CSE 152: Introduction to Computer Vision

Course Information

Instructor

David Kriegman
Office: CSE 4120
Phone: (858) 822-2424
Email: kriegman at cs.ucsd.edu
Office Hours: Mon 4:00-5:00PM in CSE 4120

Teaching Assistants

Nikhil Bangalore Mohan
Email: nmohan at eng.ucsd.edu
Office Hours: Wed 9:00 - 10:00 AM in CSE B260, Wed 11:00am-12:00pm in CSE B275
Steve Guerin
Email: sguerin at eng.ucsd.edu
Office Hours: Thu 6:00-7:00pm in CSE B215, Tue 12:00 - 1:00 PM in CSE B270

Class Description

The goal of computer vision is to compute properties of the 3D world from images and video. Problems in this field include identifying the 3D shape of a scene, determining how things are moving, and recognizing familiar people and objects. This course provides an introduction to computer vision with topics such as feature detection, image segmentation, motion estimation, object recognition, and 3D shape reconstruction.

Grading

There will be five homeworks, a midterm, and a final exam. The assignments will contain both written questions and Python programming questions.

•  Assignments:	55%	(5% for HW0, 12.5% for each of the other four)
•  Midterm:	15%	(Date TBD)
•  Final Exam:	30%	(Wed, 3/18/20 7:00-10:00pm)

Piazza

We will be using Piazza as a forum for discussion. You'll be able to interact with the professor, the TAs, and your classmates on Piazza. If you have a question or confusion, it is likely that other students do too, so as a first step we recommend heading to Piazza to (a) first check if anyone else has asked your question and if not, to (b) ask it yourself! Note that class announcements will also be made on Piazza, so you should check Piazza and/or your email somewhat frequently.

Podcasts

We will try to make podcasts available for the class, but we cannot make any guarantees due to potential technical difficulties. In any case, you are highly encouraged to attend lectures in person so that Professor Kriegman doesn't get lonely.

Textbooks

This course does not require a textbook. Primary readings can be found in two online texts:

•  [RS] Computer Vision: Algorithms and Applications, by Rick Szeliski [PDF]

•  [GBC] Deep Learning, by Ian Goodfellow, Yoshua Bengio and Aaron Courville [Link]

A good secondary source is an old text:

•  [TV] Introductory Techniques for 3-D Computer Vision, E. Trucco and A. Verri, Prentice Hall, 1998 [eresearve]

Prerequisites

Linear algebra (e.g. Math 20F), multivariable calculus (e.g. Math 20A), Python. Probability can also be useful.

Late Policy

Each assignment will come with a description of the relevant submission procedure. However, unless otherwise stated, the late penalty is 10% per day and submissions will only be accepted for up to three days after the deadline.

Collaboration Policy

You may work together on homework assignments to discuss ideas and methods only. The work and code you submit should be your own. It is never permitted to copy or directly reference the code or written work of others.

Academic Integrity

In this course we expect students to adhere to the UC San Diego Integrity of Scholarship Policy. This means that you will complete your work honestly, with integrity, and in support of an environment of integrity for the class you are enrolled in.

Assignments

All assignments must be submitted on Gradescope as a single PDF file. Written problems may be either typeset or handwritten/scanned, but we may dock points if your handwriting is illegible or hard to read. Programming problems should be done in the provided IPython notebooks and exported (including outputs and figures) as a PDF. In addition to the PDF you should submit the .ipynb file.

Assignment 0

HW0, HW0.pdf, HW0 Solutions
Due on Thursday, January 16, 2020 at 11:59pm PT

Assignment 1

HW1, HW1.pdf
Due on Thursday, January 30, at 11:59pm PT

Assignment 2

HW2, HW2.pdf

Due 2/13

Assignment 3

HW3, HW3.pdf

Due 3/4

Assignment 4

HW4, HW4.pdf

Due 3/18

Syllabus

Note that the syllabus is tentative and subject to change.

Date	Lecture	Reading	Events
1/6	1. Introduction to Computer Vision, Linear Algebra Intro (in section)	[RS, 1-28]
1/8	2. Geometric Image Formation	[RS, 29-52]	Assignment 0 Released
1/13	3. Filtering, Discussion + Python Review	[RS, sec 3.2-3.3]
1/15	4. Corner Detection and SIFT	[RS, sec 4.1.1, opt 4.2]	Assignment 0 due Assignment 1 released
1/20	MLK Day - No Class	Discussion Wk3
1/22	5. 3D Shape Recovery: Shape-from-X, Introduction to Stereo, 3D Cameras	[RS, sec 4.1.2, 7.1]
1/27	6. Stereo 1: Epipolar Constraint and the Fundamental Matrix, Discussion Slides	[RS, sec 11.1, 7.2,]	Assignment 1 due
1/29	7. Stereo 2: Rectification + Stereo Matching
2/3	8. Aligning 2D and 3D Images and Structure from Motion		Assignment 2 released
2/5	9. Model Fitting and RANSAC	Discussion wk 5 slides
2/10	10. Photometric Image Formation
2/12	11. Recovering Fine Surface Geometry: Lambertian Photometric Stereo	Discussion wk 6 slides	Assignment 2 due
2/17	Presidents Day - no class
2/19	12. Midterm	Practice Midterm
2/24	13. Video 1: Optical Flow and the Motion Field	[TV, 177-191]	Discussion wk 8 slides
2/26	14. Video 2: Tracking	[TV, 191-198]	HW3
3/2	15. Recognition
3/4	16. Neural Networks and Learning		Assignment 4 released
3/9	17. Convolutional Neural Networks
3/11	18. Color
3/18	Final Exam (7-10 PM)

Resources

Diversity and Inclusion

We are committed to fostering a learning environment for this course that supports a diversity of thoughts, perspectives, and experiences while respecting your identities (including race, ethnicity, heritage, gender, sex, class, sexuality, religion, ability, age, educational background, etc.). Our goal is to create an inclusive learning environment where all students can feel comfortable and thrive.

Accordingly, the CSE 152 staff will make a concerted effort to be welcoming and inclusive to the wide range of students in this course. If there is some way we can help you feel more included, please let one of the course staff know (in person, over email/Piazza, or even via a note under the door).

We also expect that you, as a student in this course, will honor and respect your classmates, abiding by the UCSD Principles of Community. Please understand that others’ backgrounds, perspectives, and experiences may be different than your own, and help us build an environment where everyone is welcomed and respected.

If you experience any sort of harassment or discrimination, please contact an instructor as soon as possible. If you prefer to speak with someone outside of the course, please contact the Office for the Prevention of Harassment and Discrimination.

Students with Disabilities

We aim to create an environment in which all students can succeed. If you have a disability, please contact the Office for Students with Disabilities (OSD), which is located in University Center 202 behind Center Hall, and discuss appropriate accommodations as soon as possible. We will work to provide you with the accommodations you need, but you must first provide a current Authorization for Accommodation (AFA) letter issued by the OSD. You are required to present your AFA letters to faculty (please make arrangements to contact Prof. Kriegman privately) and to the department's OSD Liaison so that accommodations may be arranged.

Basic Needs/Food Insecurities

If you are experiencing any insecurities related to basic needs (food, housing, financial resources), there are resources available on campus to help, including The Hub and the Triton Food Pantry. Please visit http://thehub.ucsd.edu for more information.