Efficient Person Reidentification for IoT-Assisted Cyber–Physical Systems

The main objective of this study is to propose a cyber–physical system (CPS)-based person reidentification (P-ReID) framework for smart surveillance. The Internet of Things (IoT)-based interconnected vision sensors in smart cities are considered essential elements of a CPS, and contribute significantly to urban security. However, the reidentification of targeted persons using emerging edge AI techniques still faces certain challenges. To improve efficiency at the edge and overcome the traditional sensing of video cameras, we employed an AI-based P-ReID framework for CPS that is functional in IoT environments. In addition, we present dual attention dilated network (DADNet), which integrates an energy-efficient convolutional neural network (CNN) with a self-attention module to substantially improve the person matching probability. Furthermore, we applied dual feature fusion to intelligently integrate discriminative and robust features using early and late fusion strategies that allow DADNet to significantly consider the foreground and marginally utilize the background information. Furthermore, we impose diversity orthogonality regularization over several CNN layers, which boosts the performance of DADNet, resulting in an appropriate usage over IoT networks. A comprehensive set of ablation studies, comparison with other state-of-the-art approaches, and a time complexity analysis confirm the strength of our DADNet for reidentification tasks in AI-enabled IoT settings that are well suited for a CPS.

I. Introduction

The network systems of cyber and physical elements are mainly composed of cyber–physical system (CPS) that interact in a response cycle with the assistance of human involvement, interactions, and utilization. The demand for CPS has gained wide attention in various fields owing to a focus on data communication, data handling, and the integration of information systems [1]. CPS is currently used in a variety of areas, such as transportation, healthcare, and automotive systems, directly impacting our daily lives. A CPS is designed to generate complex systems by connecting individual components. Data are commonly gathered using a visual sensor and transferred to the control system through a network without any human intervention [2]. However, CPS is incurring significant security challenges as the cyber and physical worlds become more interconnected. This means that both the systems and interconnections among CPS subsystems are becoming more complex. A CPS is composed of three layers: 1) a perception layer; 2) a transmission layer; and 3) an application layer the most interactive [1], [3].