Introducing object detection

With the rise of autonomous cars, facial detection, smart video surveillance, and people-counting solutions, fast and accurate object detection systems are in great demand. These systems include not only object classification from an image but also the location of each one of the objects, by drawing appropriate bounding boxes around them. This (drawing bounding boxes and classification) makes object detection a harder task than its traditional computer vision predecessor, image classification.

Before we explore the broad use cases of object detection, let’s understand how it adds to the object classification task that we covered in the previous chapter. Imagine a scenario where you have multiple objects in an image. I ask you to predict the class of objects present in the image. For example, let’s say that the image contains both cats and dogs. How would you classify such images? Object detection comes in handy in such a scenario, where...