Award Data

US military and intelligence agencies have invested significant resources in data collection and effective search and analytics tools. However, due to increasing amounts of data, finding relevant information has become more difficult. Thus, there is an important need for recommender system technology that pushes relevant un-queried data to analysts through automation and machine learning technique ...

Due to the lack of consistency in existing automated methods for assigning VNIIRS levels to motion imagery, and the overwhelming human resources required to manually assign levels, a new method of automated/semi-automated VNIIRS assessment is needed. In recent years, advancements in deep learning have provided solutions to previously intractable computer vision problems. In many cases, automated d ...

The development of sophisticated anti-access/area denial (A2/AD) capabilities by our adversaries requires us to develop long range capabilities to mitigate this A2/AD threat. Extending the range of Over The Horizon Radars beyond their conventional single hop operating mode will potentially provide coverage out to 10000 km and beyond. We propose combining existing state-of-the art HF radar ray prop ...

NLP pipelines available today are getting robust for general language modeling purposes. But domain-specific data, abbreviations and lingos, and text about time or space still need a lot of tuning and training that are well beyond application of standard tool sets. Deep learning for recommendation engines is quite new, and all recommender systems, in particular for specially trained users, tend to ...

Creating comprehensive geospatial datasets requires that National Geospatial Agency (NGA) analysts spend large amounts of time searching for, delineating, and labeling non-moving features in overhead imagery. This tiresome and tedious task can negatively impact not only the analysts’ work satisfaction but also the resulting data quality. Fortunately, recent advances in gamification and crowdsour ...

The NGA requires an automatic, unsupervised SAR feature extraction (AUFE) technique, that can ultimately be deployed for geospatial analysis, modeling, and target detection. Our proposed “SAR Unsupervised and Robust Feature ExtractoR” (SURFER) solution includes in Phase I: (1) a sound and deterministic assessment of the underlying RF phenomenology and SAR processing theoretical basis for effec ...

An important application for geospatial 3D models is fast transmission and rendering for disadvantaged users who have only a web browser and a limited bandwidth connection. Point cloud models commonly used within the NGA are too large for efficient transmission and rendering. Kitware’s new research on the IARPA CORE3D program has demonstrated procedural building models from point clouds for more ...

Traditional active 3D imaging systems, such as airborne and terrestrial lidar scanners, use a transmitter and receiver typically co-located on the same platform and connected in synchronous communications. However, recent advances in laser, detector, and airborne systems technology have opened the door to smaller, higher-performance and significantly lower-cost airborne lidar systems in which it i ...

Newer techniques in data collection such as Lidar and photogrammetry can provide large quantities of accurate and up-to-date source data models in operational areas, but transforming this often massive amount of raw source data into a lightweight 3D representation that can be quickly consumed by defense customers using a web browser or mobile devices remains a challenging problem. While point clou ...

Volans-I operates a fleet of VTOL, autonomous logistics UAS, capable of autonomous navigation and delivery of mission critical supplies (20+ lbs) over the horizon and from distances in excess of 500 miles. Their systems are able to conduct fully autonomous deliveries in numerous austere conditions including moving target ship-to-ship operations as well as GPS and communications denied environments ...