Data Fusion Handoff Navy SBIR FY2006.2 Sol No.: Navy SBIR FY2006.2 Topic No.: N06-109 Topic Title: Data Fusion Handoff Proposal No.: N062-109-0659 Firm: Toyon Research Corp. 6800 Cortona Drive Goleta, California 93117-3021 Contact: Charlene Ahn Phone: (805) 968-6787 Web Site: www.toyon.com Abstract: There are many applications in which target tracking systems rely on multiple sensors to track objects over long durations to achieve situational awareness. In particular, Naval missions, such as those that support Maritime Domain Awareness, rely on a collection of sensors that typically have disjoint coverage. The objective of such a system is continuous tracking of surface vessels. across large geographical regions. Suppose a vessel is tracked while in the field-of-view (FOV) of a particular sensor. The vessel leaves the FOV of that sensor and, after a time gap, enters the FOV of a second sensor. While the vessel will be tracked upon entering the FOV of the second sensor, any intelligence gathered on that vessel prior to the coverage gap will be lost unless the system correctly recognizes that the vessel is the same vessel that left the first sensor's FOV and entered the second sensor's FOV. Toyon Research proposes to develop a collection of algorithms to support both the decentralized communication and fusion required by such a sensor network in order to maintain a constant track ID on any particular vessel. Toyon will demonstrate the system in a simulated scenario defined in cooperation with Navy personnel. Benefits: The algorithms developed on this effort will support a distributed sensor architecture in which a collection of sensors with typically disjoint field-of-views (FOVs), though some may have overlapping FOVs, are used to keep track of objects that move around within the sensor network. As the tracked objects pass from one sensor's FOV to another, communication between the sensor nodes enables continuous tracking of the objects. The sensor nodes alert one another when the tracked objects might enter another sensor's FOV. Additionally, the sensor nodes pass track information which allows a sensors to identify objects that come within its FOV as the same object that was in another sensor's FOV. Such a system has wide applicability to a variety of Intelligence, Surveillance and Reconnaissance and Security missions, for example, monitoring surface vessels for terrorist activity or drug-trafficking or for video surveillance systems that must track objects in and out of different regions. Return