An Integrated Framework for Context-Enabled Discovery of Human Activity from Video

This Small Business Innovation Research (SBIR) Phase I project will constitute design of algorithms, toolsets and interfaces to detect human activity from video and improve operator’s wide area situational awareness of live feeds from multiple aerial and ground sensors in the battlefield. The key innovations in the proposed effort are: 1) automated and robust detection of atomic actions that may span multiple sensors, 2) extraction and exploitation of scene context for improving activity discovery, 3) an interactive activity specification framework for effective threat specification and automatic recognition, tuned towards the requirements of the operator in the battlefield, 4) automatic context-enabled wide area activity recognition by using information from multiple heterogeneous sensors and 5) enhanced user interface based on NASA’s WorldWind geo-browser plug-in for wide area situational awareness of the operator. In addition, metrics for activity detection evaluation will be investigated and a thorough performance analysis of the proposed innovation will carried out. to ensure robustness and This will ensure that a scalable and robust baseline activity discovery system is developed by the end of Phase I.