|
|
CSE 152: Introduction to Computer Vision
Spring 2011
Course Information / Course Outline / Assignments / Notes and Links
|
Recent
announcements
- (05/27/2011) Assignment 4 is posted
- (05/25/2011) Discussion section slides were posted here
- (05/23/2011) Assignment 3 due date is postponed to 05/26
- (05/16/2011) Prof. Kriegman is out of town on 5/17. Lecture will be presented by the TA
- (05/13/2011) Assignment 3 is posted
- (05/03/2011) Solution for assignment 1 is posted
- (04/23/2011) Assignment 2 is posted
-
(04/07/2011) Assignment 1 is posted
- (04/06/2011) Starting next week, we will have our regular discussion section
- (04/05/2011) Until further notice, the class will continue to meet in CSB 002
- (3/29/2011) There is no discussion section in the first week.
- (3/29/2011)
The first day of class.
Course
Information
- Lecture: Tuesday & Thursday 9:30 - 10:50 AM in CSB 002
- Discussion: Wed 1:00 - 1:50 PM in
WLH 2204
- Instructor:
Prof. David Kriegman
Office: EBU-3B, Room 4120
Phone: 858-822-2424
Email: kriegman [AT] cs.ucsd.edu
Office Hours: Tue 1:30 - 2:30 pm - TA:
Cuong Tran
Email: cutran [AT] cs.ucsd.edu
Office Hours: Thu 2:00 - 4:00 pm in EBU3b, Room B250A (CSE Building Basement)
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.
Text: Introductory Techniques for 3-D Computer Vision, E. Trucco and A. Verri, Prentice Hall, 1998. Some Algorithms and Applications, Richard Szeliski. A draft of the book, which is currently being written, is available at http://szeliski.org/Book/
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/coursepage.aspx?cid=17658&page=docs# Also hardcopies of the book will be available on 3-hour reserve.
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:
45%
Midterm:
20%
Final
Exam: 35%
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 04/07): Here is a PDF file
for Assignment 0.
Test image for assignment: flag.jpg.
Matlab tutorial
Assignment 1
(due 04/21): Here is a PDF file
for Assignment 1.
May 03)
Test HSV image: img.mat
Turn in a hard copy in class including your answer to paper-and-pencil questions as well as the printout of your code and results for programming questions. In addition, please email the TA <cutran@cs.ucsd.edu> a zip file of your code (see the Instruction section for more details).
A typo in question 3 has been corrected. The projection matrix is 3x4 not 4x3
Assignment 2
(due 05/05 05/03): Here is a
PDF file
for Assignment 2.
Test image:
can.jpg
Turn in a hard copy (in class) of your code and required results. In addition, please email the TA <cutran@cs.ucsd.edu> a zip file of your code (see the Instruction section for more details).
Assignment 3
(due 05/24 05/26): Here is a
PDF file
for Assignment 3.
Test data:
data.zip
Turn in a hard copy (in class) including your answer to paper-and-pencil questions as well as the printout of your code and results for programming questions. In addition, please email the TA <cutran@cs.ucsd.edu> a zip file of your code (see the Instruction section for more details).
A typo in question 1 is corrected. In the description part, the (-15,0,1) & (15,0,1) should be (-12,0,1) & (12,0,1)
Assignment 4
(due 06/03): Here is a
PDF file
for Assignment 4.
Faces dataset:
yaleBfaces.zip
Matlab code to read in the input images from the dataset:
getAmatrix.m. See details in the assignment on how to use
Turn in a hard copy of your code and required results. Put your hard copy in the TA's mail box (CSE Building, 2nd floor) before 5pm on the due date. In addition, please email the TA <cutran@cs.ucsd.edu> a zip file of your code (see the Instruction section for more details).
Update the format of eigenTest(), linearBasisTest(), and nineLightBasisTest(). Include the ground truth labels as inputs.
Update part 3, nine_idx = [1, 37, 43, 42, 47, 36, 41, 40, 44]. Using cosine angle distance instead of Euclidean distance.
Course
Outline
**
Tentative syllabus - subject to change.
March 29 -
Introduction to Computer Vision [T&V Chapter 1, Sz. 1-28]
March 31 -
Image Formation, Cameras, Projections and Rigid-body Transformations
[T&V
Chapter 2, pp. 26-40, Szeliski. pp. 29-58]
April 5 -
Rigid-body Transformations, Camera Calibration and Lenses [Szeliski pp.7-90]
April 7 -
Human Visual System, Cues and Illusions
April 12 -
Radiometry (Lighting and Shading) [T&V Chapter 2, pp. 16-26, Szeliski pp.60-72]
April 14 -
Color [Gonzalez
and Woods: Chapter 6, Basics
of Color, An
FAQ on Color]
April 19 -
Binary Image Processing [ Link
to Chapter 4 of "Robot Vision" by Horn (e-reserves) ]
April 21 -
Filtering [T&V,
Chapter 3, pages 55-63, Szeliski pp. 111-121]
April 26 -
Edge Detection [T&V,
pages 67-81, Szeliski pp. 238-249]
April 28 -
Hough Transform [T&V,
pp. 97-100, Szeliski pp. 250-257]
May 3 -
Generalized Hough Transform + Line Fitting
May 5 - Midterm (Sample
midterm questions)
May 10 -
Stereo (Introduction) [T&V, pp. 140-171, Szeliski pp. 533-558]
May 12 -
Stereo (Epipolar Geometry)
May 17 -
Stereo (Window-based methods + Dynamic Programming + Helmholtz)
May 19 -
Photometric Stereo [Forsyth and Ponce, Chapter 5, pages 80-86, Szeliski
pp. 580-582 ]
May 24 -
Photometric Stereo / Introduction to Structure-From-Motion (SFM)
[T&V, pages
191-198, Szeliski pp. 343-368 ]
May 26 -
Recognition (PCA, Eigenfaces and Fisherfaces)
[Szeiliski pp. 655-693, Fisherfaces paper]
May 31 -
Recognition, Bayesian Classifiers [T&V, pages 262-270]
June 2 -
Appearance-Based Recognition, Motion Field & Optical Flow
[T&V, pages
191-198, Szeliski pp. 381-415]
June 7 - 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
- Computer Vision - A
Modern Approach, Forsyth and
Ponce. A rather good, comprehensive, upper level textboook.
- 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).
- CV-Online: A useful
online compendium of Computer Vision sources.
á Some useful links
- Camera
Calibration Toolbox for Matlab (Bouguet)
- Microsoft Camera
Calibration Toolbox (Zhang)
- Intel OpenCV
- The Computer Vision
Homepage
- Handy
Math Reference: MathWorld
- Related
classes at UCSD: CSE
166, CSE 252A,
CSE 252B
Last updated March 29, 2011.