Award Data

On this effort Toyon Research Corp. and The Pennsylvania State University are developing deep learning-based algorithms for object recognition and new class discovery in look-down infrared (IR) imagery. Our approach involves the development of a hybrid classifier that exploits both transfer learning and semi-supervised paradigms in order to maintain good generalization accuracy, especially when li ...

Signature Research, Inc. (SGR) and Michigan Technological University (MTU) propose a Phase I STTR effort to develop a learning algorithm which exploits the spatio-spectral characteristics inherent within IR imagery and motion imagery.Our archive of modelled and labeled data sets will allow our team to thoroughly capture the variable elements that will drive machine learning performance.The overall ...

Nutronics, Inc. and Montana State University propose to develop and evaluate computational methods for a Volume Digital Holographic Wavefront Sensor (VDHWFS).VDHWFS based imaging offers the potential to provide the equivalent of wide field of view adaptive optics (AO) compensated imaging, but without the added complexity of AO components and hardware.Recent result for coherent imaging developed by ...

Nutronics, Inc. and Montana State University propose to develop an approach for non-linear control of hysteresis and incorporate (if necessary) integrated Multi-Input-Multi-Output real time control with this capability.Our control systems already include a proven high speed real time control approach to determine the optimal set of actuator commands that satisfy inter-actuator stroke limitations.O ...

Adaptive optics (AO) system performance is hindered by the mechanical limits of the deformable mirror (DM), namely stroke limits, interactuator stroke limits, and mechanical resonance.The nature of the multi-in multi-out (MIMO) control system does not lend itself well to notch filters to combat the mechanical resonances, and the stroke limits introduce non-linearities to the system.The traditional ...

The Biomagnetics Micro Dosimetry System (BMDS) program will design, model, and simulate a microdosimetry system that can measure and create a three dimensional map of weak radiofrequency signals in biological organisms. The heart of the BMDS project is the front end called a Quinc, that delivers very sensitive, broad band measurements with high spatial resolution.The Quinc based front end is a val ...

Modern Directed Energy (DE) missions require target engagements at low elevation angles and long ranges.These engagement geometries require propagation through distributed-volume turbulence. To correct for distributed-volume turbulence effects, an estimation of the turbulence along the propagation path is required. Correcting for these image aberrations will improve the quality of the target image ...

Nutronics, Inc. and Montana State University propose to develop a method for characterization of the full Mueller matrix for reflective scattering from a test object. The Complex Object Reflectance Characterization System (CORCS) will initially be designed for laboratory use and characterization of test objects by active imaging to measure both the Mueller Matrix and the target depth associated wi ...

In partnership with the Colorado School of Mines Alliance for the Development of Additive Processing Technologies and with support from the Johns Hopkins University Energetic Research Group, Special Aerospace Services will provide the Air Force with characterization of fully dense Selective Laser Melted GRCop-84 subjected to a variety of manipulations that affect key performance metrics for regene ...

Free Space Optical (FSO) communication systems provide many benefits for satellite communications, including high data rates and low Size, Weight and Power (SWaP) compared to traditional RF communication systems.Additionally, FSO systems operate without RF emissions and are inherently immune to RF interference and jamming.The narrow optical beams and small Field-of-View of the optical receivers al ...