SAR image target identification method based on feature construction

Abstract

The invention belongs to the field of radar automatic target recognition, and particularly provides an SAR target recognition method based on feature construction. According to the invention, the characteristics of the original image are not damaged; the method comprises the following steps of: constructing SAR (Synthetic Aperture Radar) image features by utilizing a Symbolic Regression method anda polynomial method; linearly fusing the original features and the constructed features, using a global feature dimension reduction method for achieving high-discrimination-capability feature extraction, and finally conducting classification through a classifier. According to the method, the spatial structure relationship between pixels of the original images is fully utilized to construct features with stronger identification capability, and then the features are fused with the features of original SAR images, so that target identification performance of SAR images are effectively improved.

Description

technical field [0001] The invention belongs to the field of radar automatic target recognition, in particular to a synthetic aperture radar image target recognition method based on image feature construction. Background technique [0002] Synthetic Aperture Radar (SAR) is widely used in the field of remote sensing because of its strong anti-interference ability and all-weather working mode. SAR image target recognition is generally divided into preprocessing, feature extraction, and classifier design; among them, feature extraction is the most important step, which directly affects the highest recognition performance of the classifier. SAR images are generally composed of targets, shadows, and background clutter, so extracting robust discriminative features from complex SAR images has always been one of the research focuses of SAR target recognition algorithms. [0003] In the early days, scholars have done a lot of research on the texture characteristics, geometric charac...

AI Technical Summary

Problems solved by technology

[0003] In the early days, scholars have done a lot of research on the texture characteristics, geometric characteristics, and scattering point characteristics of the original SAR image, and many SAR image feature extraction algorithms have been proposed; The azimuth, elevation angle and environmental noise are very sensitive, so SAR image features have always been a challenging problem

[0004] At present, the biggest disadvantage of many SAR image feature extraction algorithms is that they ignore the relevant characteristics in SAR imaging, and lose the structural relationship between SAR image features in the feature extraction process, so it is still difficult to extract robust SAR image features.

Images