Computer Vision I


Tuesday, Thursday 12:30-1:50

Center Hall, Rm. 208


Class mailing list: cse252a at  graphics.ucsd.edu

Class web board: http://www.etalonsoft.com/cse252a/






          3/2/04: HW4 posted, due 3/12/04

          2/19/04: HW3 due date changed to 3/2/04

          2/18/04: HW 3 posted, due 2/26/04

          2/3/04: HW 2 posted, due 2/12/04      

          1/29/04: Class web board set up by Louka.

          1/22/04: Homework 1 posted, due 2/4/04

          1/7/04: Course number has now officially changed from CSE29-A00 to CSE252A!!  Make sure you’re enrolled for the






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. 

Note that this course will be renamed CSE252A in the future, and a companion course,

CSE252B, Computer Vision II will be introduced 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)


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 Tuesday, 1/20/04

Homework 1: Photometric Stereo, Due Tuesday 2/4/04

Homework 2: Radiometry and Cameras, Due Thursday 2/12/04

Homework 3: Stereo, Due Tuesday 3/2/04.  Test images: RDSL.jpg, RDSR.jpg,, T3bw.jpg, T4bw.jpg  See also the paper ``A Maximum Likelihood Stereo Algorithm’’, by Cox, Hingorani, Rao, and Maggs,

Homework 4: Face Recognition, Due Friday 3/12/04





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





Link to lecture notes




Jan. 6

Intro to Computer Vision


Jan. 8

Human Visual System, F&P sec. 1.3


Jan. 13

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


Jan. 15

Part 2

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


Jan. 20

Part 2

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


Jan. 22

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


Jan. 27

Part 2

Photometric stereo


Jan. 29

Part 2

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. 3

Filtering, F&P Chap. 7, Corner detection



Feb. 5

Edge detection, (Canny) F&P  Chap. 8


Feb. 10

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


Feb. 12

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


Feb. 17

Stereo II, Dynamic Programming, Chapter 11


Feb. 19

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


Feb. 24

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


Feb. 26

Tracking, F&P Chap.17


Mar. 2

Statistical Pattern Recognition, F&P 22.1-22.3


Mar. 4

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


Mar. 9

Appearance-based Recognition, Eigenface, Fisherface, Appearance Manifolds


Mar. 11

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.


Another excellent textbook: Introductory Techniques for 3-D Computer Vision Trucco and Verri


 CV-oneline: A useful on-line compendium of Computer Vision sources



Handy Math reference:   MathWorld

Some other useful vision links