Multi-analysis surveillance and dynamic distribution of computational resources: Towards extensible, robust, and efficient monitoring of environments

Abstract

Intelligent surveillance has been a hot area of research for the past two decades. However, the integral security of environments remains a challenge due to the presence of new types of threats and the very dynamism and complexity of these environments. To make further progress, new proposals are needed to facilitate the design and deployment of multi-analysis surveillance systems where different types of analysis are simultaneously performed and the available computation resources are limited. Such systems need to provide three main characteristics: extensibility, robustness and efficiency. Extensibility to add new analysis components when new events of interest must be monitored. Robustness to avoid that failures in one analysis component affect the rest. Efficiency to analyze environments in real-time and to support decision-making processes that address the detected anomalies.This paper proposes a formal model for the multi-analysis surveillance of environments by means of the named components of normality, designed to deploy surveillance systems that satisfies the three previously mentioned characteristics. Extensibility thanks to the activation and deactivation of components of normality based on the monitoring needs of the analyzed environment. Robustness as a result of the isolation of these components such that a failure in one of them does not spread to the rest. Finally, efficiency due to the dynamic allocation of resources that benefits the components that detect anomalies at a given time. The experimental results prove that such dynamic allocation improves execution times and reduces waiting times.