RGB-D sensing based human action and interaction analysis: a survey

Human activity recognition has been actively studied in the last three decades. Compared to human action performed by a single person, human interaction is more complex due to the involvement of more subjects and the interdependence between them. Recently, motivated by the remarkable success of deep learning techniques, many learning-based feature representations have been developed for activity recognition. This paper provides a comprehensive review of human action and interaction recognition methods, covering both hand-crafted features and learning-based features, with a special focus on data captured by RGB-D sensors. Furthermore, this review reveals practical challenges in human activity analysis along with their promising solutions and potential future directions.