Object detection was briefly introduced in Chapter 1, Computer Vision and Neural Networks. In this section, we will cover its history, as well as the core technical concepts.
Introducing object detection
Background
Object detection, also called object localization, is the process of detecting objects and their bounding boxes in an image. A bounding box is the smallest rectangle of an image that fully contains an object.
A common input for an object detection algorithm is an image. A common output is a list of bounding boxes and object classes. For each bounding box, the model outputs the corresponding predicted class and its confidence.
