The goal of computer vision is to compute properties of the three-dimensional world from digital images and videos. This field tackles problems such as reconstructing the 3D shape of an environment, recognizing people, objects and scenes - all through analysis of images and videos. This course aims to provide an introduction to computer vision, and will cover the topics of image formation, feature detection, motion estimation, object detection and recognition, convolutional network architectures and a few advanced topics in computer vision.
- Prerequisites:
- CS 334 or 534
- Data structures
- Working knowledge of Python
- Knowledge of how to use git and GitHub (clone, pull, commit, push, etc)
- Linear algebra
- Vector calculus