A False Alarm Controllable Detection Method Based on CNN for Sea-Surface Small Targets

It is a compelling task to detect sea-surface small targets in the background of strong sea clutter. Traditional detection methods usually suffer from poor detection performance and a high probability of false alarm (PFA). In this letter, a PFA-controllable and feature-based detection method is proposed based on an enhanced convolutional neural network (CNN). The time-frequency features of received signals are first extracted by the short-time Fourier transform and converted into feature images. These feature images are then employed as inputs of an enhanced CNN with a PFA control unit. The enhanced CNN takes full advantage of the subtle feature extraction ability of the asymmetric convolution and robust time-frequency maps. Finally, detection results are obtained according to the given PFA. The results on the IPIX dataset show that the probability of detection of the proposed method is about 0.864 when the observation time is 1.024s and PFA is 10^-3. Compared with five typical detection methods, the proposed method achieves better detection performance. Besides, results also verify the stable PFA control ability of the proposed method. The source code is available at https://github.com/quqizhe-whu/STDN.