Computer Vision I

Tuesday, Thursday 09:30-10:50 am
WLH 2205


Class Web Board: Piazza

Class web page: http://cseweb.ucsd.edu/classes/fa13/cse252A-a


Final exam, Thursday 12/12/13 8:00am-10:59am TBA Sample final exam

Course Information:

Instructor: David Kriegman
Office: EBU3B, Room 4120
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours: Tuesday 4:30 – 5:30pm


TA: Oscar Beijbom

Email: obeijbom at ucsd.edu

Office: EBU-3b Room B275

Office Hours: Wednesday: 12-1pm

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," (2nd ed.) David A. Forsyth, Jean Ponce, Prentice Hall, ISBN: 013608592X

Supplemental Text:

Computer Vision: Algorithms and Applications”, Richard Szeliski, is available at: http://szeliski.org/Book/.


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

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.

Collaboration Policy:
You may work together on homework assignments to discuss ideas and methods only, however what you turn in should be your own work and any code should be your own coding. Copying is not permitted.


Homework 0 [Due 10/3]: Getting Started with Matlab. Updated text to appread on Thursay Sep. 26.

Homework 1 [Due 10/17]: Camera Models and Homography

Homework 2 [Due 10/31]. New due date: [11/05].

Homework 3 [Due 11/19] New due date: [11/21].

Homework 4 [Due 12/06]


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

Date / Link to lecture notes

Topic / Readings

Sep. 26
Linear algebra review
Random variables review

Intro to Computer Vision

Oct. 1

Human Visual System, F&P sec. 1.3. RS 1-18

Oct. 3

Image Formation and Cameras. Projective Geometry. Homogenous Coordinates. Homography

Oct. 8

Homography. Perspective, Affine, orthographic projection and geometry. Camera Models. Lenses

Oct. 10

Lenses Continued. SO(3) Transformations. Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4

Oct. 15

Radiometry Continued. Radiance and Irradiance. Special BRDF's, Light Sources, Photometric Stereo.

Oct. 17

Lighting and Photometric Stereo F&P Section 2.2

Oct. 22

Photometric Stereo F&P Section 2.2

Oct. 24

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

Oct. 29

Color, Dichromatic model, RS 67

Oct. 31

Color, Dichromatic Model Continued. SUV Space. Filtering F&P Chap. 7, 8, RS.  101-1.22

Nov. 5

Edges RS 238=249

Nov. 7

Epipolar Constraint and Stereo I, F&P Sec. 10.1, RS 530-544

Nov. 12

Stereo II, Dynamic Programming, Chapter 11, 545-548, 552-556

Nov. 14

Optical Flow, Trucco and Verri, pp. 178-194, RS 4381-414

Nov. 19

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

Nov. 21

Tracking, F&P Chap.17, RS 235-237, 282-284, 551-552, 605-609

Nov. 26

Statistical Pattern Recognition, F&P 22.1-22.3

Dec. 3

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

Dec. 5

Appearance-based Recognition and  Model-based recognition, F&P Chap. 18, RS 655-722

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