CGAN-based space target ISAR image part segmentation method

Abstract

The invention provides a space target ISAR image part segmentation method based on a conditional generative adversarial network CGAN, which is used for solving the problem of low ISAR image segmentation precision in the prior art, and comprises the following steps: generating a training data set and a test data set; constructing a conditional generative adversarial network CGAN model; performing iterative training on the conditional generative adversarial network CGAN; the trained conditional generative adversarial network CGAN is tested; a spatial target ISAR image part in a prediction segmentation image is segmented. According to the invention, global mapping from the ISAR image to the label of the ISAR image is realized by using the adversarial game process of the conditional generativeadversarial network CGAN; according to the method, the high-frequency part of the prediction segmentation image is well constructed, Meanwhile, the low-frequency part of the prediction segmentation image is constructed by adopting L1 loss, so that the prediction segmentation image is integrally similar to a label, and the segmentation precision of a space target ISAR image part is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of radar image processing, and relates to an ISAR image segmentation method, in particular to a CGAN-based space target ISAR image component segmentation method, which can be used in the fields of space target attitude estimation, space target recognition and the like. Background technique [0002] Inverse Synthetic Aperture Radar (ISAR, Inverse Synthetic Aperture Radar) is an important branch in the development process of synthetic aperture radar, which has the ability of all-day, all-weather and long-distance imaging. As countries around the world pay more and more attention to space resources, the development of space resources has become a hot spot, and the trend of space operations will gradually intensify in the future. Space targets have become a research hotspot in the field of radar. By analyzing the acquired ISAR images of space targets, we can To realize the determination of the type, size, materi...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the shortcomings of the above-mentioned prior art, and propose a CGAN-based space object ISAR image component segmentation method, which is used to solve the problem of low segmentation accuracy of space object ISAR image components in the prior art

Images