Abstract:

An acoustic feature change detecting based method is proposed to estimate the target maneuver onset time. From the statistical analysis of many acoustic features of different targets, a certain estimated feature value in a single motion state conforms to the approximately normal distribution. Based on the normal distribution, an online method is proposed to estimate the target maneuver onset time by testing the significance of acoustic feature variation. The acoustic feature variation index is defined to select the most sensitive feature to the change of target motion state. Then the feature can be used to improve the efficiency of the method.Experiment results show that the proposed method is more rapid to estimate the maneuver onset time after the target maneuver occurs.