Award Data

Toyon Research Corp. and the Penn State Univ. propose research and development of innovative algorithms for classifying objects and activities observed in high-dimensional data extracted from multi-sensor motion imagery. The proposed algorithms include novel feature clustering techniques to enable effective characterization of intra-class and inter-class appearance variations in datasets containin ...

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 introduction of computer vision in precision-guided ammunition will potentially increase their targeting capabilities, in particular for moving targets such as tanks, vehicles and mobile command posts. EO/IR cameras offer a relatively inexpensive, low-SWaP payload solution which, combined with latest advances in SIMD hardware (GPUs), are finally starting to allow running sophisticated visual g ...

We aim to develop data-driven heterogeneous data fusion approaches for unanticipated event/target detection, which will be more robust and immune to model mismatch problems encountered by model-based approaches. Considering the low intrinsic dimensionality of the sensor data, we propose several data-level fusion approaches based on some state-of-the-art dimensionality reduction techniques. For lin ...

The Air Force is seeking solutions for a sun-tracking millimeter wave radiometer to measure atmospheric attenuation over a high dynamic range. The V- and W- bands have rarely been used for space communications and telemetry applications, but rapidly increasing government and commercial bandwidth needs will require future solutions within these bands. Our team, comprised of experienced scientists, ...

This Phase I STTR proposal describes the development of a dual frequency millimeter-wave sun tracking radiometer designed to measure total atmospheric attenuation from ground level to the top of the atmosphere.The suns brightness temperature, which is on the order of 10,000K at millimeter-wavelengths, provides an ideal background reference allowing high dynamic range estimation of total atmospheri ...

To address the challenge of long-term tracking, through extended occlusions and significant appearance changes, we propose to continue developing DC-CAT, a Deep Convolutional neural network (CNN) based Confuser-Aware high value target (HVT) Tracker.The DC-CAT system combines a state-of-the-art CNN-based adaptive HVT tracker with a CNN-based pre-trained generic target detector, in a deep-feature-ai ...

A diagnostic is proposed for obtaining instantaneous three-dimensional volumetric distributions of density in a flow field at velocities ranging from subsonic to supersonic. Two variants of laser-based Rayleigh scattering will be investigated, each of wh...

A diagnostic is proposed for obtaining instantaneous three-dimensional volumetric distributions of density in a flow field at velocities ranging from subsonic to supersonic. Multiple Sheet Filtered Rayleigh Scattering (MSFRS) will be developed, which enables a series of two-dimensional images to be rapidly obtained making up a volumetric image while suppressing background scattering from wind tunn ...

Automatic target recognition (ATR)the identification of a potential target based on signatures in sensor datais fundamentally a question of information content. While ATR has been studied for decades, it remains a challenge because multifarious tar...