Underwater target detection using a pair of omnidirectional transducers in extremely shallow water

In extremely shallow water, such as bays and inlets, active sonar may not work sufficiently well to detect underwater threats owing multiple reflections strong reverberations at the sea surface seafloor. this study, we developed "gate sonar" on basis of a unique method detecting changes in pulse signal propagated between pair omnidirectional transducers surveyed area when target passes transducers. To received signal, employed time-reversed source for gate sonar; can be created even from by using virtual array formed bottom boundaries. As result experiments 25 m-long swimming pool, confirmed that recognize functions designed. Furthermore, applying convolutional neural network (CNN) waveform its spectrogram input images, demonstrated proposed time reversal mirror (TRM)-based improve detection targets, with performing slightly better.