Reliable Non-Line-of-Sight Intrusion Detection with Integrated Sensing and Communications Hardware

TL;DR

This paper introduces a millimeter-wave NLOS intrusion detection system using integrated sensing and communications hardware, capable of reliably detecting targets in cluttered indoor environments by leveraging reflections and advanced signal processing.

Contribution

It presents a novel NLOS intrusion detection approach with a proof-of-concept system that combines Kalman and PHD filtering, validated through real-world experiments.

Findings

Reliable detection of targets in NLOS scenarios demonstrated in industrial environments.

The system effectively avoids false alarms even with false peak interference.

Experimental results show robustness and potential for future 6G applications.

Abstract

Non-line-of-sight (NLOS) sensing has the potential to enable use cases like intrusion detection in occluded areas, increasing the value provided by Integrated Sensing and Commu- nications (ISAC) in future 6G cellular networks. In this paper, we present a reliable NLOS intrusion detection system based on a millimeter-wave ISAC proof-of-concept. By leveraging reflections off a large surface, the proposed system addresses the challenge of detecting moving targets in cluttered indoor industrial scenarios where the direct line-of-sight is obstructed. A signal processing pipeline including a tracking stage, comparing a Kalman Filter (KF)- and a probability hypothesis density (PHD) filter-based approach, is applied to detect targets and track movements in NLOS. Experimental validation conducted in the ARENA2036 industrial research campus demonstrates that our system can reliably detect target presence in NLOS while avoiding false alarms. Tests with synthetically generated false peaks further demonstrate the robustness of our system to false alarms. Overall, the results underline the potential of NLOS ISAC as a promising technology for enabling intrusion detection and monitoring use cases.