[Back]


Talks and Poster Presentations (with Proceedings-Entry):

A. Manzoor, C. Villalonga, A. Calatroni, H. Truong, D. Roggen, S. Dustdar, G. Tröster:
"Identifying Important Action Primitives for High Level Activity Recognition (Best Paper Award)";
Talk: 5th European Conference on Smart Sensing and Context (EuroSSC 2010), Passau, Germany; 11-14-2010 - 11-16-2010; in: "Smart Sensing and Context Proceedings of the 5th European Conference (EuroSSC 2010)", P. Lukowicz, K. Kunze, G. Kortuem (ed.); Springer, LNCS 6446 (2010), ISBN: 978-3-642-16981-6; 149 - 162.



English abstract:
Smart homes have a user centered design that makes human activity
as the most important type of context to adapt the environment according to people´s needs. Sensor systems that include a variety of ambient, vision based, and wearable sensors are used to collect and transmit data to reasoning algorithms to recognize human activities at different levels of abstraction. Despite various types of action primitives are extracted from sensor data and used with state of
the art classification algorithms there is little understanding of how these action primitives affect high level activity recognition. In this paper we utilize action primitives that can be extracted from data collected by sensors worn on human body and embedded in different objects and environments to identify how various types of action primitives influence the performance of high level activity recognition systems. Our experiments showed that wearable sensors in combination with object sensors clearly play a crucial role in recognizing high level activities and it is indispensable to use wearable sensors in smart homes to improve the performance of activity recognition systems.

Keywords:
Activity recognition, smart homes, action primitives


Related Projects:
Project Head Schahram Dustdar:
SM4ALL


Created from the Publication Database of the Vienna University of Technology.