Computer vision is challenging, but recent advances in image processing and AI have paved the way for solutions to a number of practical applications. This talk is about the broader class of image processing methods for extracting information from video and images. We’ll start from the beginning with an introduction to the topic, applications, and current capabilities of the state-of-the-art. I’ll present some of the fundamental techniques used to analyze images/video including deep neural network models. Finally, we end with an example of how these techniques come together to solve the problem of counting people walking by a street cam.