SAR ship detection system and method based on deep neural network

Abstract

The invention belongs to the technical field of ship information detection, and discloses an SAR ship detection system and method based on a deep neural network, and the system comprises a fusion feature extraction module which is used for extracting features from an SAR image, and fully fusing the features from the bottom to the top and from the top to the bottom; a region proposal module which is used for classifying SAR image ships and backgrounds by taking the fusion features provided by the FEEN as input, and generating coarse candidate windows containing ship target positions; and a finedetection module which is used for taking the features provided by the FEEN and the coarse anchor frame provided by the RPN as input, refining the coarse anchor frame, and carrying out finer ship detection to obtain a final detection result. The detection method provided by the invention has good performance in multi-scale ship and small target ship detection under SAR complex backgrounds (far coast and near coast), and high ship detection precision is obtained.

Description

technical field [0001] The invention belongs to the technical field of ship information detection, in particular to a deep neural network-based SAR ship detection system and method. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] Synthetic Aperture Radar (SAR, Synthetic Aperture Radar) is an all-weather and all-weather sensor, such as GF-3, Sentinel-1, TerraSAR-X, etc., which can generate high-resolution SAR images. SAR images have strong penetrability and It is an indispensable digital resource in current earth observation, and is widely used in ship traffic monitoring, military and civilian fields. Ships in SAR images, as important military and civilian targets, are objects that need to be focused on. At present, there have been a lot of researches on ship target detection in SAR images. Traditional SAR image ship target detection methods include four stages: sea and land segmentation, preprocessi...

AI Technical Summary

Problems solved by technology

[0011] (1) Traditional SAR ship detection methods rely on human-predefined features or distributions, which are difficult to show good detection performance

The detection performance is poor, the reason: mainly because the traditional SAR ship detection method relies on manual extraction of features

[0012] (2) The current SAR ship detection method model based on deep neural network is difficult to detect multi-scale ships and small target ships in complex backgrounds, the detection accuracy is not high, and it does not show good performance

[0014] It is necessary to combine the existing problems and redevelop a ship detection method based on deep neural network in SAR images to solve the complex and diverse background of SAR images and the large differences in the size of ships.

Images