, 6, 7
  5. Fitting; transform domain approaches: the Fourier transform, linear systems theory as an analysis tool
    FP 3.1.1; LN Fourier, Fourier2D, FP 7.3, H 6
  6. linear shift-invariant operations: convolution
    template matching: global templates, local templates, matched filtering
    LN Correlation, Sampling, Bandlimits, interpolation, FP 7.1, 7.2, 7.4, 7.5, 7.6, H 6, 8
  7. Linear filters; Edge detection: Physical causes of edges
    LN Edge detection
  8. Detectors: Marr-Hildreth, Laplacian of Gaussian, detection of maximum of gradient
    LN Edge detection, FP 8
  9. Filters, gradients, edges, Canny up through non-maximum suppression, hysteresis
    LN Edge detection
  10. regularization
    LN Regularization, snakes
  11. corners and SIFT
    LN features
  12. photometry, shape and images
    modeling image formation: geometry, radiometry and the image irradiance equation
    LN radiometry, FP 4.1, 4.2, 4.3.3, 4.3.4, 4.3.5, H 10
  13. BRDF, reflectance function, reflectance map
    LN shape and photometric stereo, H 10
  14. photometric stereo, interreflection
    LN shape and photometric stereo, FP 5.4, 5.5, H 10
  15. motion field and optical flow, Horn-Schunck, aperture problem, Lucas-Kanade
    LN motion, H 12
  16. multiview geometry, epipolar geometry, the fundamental matrix and essential matrix
    FP 10.1.1, 10.1.2, 10.1.4 LN Projective Geometry
  17. binocular stereo
    FP 11 (except 11.4.1), H 13


Lecture Materials (Powerpoint)

Lecture materials will be posted.


Images we may use

TIFF file for image TIFF file for image
TIFF file for image TIFF file for image TIFF file for image TIFF file for image TIFF file for image TIFF file for image


Additional Material


For help on Projective Geometry, see the postscript version of the tutorial on Projective Geometry.

And Projective Geometry by Stan Birchfield.

For help on the Fourier Transform, see the tutorial on the 1D Fourier Transform.

Some material on radiometry (courtesy Alain Fournier and Paul Lalonde) radiometry.

There is a wealth of information about Computer Vision at the Computer Vision Home Page maintained at CMU: Vision Home Page.
You can find test images, and assorted interesting demos there.


Illusions

The Perceptual Science Group at MIT has some demos at Demos.

Some cool visual illusions at Illusionworks: Illusionworks

More cool illusions: visual illusions

Even more cool illusions: more visual illusions



Materials for Vision Courses Elsewhere

I recommend David Jacobs' materials for his Computer vision course. Jacobs.
His lecture notes are nicely illustrated and well organized. For example, his notes on Image Formation provide an excellent overview of issues in image formation.

You can get the course materials for a course in Vision at Cornell at Cornell.

Course notes from another institution (mentioned in class):Notes.

Industrial Vision

Interesting Links