Authors
Nour Ahmed , Mariam Hesham, Samiha Hesham, Sandra Fares, Eng. Lobna Shahen and Dr. Islam Tharwat
Publishing Date
October 31, 2020
Abstract
Surveillance systems are of vital importance for the development of smart cities. These systems can be considered vision organs of such cities. It is expected that a huge amount of data (Big Data) will be generated in smart cities. Therefore, to ensure the safety of its citizens, it is important to provide an efficient and real-time analysis of these data to get real-time responses, when catastrophic events occur. Accordingly, transmitting this massive data to the cloud, to be processed, is relatively slow. Therefore, the purpose of this project is to implement a fog/edge computing-based surveillance system to offer real-time data processing. When surveillance videos capture an incident, the data get transferred to the edge for processing. Moreover, a rapid response is then provided to properly handle the occasion. Furthermore, despite tackling scalability obstacles, the system should handle privacy-sensitive data to overcome the privacy challenges in smart cities.
1.1 Background
A video surveillance system is a crucial component in the development of smart cities. Where it is useful for crime prevention, terrorist or forensic evidence detection, and traffic monitoring. However, the old traditional surveillance cannot accomplish these approaches, that’s why smart surveillance systems with smart detection modules were introduced and always in enhancements till now. However, implementing a citywide smart video surveillance system involves many challenges. A large number of cameras have to be deployed across the city, producing large amounts of data and information every day. Besides, storing and enabling access to video devices and data at this large scale, in both real-time and on-demand manner, demand more computing and storage resources than traditional video surveillance systems. These challenges have to be addressed to maximize the effectiveness of smart video surveillance.
Cloud computing was proposed then to solve some of those issues, and it proved to be efficient but with the growth of data, it could not accomplish the desired results and the fast response due to the possible delay of transmitting the data to and from the cloud server. Moreover, it could not solve the privacy and security concerns. So, fog computing technology is recently introduced as a promising one to handle the current challenges of the surveillance systems development for smart cities.
1.2 Motivation
Since smart cities utilize IoT devices in recent times, in order to improve their infrastructure, numerous amounts of data get generated at a rapid rate. Passing data to the cloud is unfavorable when dealing with surveillance systems, as these systems require urgent and instant responses to avoid misfortune events. Therefore, it is necessary to procure a strategy that will assist in managing and processing data effectively in a short period of time. Fog computing is a recently proposed solution for this problem. Instead of transferring data to the cloud, it gets transferred to the fog for real-time data processing.
1.3 Problem Statement
One of the challenges that face surveillance systems in smart cities is Big data, as the smart city involves huge amount of cameras in 24/7 mode to cover the whole city. Each camera records a massive amount of video and audio data to be processed. To handle such massive data, it is essential to provide a way to get real-time data processing analysis efficiently. Cloud computing has been utilized to perform data processing analysis, leading to slower performance. Therefore, fog computing is essential for real-time data processing analysis with high performance and low latency.