SVM-based land/sea clutter identification with multi-features

For target location error correction of over-the-horizon radar (OTHR) based on passive beacon reference source, SVM-based land/sea clutter identification with multi-features was proposed in this paper by establishing signal model and analyzing the three typical features of land/sea clutter. Experiments were carried out for different clutter-noise-ratios (CNR), and the results showed that the proposed algorithm has achieved a higher recognition rate of land/sea clutter than methods based on single feature of the backscatter amplitude and linear discriminant analysis. The proposed algorithm could provide theoretical guidance for improving target location accuracy of OTHR.