Real-life activity recognition: recognizing reading activities

Abstract

How can we extract high level information about human actions and complex real world situations from heterogeneous ensembles of simple, often unreliable sensors embedded in commodity devices? We focus on how to use body-worn devices for activity recognition in general, and how to combine them with infrastructure sensing. We discuss how to combine them with traditional computer vision approaches for a specific high level human activity, namely knowledge acquisition (in particular recognizing reading activities).