The goal of computer
vision is to compute properties of the three-dimensional
world from digital images. Problems in this field include
identifying the 3D shape of an environment, determining how
things are moving, and recognizing familiar people and
objects, all through analysis of images and video. This
course provides an introduction to computer vision,
including such topics as feature detection, image
segmentation, motion estimation, image mosaics, 3D shape
reconstruction, and object recognition.
Course Staff
Instructor: Ira
Kemelmacher
Office: CSE 650
Email: kemelmi@cs.washington.edu
Office hours: Wednesdays, 3pm-4pm
TA: Ankit
Gupta
Email: ankit@cs.washington.edu
Office hours: Thursdays, 2pm-3pm (CSE 220)
Prerequisites
- Data structures
- A good working knowledge of C and C++ programming
- Linear algebra
- Vector calculus
No prior knowledge of computer vision is assumed.
Textbooks
- Required: Richard Szeliski, Computer Vision:
Algorithms and Applications (Online edition).
- Optional: Forsyth & Ponce, Computer
Vision: A Modern Approach.
- Optional: Nalwa, A Guided Tour of Computer
Vision.
Administrative
- Email List: Please subscribe to the course email list
here.
- We have a discussion
board for the course. Please feel free to post any
doubts, or answer your classmates' questions. The course
staff will also be active on the forum, answering any
questions.
- Computer Accounts: if you don't have a CSE account and
want one for this class, click
here.
- Grading: The grade is based on four programming
projects.