CSE252A
Computer Vision I

Tuesday, Thursday 11:00-12:20pm
Solis Room 110

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

News:

03/20: The final exam is on Thursday (3/22) from 11:30-2:30 in SOLIS 110. Good luck!
03/08: Assignment 4 is posted.
03/07: The deadline for assignment 3 has been extended to next Tuesday.
02/27: Assignment 3 is posted.
02/20: A supplemental writeup is now available for homework 2 that describes the homography estimation process in more detail.
02/06: Assignment 2 is posted.
01/30: An irradiance example problem has been posted under todays lecture.
01/26: Additional reading material on radiometry and BRDFs has been made available (see lecture schedule).
01/19: Assignment 1 is posted.
01/12: The textbook is now on reserve at the S&E library.
01/12: Office hours for Prof. Kriegman and the TA have been set. See below for details.
01/11: Some students have reported problems subscribing to the email listserver. As an example, if your email address is super@cool.com you would send an email to listserver@ucsd.edu with the body "ADD super@cool.com cse252a-l". If you still encounter problems, email nalldrin@cs for further assistance.

Course Information:

Instructor: David Kriegman
Office: EBU3B, Room 4120
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours: Tu 1:30-2:30pm

TA: Neil Alldrin
Email: nalldrin at cs.ucsd.edu
Office Hours: Wed 11:00-12:00, EBU-3b B250A (CSE Building Basement)

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.

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 [Due 1/18]: Getting Started with Matlab

Homework 1 [Due 2/01]: Camera & Lenses, Rigid Transformations, and Radiometry

house_model.m
There is a bug in some versions of the textbook. F&P problem 2.5 should read .

Homework 2 [Due 2/22]: Image Warping & Mosaicing

im1.jpg im2.jpg im3.jpg im4.jpg im5.jpg im6.jpg
Correction : Under "What to Turn In", point 4 has been changed from "... applied to image 1" to "... applied to image 2". This is now consistent with section 3.
Supplemental material : A short writeup describing the homography estimation process in more detail.

Homework 3 [Due 3/13]: Dense Stereo Matching

Input Images. Either save the links below or download all the images at once, all_ims.zip.

Left Right True Disparity

DOTS

BARN1

TSUKUBA
Supplemental reading : "A Maximum Likelihood Stereo Algorithm", by Cox, Hingorani, Rao, and Maggs,

Homework 4 [Due 3/16]: Optical Flow

Correction : In the original version of the assignment, the threshold for the smallest eigenvalue of A'*A was given as 0.1. This should instead be 0.01.
Input Images : synth.zip sphere.zip corridor.zip

Synth Sphere Corridor
Supplemental reading : Trucco & Verri pp178-211.

Syllabus:

Week	Date / Link to lecture notes	Topic / Readings
1	Jan. 9 Linear algebra review Random variables review	Intro to Computer Vision
	Jan. 11	Human Visual System, F&P sec. 1.3
2	Jan. 16	Rigid Transformatoins SE(3), SO(3), Camera & Lenses, F&P Sec. 2.1, F&P Chap. 1
	Jan. 18	Perspective, Affine, orthographic projection, F&P 2.2, 2.3
3	Jan. 23 Partb	Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4; Supplemental reading Glassner Chapter 13 (requires campus network connection)
	Jan. 25	Special BRDF's, Light Sources, Photometric Stereo, F&P, 5.2-5.4; Supplemental reading Glassner pp 726-752
4	Jan. 30 Irradiance example problem	Photometric stereo
	Feb. 1	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. 6 Part b	Color; F&P, Chap. 6 Some on-line sources include: Basics of Color, A FAQ on Color
	Feb. 8	Color, Dichromatic model
6	Feb. 13	Filtering F&P Chap. 7, 8
	Feb. 15	Edges
7	Feb. 20	Epipolar Constraint and Stereo I, F&P Sec. 10.1Stereo II, Dynamic Programming, Chapter 11
	Feb. 22	Optical Flow, Trucco and Verri, pp. 178-194
8	Feb. 27	Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211
	Mar. 1	Tracking, F&P Chap.17
9	Mar. 6	Statistical Pattern Recognition, F&P 22.1-22.3
	Mar. 8	Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8
10	Mar. 13	Appearance-based Recognition, Eigenface, Fisherface, Appearance Manifolds
	Mar. 15	Model-based recognition, F&P Chap. 18