Computer Vision I

Tuesday, Thursday 3:30-4:50
Sequoyah Hall, Room 148

Class Mailing List: UCSD Listserve cse252a-l
Class Web Board: QuickTopic


03/08: Homework 4 is now posted.
02/23: Homework 3 posted. See below.
02/07: The homework 2 due date has been extended to Tuesday, Feb. 14th
02/01: Homework 2 is now posted. Due Feb. 9th.
01/27: Additional office hour for Neil next week only: Monday 1-2pm.
01/11: Homework 0 has been posted. See below.
01/10: The course mailing list has been set up. To subscribe, send an email to listserver@ucsd.edu with the body "ADD < email-address > cse252a-l".
01/10: The course discussion board has been set up.
01/09: Class meeting time and room has been changed to Tu,Th 3:30-4:50, Sequoyah Hall Room 148. This may not be reflected on tritonlink.
Instructor: David Kriegman
Office: EBU3B, Room 4120
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours: Wed. 1:00-2:30

TA: Neil Alldrin
Email: nalldrin at cs.ucsd.edu
Office Hours: Tue. 11:00-11:50, CSE B240A

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
Homework 1: Photometry and Cameras
Homework 2: Photometric Stereo and Specularity Removal
Homework 3: Binocular Stereo Homework 4: Optical Flow


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

Week Date / Link to lecture notes Topic / Readings
1 Jan. 10
Linear algebra review
Random variables review
Intro to Computer Vision
Jan. 12 Human Visual System, F&P sec. 1.3
2 Jan. 17 Rigid Transformatoins SE(3), SO(3), Camera & Lenses, F&P Sec. 2.1, F&P Chap. 1
Jan. 19 Perspective, Affine, orthographic projection, F&P 2.2, 2.3
3 Jan. 24
Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4
Jan. 26 Special BRDF's, Light Sources, Photometric Stereo, F&P, 5.2-5.4
4 Jan. 31 Photometric stereo
Feb. 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
5 Feb. 7
Part b
Color; F&P, Chap. 6 Some on-line sources include: Basics of Color, A FAQ on Color
Feb. 9 Color, Dichromatic model
6 Feb. 14
Filtering F&P Chap. 7, 8
Feb. 16 Edges
7 Feb. 21 Epipolar Constraint and Stereo I, F&P Sec. 10.1Stereo II, Dynamic Programming, Chapter 11
Feb. 23 Optical Flow, Trucco and Verri, pp. 178-194 (note: link only works through campus network)
8 Feb. 28 Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211
Mar. 2 Tracking, F&P Chap.17
9 Mar. 7 Statistical Pattern Recognition, F&P 22.1-22.3
Mar. 9 Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8
10 Mar. 14 Appearance-based Recognition, Eigenface, Fisherface, Appearance Manifolds
Mar. 16 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
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