Modern society is witnessing a rapid and inexorable aging of the population, as a result of which there have beensignificant scientific advances in the medical field. It is also important, however for the scientific community tofind ways to ensure that global aging is economically sustainable.The purpose of this work is to propose an augmented reality tool that can provide support to elderly peoplein their daily lives. This is an important topic for an aging society seeking ways of enabling older people tolive independently for as long as possible. This paper presents a framework designed to offer a certain degreeof independence to the elderly in their homes. The first prototype, which was developed as part of the regional@Monitech project, has allowed us to evaluate the feasibility of the idea and its potential.

The automatic detection of human activities requires large computational resources to increase recognition performances and sophisticated capturing devices to produce accurate results. Anyway, often innovative analysis methods applied to data extracted by off-the-shelf detection peripherals can return acceptable outcomes. In this paper a framework is proposed for automated posture recognition, exploiting depth data provided by a commercial tracking device. The detection problem is handled as a semantic-based resource discovery. A simple yet general data model and a corresponding ontology create the needed terminological substratum for an automatic posture annotation via standard Semantic Web languages. Hence, a logic-based matchmaking allows to compare retrieved annotations with standard posture descriptions stored as individuals in a proper Knowledge Base. Finally, non-standard inferences and a similarity-based ranking support the discovery of the best matching posture. This framework has been implemented in a prototypical tool and preliminary experimental tests have been carried out w.r.t. a reference dataset. © 2014 Springer International Publishing.

Innovative analysis methods applied to data extracted by o®-the-shelf peripherals can provideuseful results in activity recognition without requiring large computational resources. In thispaper a framework is proposed for automated posture and gesture recognition, exploiting depthdata provided by a commercial tracking device. The detection problem is handled as a semanticbasedresource discovery. A general data model and the corresponding ontology provide theformal underpinning for posture and gesture annotation via standard Semantic Web languages.Hence, a logic-based matchmaking, exploiting non-standard inference services, allows to: (i) detectpostures via on-the-°y comparison of the annotations with standard posture descriptionsstored as instances of a proper Knowledge Base; (ii) compare subsequent postures in order torecognize gestures. The framework has been implemented in a prototypical tool and experimentaltests have been carried out on a reference dataset. Preliminary results indicate the feasibility of theproposed approach.