This course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, multiview 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 the classification theory best learned in an ML course.
* Photos and promotional materials on this page are copyrighted on udacity.com
We only endorse high-quality online courses and educational content. This page contains affiliate links and we may earn a small commission when you click on the link at no additional cost to you. Thank you!
Read the full policy here.