CSE 252A: Computer Vision I

Course Information

Instructor

David Kriegman
Office: EBU3B, Room 4120
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours: Monday 3:00 – 4:00 pm; Wednesday 2:30 – 3:30

Teaching Assistants

Bolun Zhang (boz028@eng.ucsd.edu)
Office Hours: Monday 4:00 - 5:00 pm B260A; Friday 4:00 - 5:00 pm B240A
Zachary Murez (zmurez@eng.ucsd.edu)
Office Hours: Wednesday, Thursday 3:00 - 4:00 pm 4148/4127
Nimish Srivastava (n2srivas@eng.ucsd.edu)
Office Hours: Tuesday 4:00 - 6:00 pm B240A
Rajat Sharma (ras043@eng.ucsd.edu)
Office Hours: Thursday 5:00 - 6:00 pm B260A

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 winter quarter.

Grading

There will be five homeworks and a final exam. The assignments will contain written questions and questions that require Python programming.

• Homeworks: 65% (5% for the first one and the other four 15% each)
• Final Exam: 35% (Thursday, 12/14 7:00PM-10:00PM)

Piazza

We will be using Piazza as our class web board. You'll be able to ask the professor, the TAs and your classmates questions on Piazza. Class announcements will be made using Piazza, so be sure to check your email or Piazza frequently.

Podcasts

We will try to make podcasts available for the class, but make no guarantees due to potential technical difficulties. It is highly encouraged that you still attend lectures in real life so we don't get lonely.

Required Textbook

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

Supplemental Textbook

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

Late Policy

Programming assignments will have a submission procedure described with the assignment, and has a 10% per day late penalty up to 3 days.

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.

Assignments

All assignments must be submitted on Gradescope as a single pdf file. Written problems may be typeset or hand written and scanned (but must be legable). Programing problems should be done in the provided ipython notebooks and exported (including outputs and figures) as a pdf. In addition to the pdf you must also submit the .ipynb file. See piazza post Homework 0 for instructions on setting up ipython notebooks.

Homework 0

hw0.tar.gz, hw0.pdf (subject to change)
due: Wednesday, October 11, 2017 11:59pm

Homework 1

hw1.tar.gz
due: Friday, October 27, 2017 6pm

Homework 2

HW2.zip, HW2.pdf
due: Friday, November 10, 2017 11:59PM

Homework 3

HW3.zip, HW3.pdf
due: Monday, November 27, 2017 11:59PM

Homework 4

HW4.ipynb, HW4.pdf
due: Friday, December 8, 2017 11:59PM

Syllabus

Note that this Syllabus is tentative & subject to change

Week	Date	Lec #	Lecture
1	10/2	1	Intro to Computer Vision, RS. 1-18
1	10/4	2	Human Visual System
2	10/9	3	Rigid Transformatoins SE(3), SO(3), Camera & Lenses, F&P Sec. 2.1, F&P Chap. 1, RS. 29-45, Linear algebra review
2	10/11	4	Perspective, Affine, orthographic projection, F&P 2.2, 2.3, RS. 46-59
3	10/16	5	Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4; Supplemental reading Glassner Chapter 13 (requires campus network connection)
3	10/18	6	Photometric stereo RS 580-583
4	10/23	7	Filtering
4	10/25	8	Edges
5	10/30	9	Stereo I:Epipolar Constraint and Stereo I, F&P Sec. 10.1, RS 530-544
5	11/1	10	Stereo II: Machine
6	11/6	11	Stereo III, Dynamic Programming, Chapter 11, 545-548, 552-556
6	11/8	12	Model fitting, Chapter 10
7	11/13	13	Optical Flow, Trucco and Verri, pp. 178-194, RS 4381-414
7	11/15	14	Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211
8	11/20	15	Tracking, F&P Chap.17, RS 235-237, 282-284, 551-552, 605-609
9	11/27	16	Recognition & Statistical Pattern Recognition, F&P 22.1-22.3
9	11/29	17	Deep Networks 1
10	12/4	18	Deep Networks 2
10	12/6	19	Color; F&P, Chap. 6, RS 8-89, Some on-line sources include: Basics of Color, A FAQ on Color
Resources Course webpage of the last time this class was taught by Kriegman fa13 Linear algebra review Random variables review Sample Final Questions