AI

This course teaches how modern computer vision systems locate multiple objects in an image with bounding boxes and class labels, and how they follow those objects across video frames without losing track of who's who. It's part 1 of the Computer Vision Deep Dive track, building on Computer Vision Basics, and is meant for anyone who already understands basic image classification and wants to see how real-world CV systems like self-driving cars, security cameras, and retail analytics actually work. Expect conceptual, non-mathematical explanations of detection mechanics, tracking identity, and the practical tradeoffs that separate a demo from a deployed system.