Main

Ambulatory measurement and interpretation of human activity

A research unit at the Dept. of Electrical, Electronics, Computers and Systems Engineering (DIEECS), Universidad de Oviedo, Gijón Campus.

We pursue new ideas and knowledge in the ambulatory measurement of human activity: motion, behaviour, feelings, attitude,...

Our goal is to automatically recognize physical activity and condition by integrating information gathered from sensors. This research should lead to the development of novel devices, based on simple sensors attached to the body, and able to provide real-time information while satisfying easiness, privacy, reliability and cost requirements. Examples of such devices are pedestrian navigation systems, monitoring devices to help the elderly live independently at home, portable sport training devices, etc.

Our research has applications in several application domains: health hazard monitoring, human-robot interaction, rehabilitation assessment or eldercare.

More info about our work can be accessed under the following links: publications, projects.

Location: Ed. Departamental Oeste, Módulo 2, 1ª planta (2.1.15), Campus de Gijón, Viesques 33204 Gijón, Asturias, España (map)

People: Juan Carlos Alvarez Alvarez / Antonio Miguel López Rodríguez / Diego Álvarez Prieto

Research areas

We explore novel methods for the ambulatory measurement of human activity.

Motion prediction and anticipation: prediction is a step forward from just motion measurement, which allow us to solve problems that demand a tightly We explore novel methods for the ambulatory measurement of position/orientation and its derivatives, using optimized arrangements of inertial sensors. Multi-sensor systems give us a way to improve robustness, fault-tolerance and auto-configuration properties, essential for monitoring applications.

Methods for 3D kinematics estimation with inertial sensors: the ambulatory measurement of position/orientation and its derivatives, using optimized arrangements of inertial sensors. Multi-sensor systems give us a way to improve robustness, fault-tolerance and auto-configuration properties, essential for monitoring applications.