Charles River Analytics received follow on funding from the U.S. Army’s Aviation and Missile Research, Development and Engineering Center (AMRDEC) to continue developing the Evaluation Testbed for ATD/T Performance Prediction (ETAPP). ETAPP predicts the performance of automatic target detection/tracking (ATD/T) algorithms, constructing models of performance prediction that are more comprehensive than those commonly employed (such as quick-look models), and are less computationally expensive than using detailed exhaustive simulation.
Dr. Scott K. Ralph, a Senior Scientist at Charles River Analytics, explained ETAPP’s benefit to ATD/T performance prediction: “ATD systems process imagery to detect and locate targets in imagery in support of a variety of military missions. Accurate prediction of ATD performance would assist in system design and trade studies, collection management, and mission planning. A need exists for ATD performance prediction based exclusively on information available from the imagery and its associated metadata. We present a predictor based on image measures quantifying the intrinsic ATD difficulty on an image.”
Dr. Ralph continued, “The modeling effort consists of two phases: a learning phase, where image measures are computed for a set of test images, the ATD performance is measured, and a prediction model is developed; and a second phase to test and validate performance prediction.”