This project worked to develop methods to efficiently identify, localize, and track a threat event in space and time using “data streams of opportunity.” Sensor data from mobile devices, including accelerometer, audio, and video, were particularly interesting. Researchers envisioned a scenario in which community members (e.g., school, commuters at a transit station, etc.) opt into using a cell phone app capable of collecting and transmitting information to a Virtual Sentry. Just as Google employs data from their Maps users to predict traffic patterns and suggest routes, researchers used the data provided by the community to detect and characterize threats.
The approach built on and extended methods in probabilistic modeling and processing, reduced order signal representation, and dynamic sensing. This project aimed to provide DHS with a principled, adaptive approach to the acquisition and processing of heterogeneous streams of data for threat identification and dynamic characterization.
