Demonstration of Person Presence Detection Using 5G Synchronization Signals on SDR Testbed

• Main Authors: Hulede, Ian Ellis L, Dwivedi, Manu, Venegas, Oscar, Enayati, Saeede, Shunmugam, Akhash Subramanian, Mukherjee, Amitav
• Format: Conference Proceeding
• Language: English
• Subjects: 5G mobile communication; Atmospheric modeling; channel state information; Data mining; Data models; Deep learning; Feature extraction; Integrated sensing and communication; Integrated Sensing and Communications; Pipelines; SSB; Synchronization; Wireless communication
• ISSN: 2155-7586
• DOI: 10.1109/MILCOM61039.2024.10773810

The rapid evolution of wireless communications in the Fifth Generation (5G) has seen many practical use cases. One important use case, which is a potential candidate for the Sixth Generation (6G) is sensing and tracking and this holds much promise in the development of Integrated Sensing and Communications (ISAC). This paper focuses on the utilization of the 5G synchronization signal blocks (SSBs) which are emitted periodically to perform detection. Our post-processing involves extracting Channel State Information (CSI) estimates from the In-phase / Quadrature (IQ) samples collected over the air interface from a 5G Base Station (BS) to a User Equipment (UE) and use this data as input into a deep learning model to perform person presence detection. This demonstration provides a complete pipeline showcasing data collection, post-processing, model classification and visualization for person detection. Detection can be achieved for other objects such ground or aerial vehicles etc. but this paper will be focused on person detection.