Internet of things (IoT) for video surveillance applications
Video surveillance has become ubiquitous due to the increasing security requirements in every sphere of life. The future video surveillance system (VSS) possesses great challenges in various applications, such as intelligent urban surveillance systems and smart cities. In these applications, we need to deal with the fast-growing number of surveillance nodes which introduce several constraints, e.g., high latency, high bandwidth, high energy consumption, and CPU and memory usage. To address these issues, the Internet of video things (IoVT), which is a part of the Internet of Things (IoT), can be a solution. The IoVT is composed of visual sensors (i.e., cameras) connected to the internet. Unlike conventional systems, the VSS under an IoVT framework provides multiple layers (i.e., edge, fog, cloud) of communication and decision making by capturing and analyzing rich contextual and behavioral information. The goal of this thesis is to investigate the design framework of IoT-based future smart video surveillance systems and to evaluate its efficiency in terms of agility, scalability, and resources, such as energy, bandwidth, memory, CPU usage, and storage. To address these requirements, firstly, the characteristics of IoVT based VSS architecture should be defined. Secondly, this architecture needs to choose appropriate communication protocols. Finally, the processing algorithms and computational loads should be distributed among different layers congruously. Since an appropriate application layer protocol (ALP) can help in alleviating the challenges of future VSSs, the selection of ALPs is important for IoVT-based systems. Therefore, to perform the first task of the thesis, a generic architecture of an IoVT-based VSS is presented with proper design explanation. The second task is done by conducting a comparative analysis of several IoT ALPs, such as MQTT, AMQP, HTTP, XMPP, CoAP, and DDS, with real-time experimentation. This analysis will assist the users to choose the appropriate ALPs in various surveillance applications and determine their suitability at different nodes of the IoVT framework. The final task involves the design and implementation of a distributed Internet of Things (IoT) framework called IoT-guard, for an intelligent, resource-efficient, and real-time security management system. This system, consisting of the edge-fog computational layers, aids in crime prevention and predicts crime events in advance in a smart home environment (SHE). The IoT-guard detects and confirms crime events in real-time, exploiting Artificial Intelligence (AI) and event-driven approach to notify crime data to the protective service and police unit for taking instant actions, while saving a significant amount of resources, such as energy, bandwidth, memory, and CPU usage. IoT-guard laboratory testbed prototype is implemented and evaluations on its efficiency is performed for a real-time security application. The outcomes show better performance of the proposed system in terms of resource-efficiency, agility, and scalability over the traditional IoT surveillance systems and state-of-the-art approaches
Internet of Things, Application layer protocols, Internet of Video Things (IoVT), Video Analytics, Video Surveillance, convolutional neural network, motion detection, gun-knife detection, real-time security.
Master of Science (M.Sc.)
Electrical and Computer Engineering