Dual-Polarization Radar Sea State Classification Based on Generalized Fractal Feature and ReSeqNet Model

Sea state classification is the basis of ocean monitoring and maritime target detection. Sea state monitoring technology based on radar echo has significant advantages of all-day and all-weather. In view of the problem that the current radar sea state classification cannot take into account both accuracy and timeliness, this paper proposes a sea state classification method based on radar HRRP fractal features and residual convolutional cyclic sequence classification network (ResNet-BiGRU Sequence Classification Network, ReSeqNet). Firstly, the q-order Hurst exponent and singularity power spectrum of the measured sea clutter HRRP sequence are extracted based on fractal theory, and the fusion features are constructed. Secondly, the ReSeqNet network based on the CNN-RNN architecture is designed to capture the local fractal features and their time correlation to realize sea state classification. Finally, the performance of the proposed network is tested using a measured data set. The experimental results show that the proposed method can achieve three-level classification of low sea conditions (2-3 sea conditions), 4-level sea conditions and 5-level sea conditions. The accuracy of the two-level classification of high and low sea conditions is 100%, and the classification accuracy of high sea conditions (4-level sea conditions and 5-level sea conditions) is 99.4%, which is about 6% higher than the existing method under the condition of shorter echo accumulation time.