Class Mailing List: UCSD Listserve
cse252al
Class Web
Board: QuickTopic
Class web page: http://cseweb.ucsd.edu/classes/fa09/cse252a
9/24: There will be no classes next week. The lectures will be made up in the following weeks. Time and location to be announced.
10/9: HW1 assigned. Due 10/20
10/22: HW2 assigned. Due 11/3
11/3: HW2 Due Date Extended. Due 11/10
11/6/09: HW3 assigned. Due 11/24
11/25/09: HW4 assigned. Due 12/4
12/3/09:Final exam, Friday 12/11/09 7:00PM10:00PM Center Hall 217A, Sample final exam
Instructor: David
Kriegman
Office: EBU3B, Room 4120
Phone: (858) 8222424
Email: kriegman at cs.ucsd.edu
Office Hours: Th 2:00 – 3:30pm
TA: Steve Branson
Email: sbranson at cs.ucsd.edu
Office: EBU3B, Room B240A (basement)
Office Hours: Monday 2:003:00
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 (shapefromshading, 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
Supplemental Text:
“Computer Vision: Algorithms and Applications”, Richard Szeliski, A draft of the book, which is currently being written, is available at: http://research.microsoft.com/enus/um/people/szeliski/Book/.
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.
Grading:
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 handin 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 [Due 10/13]: Getting Started with Matlab
Homework 1 [Due 10/20]: Camera & Lenses, Rigid Transformations, and Radiometry
· For those who don't have a copy of the book, use this copy Homework 1 modified
Homework 2 [Due 11/10]: Photometric Stereo and Specularity Removal
Homework 3 [Due 11/24]: Dense Stereo Matching
Homework 4 [Due 12/4]: Optical Flow
[ Note that this Syllabus is
tentative & subject to change ]
Week 
Date / Link
to lecture notes 
Topic /
Readings 
1 
Intro to Computer Vision 

2 
Sep. 29 Oct. 1 
There will be no lectures this week, and we will make them up in subsequent weeks 
3 
Rigid Transformatoins SE(3), SO(3), Camera & Lenses, F&P Sec. 2.1, F&P Chap. 1 


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


Human Visual System 

4 
Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4; Supplemental reading Glassner Chapter 13 (requires campus network connection) 


Special BRDF's, Light Sources, Photometric Stereo, F&P, 5.25.4; Supplemental reading Glassner pp 726752 


Photometric stereo 

5 
Illumination Cones, Belhumeur, Kriegman, What Is the Set of Images of an Object under All Possible Illumination Conditions?, IJCV 28(3), 1998, 245260 


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

6 
Color, Dichromatic model 


Filtering F&P Chap. 7, 8 

6 
Edges 


Epipolar Constraint and Stereo I, F&P Sec. 10.1Stereo II, Dynamic Programming, Chapter 11 

7 
Optical Flow, Trucco and Verri, pp. 178194 


Infinitesimal structure from Motion, Trucco and Verri pp. 195202, and pgs. 208211 

8 
Tracking, F&P Chap.17 


Statistical Pattern Recognition, F&P 22.122.3 

9 
Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8 

10 
Appearancebased Recognition, Eigenface, Fisherface, Appearance Manifolds 


Modelbased recognition, F&P Chap. 18 
Programming languages:
The primary language will be Matlab. . Click here for Serge
Belongie's Matlab resource links.
Other
excellent textbooks:
Introductory
Techniques for 3D 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 0387008934 (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