Multiscale ship detection based on cascaded dense weighted networks in synthetic aperture radar images

Abstract

The sizes of ships vary by type in synthetic aperture radar (SAR) images, and this multiscale problem degrades the accuracy of ship detection. We present a multiscale ship detection method based on cascaded dense weighted networks in SAR images. Dense weighted fusion is performed in the feature extraction module and feature fusion module by cascading, i.e., feature weighting is achieved by embedding a convolutional block attention module after feature layers at different scales, followed by dense connection to fuse features at different scales. This makes it possible to refine the cascaded feature mapping, enhance the information transfer of shallow and deep features, and build a multiscale feature representation model. Experiments on the extended high-resolution SAR images dataset show that the accuracy of this method is 74.87% in inshore scenes, and 97.39% in offshore scenes, which exceeds that of other ship detection methods. In addition, in two SAR images from TerraSAR-X, the detection accuracy of multiscale ships reaches 86.63%, which indicates the method’s better robustness.