Video-Based Recognition and Representation of Human Actions

Vision-based human action recognition in videos is currently one of the most active research areas in the field of computer vision and pattern recognition, which has been actively investigated by a lot of researchers in recent years due to its great practical application potentiality. Our primary concern in this book is to explore and establish theories and methodologies for accurate representation and recognition of human actions in video data. Throughout the chapters of the book, several approaches involving diverse conceptualizations are presented to represent and recognize human actions from video data. Furthermore, in Chapter 4, a variety of distinctive visual features (shape and motion features) for the representation and recognition of human actions are explored.