Polarized SAR image classification method based on sparse coding and wavelet auto-encoder

Abstract

The invention discloses a polarized SAR (Synthetic Aperture Radar) image classification method based on sparse coding and a wavelet auto-encoder, mainly solving the problems of boundary classification caused by unreasonable characteristic extraction and poor region homogeneity caused by not considering spatial correlation. The method mainly comprises the steps of: (1) inputting images; (2) pre-processing; (3) extracting image characteristics; (4) sparse coding; (5) selecting a training sample and a test sample; (6) training a wavelet auto-encoder; (7) training a softmax classifier; (8) adjusting network parameters; (9) classifying the images; (10) coloring; and (11) outputting a classification result image. The method has a better denoising effect, considers data neighborhood information, and can better learn characteristics of a higher level from low-dimensional characteristics, allow a classification result image to have a clearer outline and edge, and improve polarized SAR image classification performance.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar SAR (Synthetic Aperture Radar) image classification method based on sparse coding and wavelet sparse autoencoder in the technical field of polarization synthetic aperture radar image classification. The invention adopts a method combining Gaussian pyramid pooling encoding and wavelet sparse self-encoder to classify polarimetric synthetic aperture radar SAR images, and the method can be used for polarimetric synthetic aperture radar SAR image target detection and target recognition. Background technique [0002] Polarization SAR has become one of the important development directions of SAR at home and abroad, and polarization SAR image classification is an important research technology of SAR image interpretation. Polarimetric SAR is an active high-resolution active microwave remote sensing imaging radar. Its research began in...

AI Technical Summary

Problems solved by technology

Although this method combines the histogram segmentation of the scattering entropy H and the scattering angle α to obtain the division threshold, it still has the disadvantage that the method does not effectively combine the neighborhood information of the data and does not consider the polarimetric SAR image. Spatial correlation leads to more noise points in the region, poor regional consistency, and a large amount of calculation, time-consuming, and complicated implementation process

However, there are still shortcomings that this method does not have good time-frequency local properties and cannot describe the detailed characteristics of the data.

Images