SAR image rotating ship detection method based on directed Gaussian function

Abstract

The invention relates to an SAR image rotating ship detection method based on a directed Gaussian function. The SAR image rotating ship detection method comprises the following steps: S1, acquiring an SAR image to be detected; S2, inputting the SAR image into a directed ship detection network model so as to detect directed ship targets with different scales, wherein the directed ship detection network model is obtained by constructing a directed ship detection network and performing network training, the directed ship detection network comprises a feature extraction network and a head network, and a plurality of groups of multilevel feature maps of an input SAR image are obtained through ResNet-50 and FPN networks. In the head network, the classification sub-network determines each pixel in the feature maps as a center pixel of a ship object, the regression sub-network regresses a directional bounding box of each object, and head network loss functions corresponding to the three sets of feature maps are subjected to weighted calculation to obtain a total loss function so as to train the network. Compared with other ship detection methods, the method provided by the invention has the advantage that the recognition accuracy is obviously improved.

Description

technical field [0001] The invention belongs to the technical field of image detection, and in particular relates to a method for detecting a rotating ship in a SAR image based on a directed Gaussian function. Background technique [0002] Ship detection technology can effectively improve the efficiency of maritime transportation and reduce maritime traffic accidents, so it has always been one of the hottest researches in the field of remote sensing. As an important remote sensing technology, synthetic aperture radar (SAR) has the advantages of all-weather, all-weather and long-distance operation, providing rich and high-resolution landmark information. Ship targets are composed of many complex metallic components and typically have a high radar cross section (RCS), meaning they reflect energy higher than that of other targets or the background in the SAR image. These significant advantages make SAR ship detection a powerful means of maritime surveillance. [0003] Althoug...

AI Technical Summary

Problems solved by technology

[0003] Although the use of SAR systems to achieve ship target detection has obvious advantages, there are still many difficulties that limit the performance of ship detection

Doppler parameters caused by ship self-motions such as roll and yaw lead to a mismatch between the SAR imaging model and the matched filter model, which in turn causes the target pixels to expand to a large width

Images