SAR ship detection in complex background based on multi-feature fusion and non-local channel attention mechanism

With the development of artificial intelligence (AI) and synthetic aperture radar (SAR) technology, SAR ship target automatic detection has made significant progress. However, due to the complex structure and various sizes of ship, detecting multi-scale ships under complex backgrounds is still challenging. The existing convolution neural networks (CNNs)-based SAR ships detection methods suffer from insufficient feature extraction capabilities and poor feature reusability. To address the issues, an SAR ship detection method based on multi-feature fusion and non-local channel attention mechanism (MFNL-Net) is proposed in this article. MFNL-Net is a one-stage detector and designed to improve the performance of detecting multi-scale ships by enhancing the feature extraction ability and nonlinear relationship between different features. Specially, the non-local channel attention block (NLCA-Block) is employed to enhance the nonlinear relationship between different channel features and the ability of local feature expression; the pooling feature fusion (PFF) module and the deconvolution feature fusion (DFF) module are reasonably combined to obtain abundant ships target feature information and suppress interference caused by surroundings; the multi-scale spatial pyramid pooling (MSPP) is used to boost feature information interaction and reduce the loss of significant feature; the focus classification loss is used to alleviate influences of the positive-negative samples imbalance. To evaluate the effectiveness of MFNL-Net, experiments are conducted on real SAR ship datasets SSDD and GS-Ship. Experimental results show that our method obtains 9.10%, 8.61%, 7.23%, and 4.44% gains in mean average precision (mAP) compared with the four state-of-the-art CNNs-based methods, respectively.