Computer vision gives machines the ability to make sense of images and video: unlocking your phone with your face, reading road signs in a self-driving car, or spotting problems in a medical scan. To a computer an image is just a grid of numbers, so the field is about finding patterns in those numbers that match what people see.
The lessons start with a simple overview of how computers see, then explain the convolutional neural network (CNN), the model that changed image classification, and finish with object detection using YOLO, which finds and labels many objects in a single pass.
Watch the lessons in order. If a video runs long, feel free to treat it as a reference you dip back into later rather than something to finish in one sitting.
A friendly overview of how computers see: from tracking a colored ball pixel by pixel to recognizing edges, faces, and objects in images and video.
Video 11minDr Mike Pound explains why the convolutional neural network was a step change in image classification accuracy, and what it actually does with an image.
Video 14minAn introduction to YOLO (You Only Look Once), the object detection approach that finds and labels multiple objects in an image in a single pass.
Video 16min