Study and analysis of head pose estimation methods and databases

Head pose estimation is an active and popular area of research. Over the years many approaches have constantly been developed, leading to a progressive improvement in accuracy; nevertheless, head pose estimation remains an open research topic, especially in unconstrained environments. In this thesis, we will review the increasing amount of available datasets and the methodologies used to acquire ground-truth annotations. We will discuss the evolution of the field by proposing a classification of head pose estimation methods and by explaining their advantages and disadvantages, all with a main focus on the recent deep learning based techniques. An in-depth performance comparison and discussion is presented at the end of the work. The thesis also states promising directions for future research on the topic.