SAR ship detection method based on global and local context information

Abstract

The invention discloses an SAR ship detection method based on global and local context information. The method comprises the steps: 1, obtaining an SAR image, and carrying out the processing of the SAR image to obtain a binarized image; 2, performing morphological processing on the binarized image; 3, carrying out region selection based on global context information, and screening out sub-images of all hidden ships; 4, carrying out classification and regression prediction on the sub-images of the hidden ship; 5, performing morphological processing on the binarized image again; and 6, carrying out false alarm suppression based on local context information to obtain a ship target. The method comprises screening sub-images to be detected by using global context information of an SAR image, and screening out sub-images containing ships; and then the detection result is screened again by using the detection frame and the local context information of the peripheral neighborhood, so that the calculation redundancy can be reduced, the detection efficiency can be improved, the false alarm can be reduced, and the detection precision can be improved.

Description

technical field [0001] The invention belongs to the technical field of radar target detection, in particular to a SAR ship detection method based on global and local context information. Background technique [0002] In recent years, radar imaging technology has been developed by leaps and bounds, and has been widely used in many fields such as military affairs, agriculture, forestry, geology, ocean, disasters, and mapping. Synthetic Aperture Radar (SAR) is an active sensor that uses microwaves for perception. Compared with other types of sensors such as infrared and optical, SAR imaging is not limited by conditions such as light and weather. Therefore, SAR has become an important means of earth observation and military reconnaissance, and target recognition based on SAR images has also received more and more attention. [0003] The two-parameter CFAR detection algorithm is a traditional SAR image target detection method. The premise of this method requires that the target ...

AI Technical Summary

Problems solved by technology

There are many SAR image target detection methods based on deep learning in the prior art, such as the R-CNN series of SAR target detection methods based on two-stage suggestion frame generation, SSD based on single-stage default frame regression, and SAR target detection methods of YOLO series And the CenterNet series of SAR target detection methods based on Anchor Free. These detection methods use data-driven methods to obtain efficient detection models. The input images are all proposed based on natural or optical images, and the size requirements for the input images are small, while The size of SAR images is generally much larger than that of ordinary optical images, and the unique imaging method of SAR images makes them more complex than ordinary optical images. The complex background clutter area containing the target will also cause serious interference to the detection results

Images