Design of Collaborative Framework of Network Technologies to Enhance Surveillance Security and Intrusion Detection

Abstract

Surveillance Security in recent times has been challenged with the existence of a single network technology that meets certain demands and fails to counteract the overall needs of the security systems. This problem enables intruders to easily by-pass the surveillance system and create problems in huge crowded arenas. The Major objective of this study is to design a theoretical Framework that is formed as a collaboration of various Network Technologies like Crowdsourcing, Edge Technology, Cloud enabled services, Internet of Things (IoT) along with Machine learning techniques and deep learning algorithms for attaining two major objectives via 1) Enhancement of Transmission speed in terms of Latency, Bandwidth, Transmission Speed with Delay factors; and to enhance integration of technologies in order to accept the video surveillance data in the form of clips, pre-process them using machine learning filters and finally match the objects in video with the trained set of objects using deep learning algorithms. The detailed analysis of all the techniques and their theoretical observations are discussed in the study. Such Frameworks are capable to provide optimal solutions to acquire data in time, store them and process them with optimal accuracy than the existing models.