Computer Vision and Object Detection

Abstract

In the previous chapter, we created a cloud API to make our applications even smarter. With only a few keystrokes, we created an Azure Cognitive Service capable of performing Computer Vision tasks. So far, the service is doing nothing but patiently residing on the cloud and expecting us to call it. Moving forward, we will feed Microsoft’s AI with Kinect’s color data to detect a variety of objects. Such objects include cars, people, televisions, phones, laptops, dogs, cats, and even teddy bears. We won’t stop there, though. Then, using the Kinect’s depth data, we’ll measure the distance between each object and the camera! Here’s an overview of the process: