Visual recognition for IoT-based smart city surveillance

Abstract

The rapid evolution of edge technology and Internet of things technology, combined with sophisticated facial recognition systems, has catalyzed a transformative paradigm in urban surveillance, culminating in the emergence of smart cities. This thesis delves into the intersectionality of Internet of things and facial recognition methodologies within the urban milieu, examining their synergistic integration in the construction of intelligent, responsive, and secure urban environments. The exploration encompasses a comprehensive analysis of the technological intricacies inherent in Internet of things sensor networks and facial recognition algorithms, while critically evaluating their ethical, legal, and societal implications. The dissertation provides an exhaustive overview of the deployment of Internet of things devices, spanning from embedded sensors in urban infrastructure to wearable gadgets, facilitating real-time data acquisition and analysis. When coupled with facial recognition technologies, this data forms the fundamental backbone of smart city surveillance, presenting distinctive opportunities for urban management, security enhancement, and resource optimization. This research meticulously scrutinizes challenges related to data privacy and algorithmic biases, proffering innovative solutions and policy frameworks to effectively address these concerns. Moreover, the study investigates the integration of edge computing, optimizing data processing and analysis for resource-constrained IoT devices. In addition to critical examination, attention is directed towards recent advancements in machine learning and artificial intelligence, elevating the accuracy, resilience, and real-time processing capabilities of facial recognition systems internet of things and edge technology based solutions. Showing a theoretical understanding and practical implementation of smart city surveillance real world application.