Human Action Recognition: A Review

Human Action Recognition is a challenging problem in the field of machine vision. It finds diverse application in a range of fields, whether it be in care of elderlies, or in sports, movies, interactive gaming and other areas. Videos from various sources need to be labelled so that an awareness on what exactly a person is doing can be recognized. Human Action recognition, in its primitive form can be thought of as a combination of three processes, feature extraction, classification on the basis of the extracted features and finally, recognition of actions. The action labels are a solution to many challenges like surveillance, video retrieval and health care problems. Processing the data online is of great help in automatic surveillance in hospitals, malls, sports galleries, homes with patients