Stereo Vision, Dense Motion & Tracking

This course enables learners to develop 3D vision applications using a stereo imaging system. They are introduced to stereo vision theory, dense motion and visual tracking. They are able to discuss techniques used to obtain the 3D structure of objects. Topics include epipolar geometry, optical flow, structure from motion, multi-object tracking, 3D vision and visual odometry.

This course is ideal for anyone curious about or interested in exploring the concepts of computer vision. It is also useful for those who desire a refresher course in mathematical concepts of computer vision. Learners should have basic programming skills and experience (understanding of for loops, if/else statements), specifically in MATLAB (Mathworks provides the basics here: https://www.mathworks.com/learn/tutorials/matlab-onramp.html). Learners should also be familiar with the following: basic linear algebra (matrix vector operations and notation), 3D co-ordinate systems and transformations, basic calculus (derivatives and integration) and basic probability (random variables).

Material includes online lectures, videos, demos, hands-on exercises, project work, readings and discussions. Learners gain experience writing computer vision programs through online labs using MATLAB* and supporting toolboxes.

This is the third course in the Computer Vision specialization that lays the groundwork necessary for designing sophisticated vision applications. To learn more about the specialization, check out a video overview at https://youtu.be/OfxVUSCPXd0.

* A free license to install MATLAB for the duration of the course is available from MathWorks.

Stereo Vision
-In this module, we will discuss the fundamentals and applications of stereo vision and multiple camera systems.

Dense Motion & SFM
-In this module, we will discuss motion perception, optical flow, applications of dense motion, and structure from motion.

Visual Tracking
-This module provides information about visual tracking, including: object tracking, motion models, inferences used in tracking, and multi-object tracking.

3D Vision
-This module discusses the active methods used to develop 3D vision, as well as the applications of 3D vision.