Chapter 9: Localizing Elements in Images with Object Detection

Object detection is one of the most common yet challenging tasks in computer vision. It's a natural evolution of image classification, where our goal is to work out what is in an image. On the other hand, object detection is not only concerned with the content of an image but also with the location of elements of interest in a digital image.

As with many other well-known tasks in computer vision, object detection has long been addressed with a wide array of techniques, ranging from naïve solutions (such as object matching) to machine learning-based ones (such as Haar Cascades). Nonetheless, the most effective detectors nowadays are powered by deep learning.

Implementing state-of-the-art object detectors (such as You Only Look Once (YOLO) and Fast Region-based Convolutional Neural Network (Fast R-CNN) from scratch is a very challenging task. However, there are many pre-trained solutions we can leverage, not...