Blind separation algorithm for underwater target detection

An algorithm for blind separation of sources is proposed. The algorithm based on the independent component analysis (ICA) theory can reduce the noise and improve the detection performance. Aimed at the problem difficult to eliminate the noise, the virtual signal is proposed and applied to the ICA algorithm for underwater target detection by using half-blind acoustic characteristics. The mixed signals can be separated by adding the virtual signal. Simulation results indicate that the algorithm performs better than the match filter method in strong background noise, such as the Gauss distribution and the K distribution noises.