Parietal Systems, Inc. — Department of Defense SBIR Phase I: ABSTRACT: PSI will apply a novel form of unsupervised learning to the problem of detectin

Description

ABSTRACT: PSI will apply a novel form of unsupervised learning to the problem of detecting and identifying coordinated threats. Particular emphasis is placed on detecting motion based leading indicators of impending"swarming"attacks of small, low cost adversaries. The developed system will be able to not only detect the threats, but also provide operator's insight into the pedigree of this decision and notify operators when there has been a shift in tactics. The purpose of this Phase I effort is to demonstrate proof of concept and to perform an initial robustness analysis of the algorithm against various operating conditions. BENEFIT: The algorithm learns motion behaviors on the fly, and outputs statistics which are needed by track fusion systems, sensor management systems, network detection, and other exploitation systems. The technology will improve ground-target exploitation for surveillance of moving targets (vehicles and dismounts) in complex urban environments for military, law enforcement, emergency management, and security monitoring applications.