Lectures
You can download the lectures here. We will try to upload lectures prior to their corresponding classes.
-
Lecture 1- Introduction
tl;dr: Overview of the course, objectives, and introduction to computer vision.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski (2nd Edition) Chapter 1
- Szeliski 3.1 - 3.3
-
Lecture 2 - Image Formation and Camera Models
tl;dr: Understanding how images are formed and the basic principles of camera models.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 3.1-3.3, 7.2
- Szeliski 2.3.1, 3.4-3.5
-
Lecture 3 - Features Detection and Invariance.
tl;dr: Understanding how to detect features in images and make them invariant to transformations.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 7.1
- Szeliski 7.1
-
Lecture 4 - Image Transformations & Image Alignments.
tl;dr: Understanding how to transform images and align them.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 3.6
- Szeliski 6.1
-
Lecture 5 - RANSAC & Camera Calibration.
tl;dr: Understanding how to estimate the camera parameters and how to robustly estimate the parameters using RANSAC.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 6.1
- Szeliski 2.1.3-2.1.6
-
Lecture 6 - Panoramas & Single View Modling.
tl;dr: Understanding how to create panoramas and model a scene from a single image.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 8
- Szeliski 11.1
-
Lecture 7 - Stereo & Light and perception.
tl;dr: Understanding how to estimate depth from stereo images and how light and perception are related.
[notes] [Jupyter Notebook] [slides1] [slides2] [all]
Readings:
- Szeliski 12.3-12.5
- Szeliski 2.2