This class is a general introduction to computer vision. It covers standard techniques in image processing like filtering, edge detection, stereo, flow, etc. (old-school vision), as well as newer, machine-learning based computer vision.
News
- May 21: HW5 is out. Due on June 4 (Thu).
- May 7: HW4 is out. Due on May 21 (Thu).
- April 23: HW3 is out. Due on May 7 (Thu).
- April 9: HW2 is out. Due on April 23 (Thu).
- April 2: HW1 is out. Due on April 9 (Thu).
- March 28: Initial draft of textbook is ready.
- March 15: Website is up!
Course Information
Instructors
TAs
- Svetoslav (Svet) Kolev
- Aleksander Hołyński
- Keunhong Park
Contact
- Course Slack: there will be a Slack workspace for the class. This will be the main point of contact for this course. You will be emailed instructions on how to sign up.
- Email: To contact the course staff (instructors + TAs), email cse576-staff@cs.washington.edu. Please use the Slack for most questions, we will be much more responsive.
Lectures
- When: Tuesdays and Thursdays from 3:00pm-4:20pm
- Where: Lectures will be on Zoom this quarter.
- How: Check Canvas for a link to the Zoom lecture.
Prerequisites
- Data structures
- A good working knowledge of C and C++ programming
- Linear algebra
- Vector calculus
- No prior knowledge of vision is assumed.
Grading
- Grading is based on homework only.
- We will have no exams.
Late Homework Policy
- Homeworks are due by 3pm (before the lecture) on the due date.
- Late work will be penalized.
- Please ask the instructor if you have an exceptional circumstance.
Student Conduct Code
The Student Conduct Code explains that admission to the University carries with it the presumption that students will practice high standards of professional honesty and integrity (WAC 478-120-020 [2]). In particular, all work (homework and exams) is to be your own individual work. You may discuss programs but NOT copy any code.
Resources
Course Textbook
- Richard Szeliski, Computer Vision: Algorithms and Applications
Recommended Readings
- Palmer, S. E. (1999). Vision Science: Photons to Phenomenology. The MIT Press, Cambridge, Massachusetts.
- Livingstone, M. (2008). Vision and Art: The Biology of Seeing. Abrams, New York.
- Brown, M. S. (2019). ICCV 2019 tutorial on understanding color and the in-camera image processing pipeline for computer vision.
- Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer, New York, NY.
- Glassner, A. (2018). Deep Learning: From Basics to Practice. The Imaginary Institute.
- Zhang, A., Lipton, Z. C., Li, M., and Smola, A. J. (2019). Dive into deep learning.
- Hartley, R. I. and Zisserman, A. (2004). Multiple View Geometry. Cambridge University Press, Cambridge, UK, 2nd edition.