SAR (Synthetic Aperture Radar) target recognition method based on component analysis multi-scale convolutional neural network

Abstract

The invention discloses a synthetic aperture radar (SAR) target recognition method based on a component analysis multi-scale convolutional neural network, which mainly solves the problem of low SAR target recognition accuracy caused by insufficient mining of inherent information of an SAR target and difficulty in establishing a proper template library in the prior art, and comprises the following implementation steps: (1) generating a training set; (2) constructing a component to analyze a multi-scale convolutional neural network; (3) the training component analyzing the multi-scale convolutional neural network; and (4) classifying the SAR complex image to be classified. According to the SAR target identification method, the amplitude information and the electromagnetic scattering information of the SAR target are utilized at the same time, and the SAR images are classified through the network, so that the intrinsic information of the SAR target is more fully mined, a template library does not need to be constructed, and the accuracy of SAR target identification is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a synthetic aperture radar SAR (Synthetic Aperture Radar) target recognition method based on component analysis multi-scale convolutional neural network in the technical field of target recognition. Aiming at synthetic aperture radar SAR images, the present invention proposes a multi-scale convolutional neural network structure combined with component analysis, which can be used to identify the model of a stationary target in the SAR image. Background technique [0002] Synthetic Aperture Radar (SAR) is an active microwave imaging radar with the characteristics of all-weather, all-time, high resolution and strong penetrating power. It has become an important means of earth observation and military reconnaissance. The most commonly used SAR target recognition method based on deep learning is the end-to-end process of feature extraction and classifier joint training,...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a synthetic aperture radar SAR target recognition method based on component analysis multi-scale convolutional neural network, aiming to solve the problem of using SAR target electromagnetic scattering information based on the template matching method in the prior art. It is difficult to establish a suitable template library at the time, resulting in low accuracy of SAR target recognition, and the lack of mining of the physical characteristics of the SAR target when using the amplitude information of the SAR

Images