CSE252A
Computer Vision I
Tuesday, Thursday
Center Hall, Rm. 208
http://www.cs.ucsd.edu/classes/wi04/cse291-c/
Class mailing list: cse252a at� graphics.ucsd.edu
Class web board: http://www.etalonsoft.com/cse252a/
News:
���������
���������
���������
���������
���������
���������
���������
����������������������� CSE252A.
Instructor: David Kriegman
Office: AP&M 3101
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours:��� Wednesday
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.
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
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:
Homework 0: Getting Started with Matlab, Due
Tuesday,
Homework 1: Photometric Stereo, Due
Homework 2: Radiometry and Cameras, Due
Homework 3: Stereo, Due
Homework
4: Face Recognition, Due
�
Syllabus
[ Note that this Syllabus is tentative &
subject to change]
|
Week |
Date/ Link to lecture notes |
Topic/Readings |
|
1 |
Intro to Computer Vision |
|
|
|
Human Visual System, F&P sec. 1.3 |
|
|
2 |
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 |
|
|
3 |
Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4 |
|
|
|
Special BRDF�s, Light Sources, Photometric Stereo, F&P, 5.2-5.4 |
|
|
4 |
Photometric stereo |
|
|
|
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 |
Filtering, F&P Chap. 7, Corner detection |
|
|
|
Edge detection, (Canny) F&P� Chap. 8 |
|
|
6 |
Color; F&P, Chap. 6� Some on-line sources include: Basics of Color, A FAQ on Color |
|
|
|
Epipolar Constraint and Stereo I, F&P Sec. 10.1 |
|
|
7 |
Stereo II, Dynamic Programming, Chapter 11 |
|
|
|
Optical Flow, Trucco and Verri , pp. 178-194 |
|
|
8 |
Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211 |
|
|
|
Tracking, F&P Chap.17 |
|
|
9 |
Statistical Pattern Recognition, F&P 22.1-22.3 |
|
|
|
Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8 |
|
|
10 |
Appearance-based Recognition, Eigenface, Fisherface, Appearance Manifolds |
|
|
|
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
