Hierarchical recognition of daily human actions based on continuous Hidden Markov Models

Abstract

This paper presents a recognition method of human daily-life action. The method utilizes hierarchical structure of actions and describes it as a tree. We model the actions by using Continuous Hidden Markov Models which gives an output of time-series feature vectors extracted by feature extraction filter based on human knowledge. In this method, recognition starts from the root, it then competes the likelihoods of child-nodes, chooses the maximum one as recognition result of the level, and goes to deeper level. The advantages of hierarchical recognition are: 1) recognition of various levels of abstraction, 2) simplification of low-level models, 3) response to novel data by decreasing degree of details. Experimental result shows that the method is able to recognize some basic human actions.