A Multisensory Monitoring and Interpretation Framework Based on the Model–View–Controller Paradigm - Foundations on Natural and Artificial Computation - page 440

A Multisensory Monitoring and Interpretation
Framework Based on the
Model-View-Controller Paradigm

Jose Carlos Castillo 1 , Angel Rivas-Casado 2 ,AntonioFernandez-Caballero 1 , 3 ,
Mar ıa T. Lopez 1 , 3 ,andRafaelMart ınez-Tomas 2

1 Instituto de Investigacion en Informatica de Albacete (I3A), n&aIS Group,
Campus Universitario s/n, 02071-Albacete, Spain
{ JoseCarlos.Castillo,Antonio.Fdez,Maria.LBonal } @uclm.es
2 Departamento de Inteligencia Artificial, E.T.S.I. Informatica,
Universidad Nacional de Educacion a Distancia, 28040-Madrid, Spain
{ arivas,rmtomas } @dia.uned.es
3 Departamento de Sistemas Informaticos, Universidad de Castilla-La Mancha,
Campus Universitario s/n, 02071-Albacete, Spain

Abstract. This paper proposes a monitoring and interpretation frame-
work inspired in the Model-View-Controller (MVC) paradigm. Indeed,
the paper proposes the extension of the traditional MVC paradigm to
make it more flexible in incorporating the functionalities of a monitoring
and interpretation system. The proposed model is defined as a hybrid
distributed system where remote nodes perform lower level processing as
well as data acquisition, while a central node is in charge of collecting
the information and of its fusion. Firstly, the framework levels as well
as their functionalities are described. Then, a fundamental part of the
proposed framework, namely the common model, is introduced.

1 Introduction

Monitoring and interpretation systems have to understand and predict actions
of the objects present in the scenario. To date there are many approaches devel-
oped for public transport monitoring, such as airports [14], ports [12], railway
and subway stations [7,13], and trac control [1]. Other important monitored
public places are banks, shops, home or parking lots [15]. There are also sys-
tems indicated for human activity monitoring [11,4] or simply as an answer to
industrial needs [5].
Moreover, the requirements of surveillance systems have led to systems able to
monitor large areas. They go beyond simple object detection, including tracking
and activity detection, and involving several sensors. Most works are centered
in the combination of a set of cameras for this purpose. In [16] a system for
classification and tracking of soccer players is proposed. The system consists of
eight cameras (each one with its own processor) and a central processor for data
collection and fusion. Another approach [6] describes the “EasyLiving” system.