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 recognition and classification in an image, but can also locate each one of them by drawing appropriate boxes around them. This makes object detection a harder task than its traditional computer vision predecessor, image classification.
To understand how the output of object detection looks like, let's go through the following picture:
So far, in the previous chapters, we have learned about classification.
In this chapter, we will learn about having a tight bounding box around the object in the picture, which is the localization task.
Additionally, we will also learn about detecting the multiple objects in the picture, which is the object detection task...
