Computer Vision I


Tuesday, Thursday 12:30-1:50

HSS, Rm. 1128A


Class mailing list: cse252a at graphics.ucsd.edu

        Class web board: http://cse-gsa.ucsd.edu/forum/viewforum.php?f=11






1/4/05: Subscribe to class mailing list at http://graphics.ucsd.edu/mailman/listinfo/cse252a

1/5/05: Excellent review slides by Tim Marks on linear algebra and random variables are available.

      1/12/05: Web board set up by Eric Weigle at http://cse-gsa.ucsd.edu/forum/viewforum.php?f=11

            1/20/05: lec5b slides updated to clear up typos & notation\

            1/27/05: Posted Illumination cone slides in color and with white background.  Note that some info is lost with white background.



Instructor: David Kriegman

Office: AP&M 3101

Phone: (858) 822-2424

Email: kriegman at cs.ucsd.edu

Office Hours:    Wednesday 1:30-3:00


Class Description: Comprehensive introduction to computer vision providing broad coverage including low level vision (image formation, photometry, color, image feature detection), inferring 3D properties from images (shape-from-shading, stereo vision, motion interpretation) and object recognition. 

A companion course, CSE252B, Computer Vision II is taught in the spring quarter. 4 units.


Required Text: “Computer vision: A Modern Approach,” David A. Forsyth, Jean Ponce, Prentice Hall, ISBN: 0130851981


Prerequisites: Linear algebra and Multivariable calculus (e.g., Math 20A & 20F), programming, data structure/algorithms (e.g., CSE100).  Probability can also be useful.


Programming: Assignments will include both written problem sets and programming assignments in Matlab.  Students can either purchase the Matlab student edition or use copies available on University machines such as are available in the APE Lab.



            Assignments:     60%

            Final Exam:       40%


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. 




Homework 0: Getting Started with Matlab, Due Thursday, 1/13/05

Homework 1: Photometry & Cameras

Homework 2: Constructing an image mosaic

            Test Images: piscine1.gif, piscine2.gif,  piscine3.gif, piscine4.gif,  piscine5.gif

Homework 3: Corner detection

            Test Images: image1.pgm, piscine1.pgm

Homework 4: Stereo, Due Tuesday 3/2/04.  Test images are at: http://www.ijrr.org/contents/20_07/abstract/banks/1196-1.html

 See also the paper ``A Maximum Likelihood Stereo Algorithm’’, by Cox, Hingorani, Rao, and Maggs,



[ Note that this Syllabus is tentative & subject to change]





Link to lecture notes




Jan. 4

Linear algebra review

Random variables review

Intro to Computer Vision


Jan. 6

Human Visual System, F&P sec. 1.3


Jan. 11

Rigid Transformatoins SE(3), SO(3), Camera & Lenses, F&P Sec. 2.1, F&P Chap. 1


Jan. 13

Perspective, Affine, orthographic projection, F&P 2.2, 2.3


Jan. 18


Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4


Jan. 20

Special BRDF’s, Light Sources, Photometric Stereo, F&P, 5.2-5.4


Jan. 25

Photometric stereo


Jan. 27



Illumination Cones, Belhumeur, Kriegman, What Is the Set of Images of an Object under All Possible Illumination Conditions?,  IJCV 28(3), 1998, 245-260


Feb. 1

Filtering, F&P Chap. 7,



Feb. 3


Filtering, start Edge detection, (Canny) F&P  Chap. 8


Feb. 8

Color; F&P, Chap. 6  Some on-line sources include: Basics of Color, A FAQ on Color


Feb. 10

Epipolar Constraint and Stereo I, F&P Sec. 10.1


Feb. 15

Stereo II, Dynamic Programming, Chapter 11


Feb. 17

Optical Flow, Trucco and Verri , pp. 178-194


Feb. 22

Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211


Feb. 24

Tracking, F&P Chap.17


Mar. 1

Statistical Pattern Recognition, F&P 22.1-22.3


Mar. 3

Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8


Mar. 8

Appearance-based Recognition, Eigenface, Fisherface, Appearance Manifolds


Mar. 10

Model-based recognition, F&P Chap. 18



Notes and links


Programming languages: 

The primary language will be Matlab. . Click here for Serge Belongie’s  Matlab resource links.


Other excellent textbooks:

·  Introductory Techniques for 3-D Computer Vision, Trucco and Verri (textbook for CSE152)

·  An Invitation to 3D Vision: From Images to Geometric Models, Ma, Soatto, Kosecka and Sastry,  Springer Verlag, 2003, ISBN 0-387-00893-4 (textbook for CSE252B)


Some useful links:

·  Camera Calibration Toolbox for Matlab (Bouguet)

·  Microsoft Camera Calibration Code (Zhang)

·  Intel OpenCV

·  CVonline

·  The Computer Vision Home Page

·  Handy Math reference:   MathWorld

·  Related classes at UCSD: CSE 190-B, CSE 166, CSE 252B

· Some other useful vision links