Analysis of gap filling algorithms to smart surveillance environment

Abstract

There are a large number of cameras distributed throughout smart cities. As amount as the number of cameras increases, a huge streaming workload is produced. Although Fog computing has been used to reduce latency and jitter, Gateways IoT are unable to identify whether the data produced is invalid or absent, affecting the quality of service. Therefore, this paper presents an analysis of gap filling algorithms to smart surveillance environment. Our study shows that it is possible to maximize the accuracy of data imputation. Performance evaluation shows significant improvements in the imputation of missing data using Singular Spectrum Analysis (SSA), increasing the accuracy in the estimation of the Streaming video, and thus improving the quality of service.