Applying morphological filters to acoustic broadband correlograms

An acoustic broadband correlogram, a two-dimensional display over time of the cross-correlation of signals received by a two-sensor system, is often used to detect targets close to the sensor system. Often, the correlogram is cluttered by the strong interference generated by distant and yet strong sources. These strong interferers appear in the form of dark vertical and nearly-vertical lines in the broadband correlogram and hinder the detection of nearby targets. This paper presents an automatic target detection system for broadband acoustic correlograms designed to take into account the interference from strong sources. The system consists of three parts: (1) a pre-processing stage, (2) a Delay Curve Hough Transform (DCHT) and (3) an onion peeling process. The pre-processing stage consists of a morphological filter (the rolling arc) and a linear histogram stretching process to improve the contrast of the morphologically filtered correlogram. The modified Hough Transform, based on the assumption that the target moves with constant velocity, is designed to detect delay curves in the broadband correlograms. Finally, the onion peeling process is an iterative process that sequentially removes the strongest detected delay curve from the correlogram and feeds the modified correlogram back to the Hough Transform to detect the next strongest delay curve