2021 – Present
This project aims to address the challenge of detecting large concealed metallic weapons, such as rifles, on individuals in crowded environments from a distance, discreetly, and cost-effectively. Traditional security methods often struggle with early detection in dynamic, crowded spaces, making it difficult to identify threats before they become an immediate danger. The project is focused on developing an effective radar design to detect concealed weapon threats in crowded environments. The aim is to create, test, and deploy a network of advanced stationary multibeam antennas. These antennas will use video tracking and imaging enhanced by artificial intelligence techniques to detect and distinguish concealed threats on individuals in crowded spaces.
The project utilizes mm-wave radar arrays combined with video tracking to detect specific metallic threats concealed on individuals in crowds. It leverages inverse synthetic aperture radar (ISAR) imaging, multibeam antennas, and machine learning algorithms to improve detection accuracy. The project seeks to integrate its findings into real-world scenarios by embedding them into the Virtual Sentry Framework (VSF). This integration will enhance situational awareness for stakeholders responsible for protecting soft targets and crowded places. The developed radar system will help detect potential threats, such as concealed weapons, in crowded environments like sidewalks or entryways, allowing for real-time decision-making and threat mitigation.
This project is improving on existing solutions by developing a stationary multibeam antenna system that can simultaneously scan all individuals in its field of view, unlike current systems that focus on one individual at a time. This innovation makes the system more cost-effective, easier to maintain, and more efficient for detecting concealed threats in crowds. Additionally, it incorporates video tracking and inverse synthetic aperture radar (ISAR) imaging to improve threat detection.
In 2024, the project has advanced the development of the stationary multibeam radar system, successfully tested sensor configurations for target discrimination, and created a simulated radar dataset processed with machine learning algorithms. It has also explored industry partnerships to transition its findings into practical use, particularly with companies interested in radar hardware and antenna technology.
The project is working collaboratively with SENTRY Industry Advisory Board member, Leidos, to adapt their radar hardware for concealed threat detection. Additionally, this project collaborates with other SENTRY projects as follows; The Real-Time Management of Adaptive Surveillance and Mitigation project to coordinate video tracking with radar, and with the Protecting Soft Targets: a Game-Theoretic Framework for Multitarget, Multi-Layer Defense Against Strategic Attackers project and the Dynamic Digital Twins for Secure and Smart Civic Space project to provide data that will be needed to improve their models. These collaborative efforts provide access to essential hardware, materials, and experimental facilities needed to test and refine the project’s radar system and help validate the system’s practical relevance and potential for operational deployment.