Output details

Autonomous growing neural gas for applications with time constraint: optimal parameter estimation

<24>Originality: This paper introduces the fast Autonomous Growing Neural Gas (fAGNG) algorithm for unsupervised classification applied to surveillance systems. The contribution of the paper is the design of vision-based services aimed at facilitating the monitoring of an area with poor visibility.

Significance: The significance of this research is the design of architectures for real-time surveillance applications especially in restricted environments such as the lobby of a building.

Rigour: Results published in a leading, peer-reviewed journal. The potential of this research is for the scheme to be adopted in the processing units of security systems world-wide.