Award Data

In this proposed Phase II effort we will implement a software framework that will reduce the time required to annotate large image/video datasets by a factor of 100x while also reducing the data necessary to train state of the art computer vision models by up to 80%. Our strategy combines several elements and ideas. First, we have developed a sub-tile based a priori theory of how and why CNNs can ...

In Phase I we developed and demonstrated a bi-directional, monolithic, High-Speed, Electro-optic shutter for Range Gated Imaging. While meeting the majority of the key performance parameters for Range-Gated Imaging at high Pulse Repetition Frequency, improvements can be achieved in transmission, contrast and reliability. The Phase Ii activity begins with a upgraded Electro-optic Shutter incorpora ...

High performance infrared photodetectors and light sources that span infrared wavelengths from 2 to 14 microns and beyond are critical to DoD. At the longer wavelengths these devices demand stringent cooling requirements, which add size, weight, power consumption and cost. In this program we are developing tunnel diodes based on epsilon near zero (ENZ) metal-insulator-metal (MIM) rectenna structur ...

Project FORCIS investigates solutions to the challenging problem of few-shot object detection. FORCIS leverages synthetic training data generated by simulation engines which are dynamically parameterized to maximize utility to a downstream deep-learning algorithm. We explore this approach, inspired by advances in the Reinforcement Learning (RL) branch of machine learning (ML), and contrast it agai ...

This effort will extend the RL-ICE capability for low-shot object detection to operate with zero real data within the MWIR band (zero-shot learning). Our goal is to 1.) mature our software, 2.) maximize the performance benefit of synthetic data in training an object detector and, 3.) assess the trade-space of real vs synthetic data by comparing performance to a detector trained on fully real data. ...

Ultra-Wide bandgap materials such as GaN and Ga2O3 are emerging as preferred materials in high power applications due to their high breakdown field. The thermal dissipation is poor in both those materials due to low thermal conductivity. A high thermal conductivity material such as SiC is used as a growing substrate, however, the thermal conductivity is still limited due to defects in the interfac ...

Modular continuous processes are the future of chemical process development and chemical manufacturing. They enable faster time to market, improved safety, lower costs, and enhanced flexibility over traditional batch processes. Proposed work under this topic includes the design of a modular system for synthesis of many energetic materials, energetic precursors, and critical chemicals. Modules that ...

A critical SWAP-C requirement for future IR systems is the ability to operate at room temperature (RT). While some IR devices such as microbolometers operate at RT, their speed and detectivity is compromised. Therefore, the functionality of IR platforms can still be improved. Tunnel diodes based on epsilon near zero (ENZ) metal-insulator-metal (MIM) rectenna structures have the potential of disrup ...

TP Engineering personnel have extensive experience with electro-optic systems and high Pulse Repetition Frequency (PRF) Laser systems. We have detailed knowledge of Pockels cell systems enabling active gated imaging through foliage at PRF 100 kHz PRF. Such systems can dramatically improve and protect Geiger-mode LIDAR by both controlling the transmitter output and gating out unwanted return lig ...

Deep Convolutional Neural Networks (DCNNs) have become ubiquitous in the analysis of large datasets with geometric symmetries. These datasets are common in medicine, science, intelligence, autonomous driving and industry. While analysis based on DCNNs have proven powerful, uncertainty estimation for such analyses has required sophisticated empirical studies. This has negatively impacted the effect ...