Award Data

Satellite Imagery in Geospatial Intelligence (GEOINT), in conjunction with imagery intelligence (IMINT), geospatial information, and other means of gaining intelligence, has greatly improved the potential of the warfighter and decision makers enabling them to gain a more comprehensive perspective, an in-depth understanding, and a cross-functional awareness of the operational environment. The Artif ...

The team of Signature Research, Inc. and Michigan Technological University will develop and demonstrate methods and metrics to evaluate the performance of machine learning-based computer vision algorithms with low numbers of samples of labeled EO imagery. We will use the existing xView panchromatic dataset to demonstrate a proof-of-concept set of tools. If successful, in Phase II, we will extend t ...

Detecting relevant objects of interest in large datasets using artificial intelligence techniques is very appealing. However, most state of the art approaches use deep neural network techniques -- requiring millions of human annotated training examples. These datasets mostly come from academia and don’t transfer well to novel domains. Even with the use of smaller annotated datasets and an applic ...

We propose a novel software system for remote nuclear detection and classification. First, we propose to apply GADRAS or GEANT4 to generate training data for different combinations of nuclear materials and detectors. The training data contain spectral shapes of different detector responses. Second, we propose to use a Continuous Wavelet Transform (CWT) based technique for peak detection in spectr ...

NGA seeks to incorporate Artificial Intelligence (AI) and Machine Learning (ML) to Intelligence, Surveillance and Reconnaissance (ISR) missions in the aim to capture fleeting targets, thus a large amount of dynamic scenes with accurate target motions and behaviors will be needed for training and performance evaluation. Traditional microscopic model based approach for vehicle activity simulation i ...

The Video National Imagery Interpretability Rating Scale (VNIIRS) defines different levels of interpretability based on the types of tasks an analyst can perform with videos of a given VNIIRS rating. DoD users of motion imagery rely on NGA to rate the interpretability of motion image clips and understand the factors affecting the VNIIRS of operational imagery. To develop and validate and verify an ...

Intelligent Automation Inc. (IAI), along with our collaborators propose to develop a video tagging and statistics toolkit called VAST-CQA (Video Annotation and Statistics Toolkit for Crowdsourcing Quality Assessment). The key idea of the proposed approach is to provide a video quality annotation toolkit which reduces the effects of bias, subjective assessment and other human factors using a set of ...

Video analysts have to sift through voluminous video data to extract information of interest. The NGA uses the VNIIRS scale to rate videos with subjective interpretability. VNIIRS rating provides a meaningful way of organizing video browsing and search. Manually annotating videos with VNIIRS rating however, is very tedious. We propose to develop an automated tool which uses several cues such as mo ...

To address NGA’s requirements, Sonalysts’ team of world-class experts in underwater optical communication proposes development and implementation of the Precision Optical Navigation Transceiver for Undersea Systems (PONTUS). PONTUS will transfer navigation information from an Underwater Navigation Beacon (UNB) to an Unmanned Undersea Vehicle (UUV) in an electromagnetic-spectrum-denied (e.g., G ...

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 ...