Multisensor data fusion model for activity detection

Abstract

This paper describes a novel system for detecting human activity based on multi-sensor approach. This approach aim to provide accuracy and robustness to the activity recognition system. The performances of the systems that fuse multiple data coming from different sources are deemed to benefit from the heterogeneity and the diversity of the information involved. In this work a novel Multi-Sensor Data Fusion (MSDF) architecture is presented. This applies an information fusion algorithm based Fuzzy Logic with a set of rules in order to recognize Human Behavior. So as to obtain Feature-level Fusion from Extraction of physical data.