Modeling method of human actions based on the situation with variable level of the spatial-temporal abstraction

In order to realize a system that adapts to a person by considering human behaviors such as an automatic monitoring system and a driving support system, the system must have a certain model of human behaviors. Therefore, we have proposed a modeling method of human behavior based on the causality between a situation around a person and a human behavior. In order to model human behaviors appropriately depending on the problem where the proposed modeling method is applied, the spatial and temporal abstraction levels of human behaviors should be adjustable. In this paper, we propose a modeling method of human behaviors that can adjust the spatial and temporal abstraction levels of modeled human behaviors. In this method, the temporal and spatial abstraction levels of human behavior can be adjust independently, and the spatial and temporal adjustment parameters are introduced in the time series clustering process. The usefulness of the proposed method is examined through the experiment.