Award Data

Current state-of-the-art object detection algorithms are almost exclusively based on Deep Convolutional Neural Network (DCNN). These algorithms all require a large number of labeled examples for each of the object categories they can recognize. These algorithms will fail for novel objects that only very few or even no prior examples are available. These algorithms are also far less accurate when c ...

This STTR Phase II project proposes development of a statistical relational learning framework for identification of the function of laboratory equipment from imagery. The proposed framework uses semantic reasoning to incorporate evidence from multiple classifiers and feature extractors, domain knowledge, and scene context for scene understanding and labeling. The Phase II effort will focus on dev ...

There is a growing need to accurately characterize nuclear materials not only for nuclear safeguards and nonproliferation treaty verification but also for forensics and provenance. Presently, nuclear material identification requires samples to be collected and sent to laboratories for analysis using large and expensive equipment, such as inductively coupled plasma mass spectrometers (ICP-MS) or se ...

The Nu-Trek team is proposing to develop µDet, a low Size, Weight, and Power (SWaP) read out integrated circuit (IC) for gamma and neuron detectors. µDet offers pulse shape digitization, which in turn enables gamma-neutron discrimination. This is a game changing capability that brings laboratory-level functionality to the field. In Phase I the Nu-Trek Team will develop a baseline design for the ...

Toyon Research Corporation (Toyon) and the University of California, Santa Barbara (UCSB) propose research, development, and demonstration of algorithms and an efficient software prototype for 3D model reconstruction using single images collected via remote sensing. In particular, the effort is focused on processing of high-resolution commercial satellite images for 3D reconstruction of buildings. ...

Intelligent Optical Systems, Inc., in collaboration with Bowling Green State University, proposes to develop a field-rugged, eye-readable indicating spray solution that can immediately detect synthetic opioids over a large area of contamination (i.e., military vehicles, individual protective equipment, clandestine labs, etc.). The proposed chemosensor in a spray solution format will detect multipl ...

Nalas Engineering and Johns Hopkins University collaborated in a Phase I STTR program to study reactive mixtures of HI3O8 and nanocomposite fuels previously developed by the Weihs Group. These fuel/oxidizer mixtures are uniquely able to simultaneously produce heat and biocidal iodine gas, a combination designed to destroy biological weapons. The team at Nalas focused on evaluating conditions for p ...

To Counter Weapons of Mass Destruction (CWMD), DTRA must analyze data from numerous sources about a diverse set of technologies and activities. The extreme diversity in content and the volume of DTRAs data combine to produce one of the most challenging analysis problems in the government. The CWMD mission therefore requires deep analysis - an in-depth understanding of all available data and correl ...

The discovery and commercial development of licensed vaccines often take many years of research followed by years of pre-clinical and clinical development. We propose to assess the feasibility of using a novel irradiation-inactivation technology to develop vaccines more rapidly. The technology utilizes a manganese-peptide complex to protect antigenic proteins from ionizing radiation while allowing ...

A compact laser driver will allow photoconductive semiconductor switches to be used in small EMP simulator "building blocks" (EMPBB). Combined with a battery powered on-board pulsed power system, these EMPBBs will allow the construction of flexible EMP test facilities with nothing more than a single fiber optic timing connection to each EMPBB.