SAR ship target detection method based on improved faster R-CNN

Different from optical images, detection performance in synthetic aperture radar (SAR) images is poor. To solve issues above, an improved ship target detection method is proposed in this paper. Firstly, wavelet decomposition is introduced, the advantages of using wavelet pooling in the down-sampling process of image feature maps were analyzed, replacing the normal pooling with the wavelet pooling in the standard Faster R-CNN and improving the detection performance of large ship targets. Besides, the wavelet decomposition is iterated to obtain the wavelet hierarchical decomposition, forming a wavelet convolutional neural network (WCNN). The obtained feature maps of different scales are fused with the feature maps of the backbone to improve the accuracy of small object detection. Finally, combining the above two methods, the algorithm proposed in this paper is obtained. Through ablation experiments, the target detection performance of different methods was compared, and the results showed that compared to the standard Faster R-CNN algorithm, the algorithm proposed in this paper can improve the mean average precision by 2.2%.