Motion Based Video ATR

The goal of our proposed research is autonomous real-time detection, classification, and location of targets from a video image. DTS Inc (www.dtsits.com) proposes to combine its robust software in real-time video tracking and classification of vehicles forthe transportation industry with a new classifier (From our subcontractor, Quasar International, www.quasarintl.com) to develop a true ATR video system . This classifier has been used extensively in a broad variety of applications fromnon-destructive-inspection (NDI) of manufactured parts (resonant inspection) to a discovery engine for large gene expression and protein data sets. This new classifier will allow us to classify vehicles in a larger multidimensional space, which willdramatically reduce false positives and yield a high probability of correct classification and identification. All of the systems operate using commercial-off-the-shelf hardware and computers. The development of a vehicle classification system on a PhaseI contract will be of immediate use within the transportation industry. It will greatly improve the capability for vehicle classification from a non-road-intrusive sensor. It will form the basis for developing the ATR capability and putting the system onan airborne platform. The ability to classify and track vehicles has a wide variety of applications in the security and surveillance industry for both government and commercial organizations. This system will enhance the capability of security systemsat military bases or other high-value-targets.