SBIR-STTR Award

Physical Sciences Inc. (PSI) proposes to develop an Advanced Learning-Enabled Threat Search (ALERTS) software to significantly enhance detection range and source classification accuracy during search for Special Nuclear Materials and other radioactive threats. The software will implement Machine Learning algorithms for automated extraction of spectral and temporal features by training on sets of gamma spectra. The features distinguishing specific source and the radiological background will be encoded within the algorithm parameters during training and applied during search to classify spectra into relevant source classes or background. The performance of the algorithms will be extensively evaluated with respect to detection sensitivity, classification accuracy and computational efficiency. The evaluation will demonstrate 95% probability of on the move detection from 100 m stand-off range against an 8 kg WGPu source using a 2x4x16 NaI(Tl) detector. The training and validation data sets spanning the relevant search CONOPS and threat configurations will be generated from Government Furnished Data, data available to PSI as well as additional empirically collected spectra. The ALERTS software will also implement communication protocols and data formats to enable integration with existing and planned detection systems, reach-back infrastructure, and user interfaces.

Physical Science Inc. (PSI) proposes to develop advanced computer vision algorithms to automatically extract relevant contextual information from video captured during chemical, biological, radiological, nuclear and counter explosive (CBRN) detections. PSI produces the PERM-OWL and PERM-Mobile systems which provide a gamma and neutron radiation sensor suite, synchronized contextual video, and state-of-the-art algorithms for source detection, identification, localization, and attribution. Ongoing development to integrate chemical and biological sensors is expected to complete in the next 1-2 years. The proposed Contextual Object Real-time Analysis for Lead generation (CORAL) algorithms will analyze attributed source of CBRN and counter explosive materials including people, vehicles, and business to extract relevant information for alert prioritization and adjudication. This capability will significantly reduce the operational burden of deploying CBRN sensors. The majority of sources detected by these sensors are caused by normal background variability, including commercial and industrial activity associated with well-labeled vehicles and businesses. By automatically extracting this information and correlating with other law enforcement datasets, many alerts can be deprioritized or potentially automatically adjudicated. CORAL algorithms will be directly integrated with operationally deployed PERM-Mobile systems to solicit operator feedback and guide capability refinement.