Award Data

Deep Neural Networks have become ubiquitous in the modern analysis of voluminous datasets with geometric symmetries. In the field of Particle Physics, experiments such as DUNE require the detection of particle signatures interacting within the detector, with analyses of over a billion 3D event images per channel each year; with typical setups containing over 150,000 different channels.  In an ...

In its effort to provide necessary intelligence and analysis, the National Geospatial-Intelligence Agency (NGA) utilizes extensive traffic camera systems. However, the large amount of data overwhelms both analysts and existing processing methods. In order to provide a better understanding and reduce the search space for common problems such as target tracking, it is necessary to extract the camera ...

We propose to develop a theoretical understanding of the relationship between intrinsic geometric structure in both training and latent data and characteristics of functions learned from that data for deep neural network (DNN) architectures. Along the way we propose to also understand the structure of the neural networks that are best trained on a given data set. Both of these theories will lead t ...

Building interpretable, composable autonomous systems requires consideration of uncertainties in the decisions and detections theygenerate. Human analysts need accurate absolute measures of probability to determine how to interpret and use the sometimes noisy resultsof machine learning systems; and composable autonomous systems need to be able to propagate uncertainties so that later reasoningsyst ...

NGA seeks an innovation to fully automate processes that recover camera orientation parameters, specifically for ground-based “photo” (aka image) and video frame use cases. The ability to use these ground-based systems represents an enhanced aspect to traditional photogrammetry, and in many regards, folding in hand-held systems, and considering the nuances associated with these collects, is ye ...

We propose to build ARGON, the ARet Ground-to-Overhead Network. The network will ingest analyst-supplied ground-level imagery ofobjects and retrieve instances of those objects in overhead collections, providing tips back to the analysts. A proprietary method of trainingthe network, leveraging in-house capabilities, data sources, and tools, will be critical to its success. During Phase I, we will p ...

To address the NGA need for algorithms that fuse observables from over-flight operations and from ground sources to automatically estimatethe degradation of urban environments due to battle damage or natural disasters, Intellisense Systems, Inc. (ISS) proposes to develop a newBayesian Urban Degradation Assessment (BUDA) software system. It is based on the integration of multiple damage assessment ...

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 ...

To address the National Geospatial-Intelligence Agency (NGA) need for overhead imagery analysis algorithms that provide uncertaintymeasures for object recognition and aggregation, Intellisense Systems, Inc. (ISS) proposes to develop a new Variational Object Recognition andGrouping Network (VORGNet) system. It is based on the innovation of implementing a Bayesian convolutional neural network (CNN) ...

Toyon Research Corporation proposes to research and develop algorithms for low-shot object detection, adapting popular techniques to address the complexities inherent in ATR for remote sensing. Traditional object detection algorithms rely on large corpora of data which may not be available for more exotic targets (such as foreign military assets), and therefore, traditional Convolutional Neural Ne ...