The main task of traffic monitoring applications is to identify moving targets. Usually, these applications require that a large number of parameters is tuned in order to work properly. In the motion detection system we have developed, about thirty parameters have been required to be optimized. This paper shows how a distributed implementation of a Genetic Algorithm (GA) over a network of workstations can successfully accomplish the parameter optimization task within a reduced amount of time. Accurate experiments accomplished on a challenging training sequence yield optimal parameter values. Four more test sequences allow us to assess the generality of the results previously attained.

Optimizing parameters of a motion detection system by means of a distributed genetic algorithm / A. Bevilacqua. - In: IMAGE AND VISION COMPUTING. - ISSN 0262-8856. - STAMPA. - 23:9:(2005), pp. 815-829. [10.1016/j.imavis.2005.04.001]

Optimizing parameters of a motion detection system by means of a distributed genetic algorithm

BEVILACQUA, ALESSANDRO
2005

Abstract

The main task of traffic monitoring applications is to identify moving targets. Usually, these applications require that a large number of parameters is tuned in order to work properly. In the motion detection system we have developed, about thirty parameters have been required to be optimized. This paper shows how a distributed implementation of a Genetic Algorithm (GA) over a network of workstations can successfully accomplish the parameter optimization task within a reduced amount of time. Accurate experiments accomplished on a challenging training sequence yield optimal parameter values. Four more test sequences allow us to assess the generality of the results previously attained.
2005
Optimizing parameters of a motion detection system by means of a distributed genetic algorithm / A. Bevilacqua. - In: IMAGE AND VISION COMPUTING. - ISSN 0262-8856. - STAMPA. - 23:9:(2005), pp. 815-829. [10.1016/j.imavis.2005.04.001]
A. Bevilacqua
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/5788
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 7
social impact