Visual Tracking
(Ho, Lee, Yang, Kriegman)

CSE 152: Introduction to Computer Vision

 

Winter 2013

 

Course Information / Course Outline / Assignments / Notes and Links

 

CSE 152 Discussion Board / GradeSource

Recent announcements

Course Information


Class Description:The goal of computer vision is to compute properties of the three-dimensional world from images and video. Problems in this field include identifying the 3D shape of a scene, determining how things are moving, and recognizing familiar people and objects. This course provides an introduction to computer vision, including such topics as feature detection, image segmentation, motion estimation, object recognition, and 3D shape reconstruction through stereo, photometric stereo, and structure from motion.

 

Required Text:      Introductory Techniques for 3-D Computer Vision, E. Trucco and A. Verri, Prentice Hall, 1998.

 

Since the text book is out of print, and the price of used copies have become outrageous, I've been able to place some of the reading from Trucco and Verri on Ereserves at http://reserves.ucsd.edu/eres/coursepass.aspx?cid=20316 . The password for this site is on Piazza, under the 'Course Info' tab. Also hardcopies of the book will be available on 3-hour reserve.

 

Optional Text:      Computer Vision: Algorithms and Applications, Richard Szeliski. An older draft of the book, is available at http://szeliski.org/Book/


Prerequisites: Linear algebra and Multivariable calculus (e.g. Math 20A & 20F), data structure/algorithms (e.g. CSE100), a good working knowledge of C, C++ or Matlab programming.

Grading: There will be homework assignments, a midterm, and a final weighted with the following percentages:
           Assignments:      55%
           Midterm:            15%
           Final Exam:        30%

Late Policy: Written homework will be due in class and accepted thereafter with a penalty of 10% per day starting from the due date. Programming assignments will have a hand-in procedure described with the assignment and also has a 10% per day late penalty. No assignments will be accepted after the graded assignments have been returned or the solutions have been released.

Assignments

Assignment 0 (due 01/17): Here is a PDF file for Assignment 0.
Test image for assignment: flag.jpg.
Matlab tutorial

 

Assignment 1 (due 01/31): Here is a PDF file for Assignment 1.
Test image for assignment: color.bmp.
renderConeDriver.m

renderCone.m

 

Assignment 2 (due 02/14): Here is a PDF file for Assignment 2.
Test images are in this folder.

 

Assignment 3 (due 03/07): Here is a PDF file for Assignment 3.
Test images are in this folder.

 

Assignment 4 (due 03/14): Here is a PDF file for Assignment 4.
The other files you need are in this folder.

 

Course Outline

** Tentative syllabus - subject to change.

January 8 - Introduction to Computer Vision, Linear Algebra Intro      [T&V   Chapter 1, Sz. 1-28]

January 10 - Human Visual System, Cues and Illusions

January 15 - Image Formation, Cameras, Projections and Rigid-body Transformations      [T&V   Chapter 2, pp. 26-40, Szeliski. pp. 29-58]

January 17 - Rigid-body Transformations, Camera Calibration and Lenses [Szeliski  pp.7-90]

January 22 - Radiometry (Lighting and Shading)      [T&V   Chapter 2, pp. 16-26, Szeliski  pp.60-72]

January 24 - Color      [Gonzalez and Woods: Chapter 6, Basics of Color, An FAQ on Color]

January 29 - Binary Image Processing      [ Link to Chapter 4 of "Robot Vision" by Horn (e-reserves) ]

January 31 - Filtering      [T&V, Chapter 3, pages 55-63, Szeliski pp. 111-121]

February 5 - Edge Detection      [T&V, pages 67-81, Szeliski pp. 238-249]

February 7 - Hough Transform      [T&V, pp. 97-100, Szeliski pp. 250-257]

February 12 - Generalized Hough Transform + Line Fitting

- February 14: Midterm (Sample midterm questions)

February 19 - Stereo (Introduction)      [T&V, pp. 140-171, Szeliski pp. 533-558]

February 21 - Stereo (Epipolar Geometry)

February 26 - Stereo (Window-based methods + Dynamic Programming + Helmholtz)

February 28 - Photometric Stereo      [Forsyth and Ponce, Chapter 5, pages 80-86, Szeliski pp. 580-582 ]

March 5 - Photometric Stereo / Introduction to Structure-From-Motion (SFM)      [T&V, pages 191-198, Szeliski pp. 343-368 ]

March 7 - Recognition (PCA, Eigenfaces and Fisherfaces)      [Szeiliski pp. 655-693, Fisherfaces paper]

March 12 - Recognition, Bayesian Classifiers      [T&V, pages 262-270]

March 14 - Appearance-Based Recognition, Motion Field & Optical Flow      [T&V, pages 191-198, Szeliski pp. 381-415]

March 19, 8am - Final Exam

Notes and Links

á  Programming languages: For this course, all programming will be in Matlab. A short tutorial assignment will provide the introduction. Click here for Serge Belongie's Matlab resource links.

á  Some other textbooks and resources

  1. Computer Vision - A Modern Approach, Forsyth and Ponce. A rather good, comprehensive, upper level textboook.
  2. An Invitation to 3D Vision: From Images to Geometric Models, Ma, Soatto, Kosecka, Sastry, Springer Verlag, 2003, ISBN 0-387-00893-4 (textbook for CSE 252B).
  3. CV-Online: A useful online compendium of Computer Vision sources.

á  Some useful links

  1. Camera Calibration Toolbox for Matlab (Bouguet)
  2. Microsoft Camera Calibration Toolbox (Zhang)
  3. Intel OpenCV
  4. The Computer Vision Homepage
  5. Handy Math Reference: MathWorld
  6. Related classes at UCSD: CSE 166, CSE 252A, CSE 252B