SAR ship target segmentation method based on multi-scale similarity guidance network

Abstract

The invention discloses a ship target segmentation method based on a multi-scale similarity guidance network, and mainly solves the problem that the ship target segmentation result is poor under the condition of small samples in the prior art. According to the scheme, the method comprises the following steps: constructing an original data set by using existing SAR image ship target segmentation data sets which are in different regions and contain different imaging modes; constructing the original data set into a small sample segmentation training data set and a small sample segmentation test data set; constructing a multi-scale similarity guidance network composed of a feature extraction branch for supporting the image, a feature extraction branch for querying the image, a similarity guidance module and a generation branch; training the network by using a small sample training set; and inputting the small sample test set into the trained network to obtain a segmentation result of the ship target. Compared with other small sample semantic segmentation methods, the method has the advantages that the number of data needing to be labeled on the target domain is effectively reduced, and the small sample semantic segmentation effect is improved. The method can be used for intermediate processing of SAR image interpretation.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a SAR ship target segmentation method, which can be used for intermediate processing of SAR image interpretation. Background technique [0002] In recent years, with the development of synthetic aperture radar systems, the acquired information is gradually transferred from land to sea. How to solve the small sample ship target segmentation of SAR images has become an urgent problem to be solved. In recent years, with the excellent performance of deep learning in the fields of computer vision, speech signal processing, and natural language processing, how to combine deep learning methods with SAR image ship target segmentation has become an important issue in the field of SAR image processing today. hot issues. The deep learning method is based on the idea of ​​layer-by-layer training and learning, and continuously mines the intrinsic attributes of the training data to r...

AI Technical Summary

Problems solved by technology

[0009] However, due to the particularity of SAR image imaging and the scale diversity of ship targets in the image, the existing small-sample segmentation algorithms are not well suited for ship target segmentation in SAR images.

Images