GEOGENX: target disambiguation through spatiotemporal context

Satellite platforms play a critical role in the modern defense and intelligence infrastructure, providing timely, detailed, and readily available imagery to support U.S. national security. An ever present and fundamental requirement for this type of data is automated target detection and recognition, helping to quickly locate and correctly identify targets from vast quantities of image data. Despite significant progress in the application of deep learning techniques towards this issue, deep learning algorithms are generally unable to offer the precise fine-grained object classification necessary for many critical analyst use cases. The Phase II SBIR program consists of research and development to mature, extend, exceed, and transition promising capabilities in object disambiguation to program stakeholders. This program will seek to automatically fit 3D models to detected targets to enable fine-grained target classification and segmentation without the need for additional network training. These techniques successfully adapt to realistic operational scenarios such as panchromatic non-orthorectified imagery, with the potential for adaptation to additional data sources such as National Technical Means (NTM) electro-optical (EO) imagery. The targeted audience is the community of image analysts that currently monitor overhead imagery to produce intelligence reports such as Order of Battle, indications and warnings, and science and technology assessments. The VSI team is uniquely suited to this project, offering expertise in remote sensing, object detection, 3D reconstruction, and machine learning; extensive experience in the development of innovative software solutions for challenging defense and intelligence problems; and a thorough understanding of the needs of image analysts across the defense and intelligence community.