Lesson Overview

In this lesson, you will gain exposure to many of the concepts and tools which you will keep coming back to as you learn more about computer vision and autonomous systems. We will focus on the Kalman Filter, which is an algorithm that uses noisy sensor measurements (and Bayes' Rule) to produce reliable estimates of unknown quantities (like where a vehicle is likely to be in 3 seconds).

In this lesson you'll learn the general intuition behind Kalman filters and build up a 1D filter of your own. Then, we'll take a short break from Kalman filters and really look at how we can represent motion and the state of a slef-driving car. Then, we'll go back to Kalman filters and talk about tracking objects in multiple dimensions using linear algebra. Linear algebra is one of the most powerful mathematical tools that a computer vision expert can use. When a problem can be framed in the language of matrices, it's often possible to find programmatic solutions which are effective and very fast.