Difference Imaging-Based Parking Lot Surveillance in Multi-RIS-Aided Collaborative ISAC System

TL;DR

This paper introduces a novel multi-RIS-aided collaborative ISAC system that uses difference imaging and compressed sensing to improve parking lot surveillance, overcoming traditional camera and sensor limitations.

Contribution

It proposes a new wireless sensing approach utilizing multiple RISs and difference imaging with CS algorithms for accurate parking occupancy detection.

Findings

High-accuracy parking occupancy detection achieved

Collaborative RISs improve detection rate

Wireless sensing overcomes lighting and cost limitations

Abstract

Parking lot surveillance with integrated sensing and communication (ISAC) system is one of the potential application scenarios defined by 3rd Generation Partnership Project (3GPP). Traditional surveillance systems using cameras or magnetic sensors face limitations such as light dependence, high costs, and constrained scalability. Wireless sensing with reconfigurable intelligent surfaces (RISs) has the ability to address the above limitations due to its light independence and lower deployment overhead. In this study, we propose a difference imaging-based multi-RIS-aided collaborative ISAC system to achieve parking lot surveillance. In a parking lot, the presence of vehicles induces impacts on wireless environments due to scattering characteristic variation. By delineating the parking lot into a two-dimensional image with several grid units, the proposed system can capture the variation of their scattering coefficients in free and occupied states. The variation between these two states is sparse, which can be captured through compressed sensing (CS)-based imaging algorithms. Additionally, we collaboratively employ multiple RISs to enable higher surveillance performance. Experimental results demonstrate that our method can achieve high-accuracy parking occupancy detection, and the employment of collaborative RISs further enhances the detection rate.