On December 16, Palo Alto, CA-based Orbital Insight announced that it has been awarded a Phase II Small Business Innovation Research (SBIR) contract from the National Geospatial-Intelligence Agency (NGA). The Phase II contract is a result of the successful outcome of Orbital Insight’s Phase I collaboration on the use of synthetically generated data for training object detection models in electro-optical imagery.
Orbital Insight will partner with Washington, D.C.-based Rendered.ai and the University of California, Berkeley to deliver a first-of-its-kind computer vision model to detect novel classes of objects trained on little or no real examples of objects. The project will use synthetic imagery that has been optimized via domain adaptation to train the model so that it can detect instances of the novel classes in the wild. The project will lead to a better understanding of how the model is incorporating both synthetic and real training data to generalize to real test data, and ultimately lead to better training techniques when using mixed training data.
“There is an influx in imagery and data that humans can’t analyze with eyesight alone,” said Kevin O’Brien, CEO at Orbital Insight. “While our national security relies on this data, computer vision can help provide the right answers. We’re honored to have been awarded this Phase II contract and continue our partnership with the NGA. The results of this project will be instrumental for the defense intelligence community.”
The NGA delivers advanced geospatial intelligence that provides a decisive advantage to policymakers, warfighters, intelligence professionals and first responders. Orbital Insight has previously collaborated with the United States Air Force’s AFVentures Strategic Financing in multiple SBIR phases.
Orbital Insight’s flagship GO platform is purpose built for the Intelligence Community to deliver insights in a cloud-agnostic, secure and readily deployable environment. The technology supports critical activity-based intelligence by helping spot trends buried within billions of data points, such as economic patterns associated with global ports, airports and real estate.
Source: Orbital Insight
Help IC News continue to bring you breaking news from across the IC and IC contracting landscape. Join our paid subscribers today.
By 
