Abstract

Abstract—The recognition and monitoring of activities of daily living is one of the key requirements of a Smart Living environment to promote levels of independence. In this paper,we present a novel approach to extracting high-level semantic information from low-level data acquired through video recordings. We have developed a Model Checker based on a bounded temporal past linear logic. We have evaluated the performance of the model checker based on a set of 12 experiments conducted within a Smart Kitchen environment. Initial results have demonstrated the utility of such an approach, however, further efforts are required to address issues of scalability and maintenance.