Computer Vision Course Overview

This course is broken into three main sections:

1. Introduction to Computer Vision

• Computer Vision Pipeline
• Image Representation & Classification
  
• Facial Keypoint Detection
• Notebooks

This lesson covers topics like image processing, feature extraction done manually or through training a convolutional neural network (CNN) using PyTorch.

2. Advanced Computer Vision and Deep Learning

• Computer Vision and Deep Learning
  
• Deep Learning Algorithms
• Image Captioning

This lesson is all about advances in deep learning architectures like region-based CNN's, YOLO and single-shot detection algorithms, and CNN's used in combination with recurrent neural networks.

3. Object Tracking and Localization

• Introduction to Motion
• Object Tracking
• Localization

This lesson covers how a robot can move and sense the world around it, creating a visual representation of the world as it navigates.

Each of these three sections will have an associated project that allows you to demonstrate the skills you've learned in each part.

Projects

You’ll learn computer vision and deep learning techniques by getting to apply your skills to a variety of projects. The three project in this course are as follows:

• Facial Keypoint Detection
• Automatic Image Captioning
• Simultaneous Localization and Mapping (SLAM).

Additional Resources

Notebooks

• Computer Vision Experiments

Blogs

• Building Scalable Systems to Understand Content
• Toward a deeper understanding of the way AI agents see things
• Powered by AI: Advancing product understanding and building new shopping experiences