Qualitative Recognition of Ongoing Human Action Sequences

Abstract

This paper deals with the qualitative visual recognition of continuous human action sequences. Based on an analysis of the structure of physical actions, a framework for temporal segmentation and qualitative classification of physical actions is proposed. In order to achieve correctness as well as efficiency in real time action recognition, a hierarchical spatio-temporal attention control method is developed. As the integration of these ideas, a cognitive architecture for action recognition is proposed. An experimental system is built for recognizing block assembly tasks performed by human workers. This shows the possibility of generating symbolic descriptions of the shown tasks in real time. 1 Introduction Social animals, including humans, have high competence for observing, understanding and reacting to other agents' actions effectively. Action understanding is indispensable for intelligent behavior in multi-agent environments. Also, the coincidence of higher intelligence and advanc...