Polarized synthetic aperture radar image ship detection method based on convolutional neural network

Abstract

The invention discloses a polarized synthetic aperture radar image ship detection method based on a convolutional neural network. The method comprises the steps of S1, carrying out the data preprocessing of a polarized synthetic aperture radar image, and constructing a polarized synthetic aperture radar image ship detection data set representing the polarization features and geometric features; S2, constructing a double-branch convolutional neural network for polarization feature extraction and geometric feature extraction, and constructing a classification regression task sub-network through the polarization features and the geometric features; and S3, training the dual-branch convolutional neural network based on the polarized synthetic aperture radar image ship detection data set according to preset training parameters, a loss function and a training strategy, and executing polarized synthetic aperture radar image ship detection and index evaluation by using the dual-branch convolutional neural network. According to the invention, the identification capability of the network can be greatly improved, and the ship can be effectively detected from a complex near-shore open-sea scene.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and synthetic aperture radar target detection, and more specifically, relates to a ship detection method based on convolutional neural network polarization synthetic aperture radar image. Background technique [0002] As an active microwave imaging device, SAR has broad application prospects in military and civilian fields. Especially in the field of maritime monitoring, polarization synthetic aperture radar is of great significance in ship detection tasks. The polarization information in SAR images has a huge advantage in ship target detection because it reflects the spatial structure and texture information of the target and the difference in scattering characteristics from the background clutter. In recent years, the research on ship detection driven by polarization characteristics has become a frontier topic in the current field. [0003] The traditional SAR ship dete...

AI Technical Summary

Problems solved by technology

However, the convolutional neural network algorithm applied to (Pol)SAR image ship target detection still has the following problems: (1) Due to the unique imaging mechanism of synthetic aperture radar, the difference between polarimetric SAR image and optical image is very significant, The existing ship detection algorithm based on convolutional neural network is more suitable for optical images; (2) Ship targets appear as discrete scattering point distribution in polarimetric SAR images, which are easily interfered by surrounding scatterers, and the side lobes and Ghost images often appear, and it is difficult for existing algorithms to extract invariant features; (3) Ship targets lacking fine structure features in polarimetric SAR images are easily confused with land background and ship-like scatterers, causing existing algorithms to high false alarm rate

In short, the convolutional neural network algorithm that relies on the extraction of intensity features for target detection limits the performance of the detector. The geometric characteristics of the joint ship target to solve the above problems

Images