As reported by numerous World Health Organization studies, fall incidents are considered one of the leading causes of loss of autonomy, injuries, and even deaths, and this is not only among elderly people but also in other categories such as workers. Fall incidents also have a considerable impact on the budget allocated to the care of people suffering from the effects of falls. This work presents a comprehensive review of state-of-the-art fall detection technologies considering the most powerful machine learning methodologies, both classical formalism (shallow methods), and approaches based on deep learning formalism. The authors reviewed the most recent and effective methods for fall detection and presented the used sensors, cameras, applied pre-treatments, generated attributes, and algorithms used in this field of application. The present work is completed by a discussion presenting some limitations that need to be analyzed and taken into account to further improve the quality of fall detection and reduce their impacts.