Sea-surface weak target detection scheme using a cultural algorithm aided time-frequency fusion strategy

To improve the sea-surface weak targets detection performance of the marine surface surveillance radar systems, the authors put forward a novel detection scheme based on a time-frequency distribution (TFD) fusion strategy assisted by population evolution algorithm. A Volterra-series-based weighted averaging model is utilised as the fusion rule to construct the fused TFD (FTFD), which aims to enhance the performance of time-frequency (TF) analysis and suppress signal-dependent cross-term artefacts. Herein, the optimal fusion coefficient is estimated by culture-based population evolutionary algorithm without any prior information. Unfortunately, this FTFD produces a great deal of redundant information. Hence, the normalised frequency marginal feature is extracted to reduce dimensions of the TF discriminant features, which is necessary to improve the efficiency of pattern classification. Finally, a multi-layered feed-forward neural network is utilised as a classifier in the pattern classification process. Experimental results demonstrate that the FTFD constructed by the proposed scheme achieves better performance in sharpness and strength than any subset of TFDs or their combinations and, furthermore, increases the detectability of sea-surface floating weak targets under any environment circumstances.