Gap Filling of Missing Streaming Data in a Network of Intelligent Surveillance Cameras

Abstract

The growth of video surveillance devices increases the rate of streaming data. However, even working in the Fog Computing environment, these smart devices may fail collecting information, producing missing or invalid data. This issue can affect the user quality of experience, because the PTZ-controller may lose the target object tracking. Therefore, this paper presents the Singular Spectrum Analysis - (SSA), as the method to replace missing values in this complex environment of intelligent surveillance cameras. SSA is characterized within time series field by performing a non-parametric spectral estimation with spatial-temporal correlations. The values not correctly monitored, were estimated by SSA with accuracy, allowing the tracking of a suspect object.