Persistent Electro-Optical/Infra-Red (EO/IR) Wide-Area Sensor Exploitation

Toyon proposes to develop high-performance algorithms and real-time software for exploitation of persistent wide-area high-resolution video-rate imaging information in accordance with AFRL’s pixelpedia concept. The focus in Phase I is on demonstrating feasibility of key algorithm components of the architecture, including georegistered dense 3D reconstruction based on multiple view geometry, construction of statistical model components of the pixelpedia in the georegistered 3D framework, and extension of advanced real-time parallax mitigation algorithms to leverage the 3D and statistical data. While development of some algorithm components of the proposed architecture is reserved for a potential Phase II effort, other components can be integrated as they become available from other sources, via collaboration with AFRL researchers and other contractors. As part of the Phase I feasibility demonstration, Toyon proposes to demonstrate automated detection and tracking using a data source of interest to the government. This demonstration will incorporate the new algorithm developments on this project, and leverage existing detection and feature-aided multiple target tracking algorithms and real-time software developed by Toyon for AFRL and other customers. The final report will include algorithm details, evaluation results, and recommendations. BENEFIT: The successful completion of this research and development will result in significant improvements in real-time exploitation of persistent wide-area high-resolution video-rate EO/IR imaging sensors, including automated target detection, tracking, and identification in dense and cluttered urban environments. Secondary technical benefits will include the ability to automatically calibrate imaging sensors using flight data, rapidly create high-fidelity georegistered 3D models of large scenes, perform on-line learning of georegistered statistical background models, and mitigate the effects of parallax in change detection. This technology would have direct applications in deployed and current developmental wide-area persistent surveillance EO/IR sensor systems, as well as in a broad range of Air Force and other DoD surveillance systems, including air-, ground-, sea-, and space-based platforms. One possible opportunity for transition of the developed technology is into the Distributed Common Ground System (DCGS) being developed by Raytheon, and Toyon has discussed this proposal with Raytheon and obtained a Letter of Support. In surveillance applications, geo-registered 3D data provides context for the sensor operator, as well as exploitation system operators. Highly precise 3D geo-registration is required for multi-look change detection to locate emplacement of possible structures of interest or of threats such as IEDs, and on shorter time scales to perform moving-target detection. The technology could also be used to provide improved realism in personnel training, and even in computer gaming.