Award Data

We propose to develop a fillet identification methodology using visible imagery that can be collected and processed on commodity hardware such as modern smartphones, dramatically increasing the availability of fillet identification technology. In order to accomplish this, we will gather an annotated data set of fillet pictures, traceable to verifiable whole fish images. Using these pictures, we wi ...

Natural disasters and other severe weather events have the potential to create loss of life and damage property on a large scale. Preparing for and responding to these incidents is a complex, multi-phase process. NOAA’s 2019-2022 Strategic Plan is to achieve the vision of a Weather Ready Nation to reduce the impacts of weather, water, and climate events and harness cutting-edge science, technolo ...

Volatile organic compounds (VOCs) are emitted from a wide variety of biogenic and anthropogenic sources. VOCs transform in the atmosphere, forming ozone and oxygenated VOCs (OVOCs), which in turn can form fine particulates or condense onto preexisting particulate matter (PM). Both ozone and fine PM are deleterious to human health and alter the Earth’s climate. Measurements of (O)VOCs are necessa ...

To improve the identification and detection of radio-logical materials, we propose a hybrid supervised learning and unsupervised machine learning approach to reduce the false positive rate, increase the accuracy and throughput, and augment the capabilities of the human operators. At the end of the Phase I, we will have a machine learning algorithm that is trained to recognize a variety of nuclear ...

Physical Sciences Inc. (PSI) proposes to develop an advanced machine learning (ML) algorithm to detect threat-based anomalies in gamma-ray spectra in real-time. If a network of distributed R/N sensors is employed, the algorithms will also be capable of tracking such anomalies through the network. The Radiation Anomaly Detector (RAD) will be packaged with PSI’s award winning Poisson Clutter Spli ...

There is a need for low cost, high performance gamma-ray detectors for national and homeland security applications for detection, identification and localization of special nuclear materials. Common detectors used in this application include scintillators coupled to photomultiplier tubes or silicon photodiodes, and semiconductor detectors like cadmium zinc telluride. Semiconductor detector offer ...

Perovskites are rapidly emerging as attractive radiation detectors. The goal of this program is to develop a multi-modal detection sensor based on perovskite materials. The developed detector will be integrated with a high resolution active pixel array and the pixel signals will be processed by high speed electronics to create scene images of different radiation types.

Systems & Technology Research (STR) proposes to develop Vehicle Reidentification-Aided Network Topology Inference (VRANTI), a novel system for estimating proximity network graphs of traffic cameras to facilitate intelligence applications such as tracking and monitoring of traffic systems. Network inference will be performed using statistical analyses of features extracted from camera video feeds, ...

The flow of equipment, repair parts, and other materiel to the Warfighter is critical to his or her success in the field. As a result of this critical need for materiel, DLA employees must contend with the difficult task of promoting and encouraging the reuse and disposition of excess property. With the advance of e-commerce sites and modern networks, searching a catalog for property has become a ...

There is limited domestic production of nickel superalloys, used in propulsion, turbines, heat exchangers, exposing the military to risk of overdependence on foreign sources. End-of-life parts and shop scrap represent an untapped source of superalloys that can serve as a domestic supply, provided they can be converted into material with properties meeting specs for original parts manufacturing. Th ...