Computer Vision

  • Course level: All Levels


This Computer Vision course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, multi-view geometry including stereo, motion estimation, and tracking, and classification.

We’ll develop basic methods for applications that include finding known models in images, depth recovery from the stereo, camera calibration, image stabilization, automated alignment (e.g. panoramas), tracking, and action recognition. We focus less on the machine learning aspect of CV as that is really a classification theory best learned in an ML course.


What Will I Learn?

  • Learn Image Classification
  • Learn Neural Networks
  • Learn CNN Architectures
  • Learn Detection and Segmentation
  • Learn Generative Models

Topics for this course

16 Lessons

Computer Vision

Introduction to Convolutional Neural Networks for Visual Recognition00:00:00
Image Classification00:00:00
Loss Functions and Optimization00:00:00
Introduction to Neural Networks00:00:00
Convolutional Neural Networks00:00:00
Training Neural Networks00:00:00
Training Neural Networks00:00:00
Deep Learning Software00:00:00
Recurrent Neural Networks00:00:00
CNN Architectures00:00:00
Detection and Segmentation00:00:00
Visualizing and Understanding00:00:00
Generative Models00:00:00
Deep Reinforcement Learning00:00:00
Efficient Methods and Hardware for Deep Learning00:00:00
Adversarial Examples and Adversarial Training00:00:00
Computer Vision
35 £

Enrolment validity: Lifetime


  • Data structures: You'll be writing code that builds representations of images, features, and geometric constructions.
  • No prior knowledge of vision is assumed though any experience with Signal Processing is helpful.