An Intelligent Video Surveillance System using Edge Computing based Deep Learning Model

Abstract

With the rapid increase in global data volume, various factors like low latency, high efficiency video surveillance is impossible to achieve in a centralized cloud computing model. Therefore, this paper proposes a distributed computing model for intelligent video surveillance system. This paper presents a smart video surveillance system which can execute Deep Learning algorithms in low power consumption embedded de vices. The proposed intelligent video surveillance system based on the edge computing consists of multi-camera for smart cities and homes. In general, the sending of original video surveillance data to the centralized computing model is too much time consuming and this will keep us far away to achieve our objective of real time data transmission so through this paper the edge computing technique is proposed, the idea is perform computation locally at the edge devices and then the computed data will be sent to the centralized computing model which is capable of performing the real time video surveillance by using the deep learning algorithm.