Head tracking is another huge topic in the field of Computer Vision. It is very useful when you want to create a human computer interface. For example, it is usually used in web browser games to move objects or control a 3D interface. There are differences between object detection and tracking. First of all, tracking works only on videos, since you track an object (not reestimate) a new instance in each frame. Consequently, we need to assume that the object we track is the same as it was on the previous frame.
Tracking can be done for multiple objects but here we will focus on a single object, in our case, it is a head or more precisely—face. There is a wonderful library that can help us to track it. It is called headtrackr (https://github.com/auduno/headtrackr). In addition to face tracking, it provides a functionality to create an interface that helps to control your browser applications using head motion. We will not focus on the motion estimation part here...