Enhanced CNN-Based Small Target Detection in Sea Clutter With Controllable False Alarm

As targets floating on the sea surface get more invisible, it is becoming vital and challenging to effectively detect small targets from strong sea clutter. However, fitting the distribution of sea clutter is a hard task because of the complex characteristics of clutter. Classic model-based detectors are prone to suffer from the mismatch problem and a high probability of false alarm (PFA). In this article, a PFA-controllable and data-driven detection method based on an attention-enhanced convolutional neural network (CNN) is proposed. Different from mainstream CNN-based detectors, the proposed method takes time–frequency maps obtained by the Wigner–Ville distribution (WVD) as inputs. Then time–frequency maps are converted into feature images as inputs to the designed CNN strengthened with representation powers and feature refinement abilities. The designed CNN is capable of automatically learning and classifying different features between targets and clutter. Meanwhile, a PFA control unit is employed to ensure an expected actual PFA. Results with the IPIX database show that the probability of detection (PD) of the proposed method is about 0.9066 with the PFA being $10^{-{3}}$ and the observation time being 1.024 s. Compared with five typical feature-based detectors, the proposed method achieves better detection performance. However, results with the Sea-Detecting Radar Data-Sharing Program database also verify the feasibility and superiority of the proposed detector. The source codes are available at https://github.com/quqizhe-whu/ADN .