Topics covered
The course will cover introductory concepts in computer vision. There are roughly three parts.
1. Image formation
The geometry of image formation and the design of cameras
The physics of light and how they interact with surfaces
Color perception
2. Image processing
Digital image representation
Signal processing and their applications
Modeling natural images and their applications
3. Image understanding
Image alignment and matching
Datasets and benchmarks for recognition
Overview of classical machine learning techniques
Recent advances in deep learning
Advanced topics: detection, semantic segmentation, and video understanding (time permitting)
Textbooks
There is no required textbook for this class. Nevertheless the following are useful computer vision references:
Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.) (optional)
Computer Vision: Algorithms and Applications, by Richard Szeliski (2nd ed.) (online copy of the draft).
For each lecture we will post links to the relevant sections of Richard Szeliski's (RS) book.
Programming and background
NumPy for Matlab users (Note that Matlab is no longer supported for this class)
Linear algebra review (via David Kriegman)
Random variables review (via David Kriegman)
How to write a good homework report (Note that this is for 670, but most of it is still relevant)
Past offerings of 370 at the university
Spring 2019: Subhransu Maji
Spring 2018, Subhransu Maji
Spring 2017, Subhransu Maji
Spring 2016, Subhransu Maji
Spring 2014, Erik Learned-Miller