A CFAR‐like detector based on neural network for simulated high‐frequency surface wave radar data

This article presents a deep neural network-based constant false alarm rate (NNB-CFAR) detector for simulated high-frequency surface wave radar (HFSWR) data. A network is trained to identify fluctuation parameters of each cell range-Doppler power spectrum based on the patterns present in neighbouring cells. The estimated are then used calculating detection threshold with user-specified probability alarm. To train network, realistic model HFSWR echoes generating large labelled image dataset, including many possible clutter scenarios and interfering target echoes. Several CFAR windows extracted from training dataset as replicate output maximum likelihood estimator reference cells window. NNB-CFAR algorithm was compared traditional algorithms by identifying targets second set images. also experimentally measured context all algorithms. Results show that technique can significantly improve rates amid strong clutter.