Real-Time Threat Detection and Mitigation

Objective

This effort leverages data and information to develop decision support systems for enhanced and timely protection of soft targets and crowded places in a real-time, operational capacity.

Supporting Decision Makers in Real-Time

SENTRY researchers are taking a multifaceted approach to achieve this objective. One team is exploring new methods to extract potential threat information from networks of video cameras. The next group approaches the problem by investigating the fusion of different types of anonymous data from crowds and devices to identify and mitigate threats. The last project in this research area is developing responsive and adaptive decision support systems to assist those managing layered security systems to identify appropriate actions effectively. These efforts are working to provide this information to security decision-makers in real-time.

Projects

Real-Time Management of Adaptive Surveillance and Mitigation (November 2021 – April 2025)

This project addressed the critical need for decision-support systems that effectively use multimodal sensors to help decision-makers identify threats, predict crowd behavior, and suggest strategies to influence and guide crowds to safety.

Low Complexity, AI Based Fusion of Crowd-Sourced Heterogeneous Data Streams for Real-Time Threat Detection and Mitigation (November 2021 – June 2024)

This project focused on the detection and characterization of threats utilizing and fusing data streams of opportunity, which could include sensor data from mobile devices.

Real-Time Video Surveillance for Threat Detection and Mitigation (November 2021 – April 2025)

This project aimed to tackle the challenges associated with automatically analyzing videos from extensive camera networks in crowded environments.

An Artificial Intelligence-Driven Threat Detection and Real-Time Visualization System in Crowded Places (January 2024 – April 2025)

This project addressed the challenge of timely threat detection in crowded public places by developing human-in-the-loop gun detection solutions.

End-to-End Graph-Agnostic Real-Time Evacuation Routing to Protect Soft Targets During Active-Shooter Scenarios (January 2024 – April 2025)

This project aimed to tackle the challenge of ineffective decision-making during active shooter incidents in public places, such as schools.

Real-Time Management of Threat Detection and Mitigation