Polarized SAR Image Classification Method Based on Sparse Coding and Wavelet Autoencoder

Abstract

The invention discloses a polarization SAR image classification method based on sparse coding and wavelet self-encoder, which mainly solves the boundary classification problem caused by unreasonable feature extraction and poor regional consistency caused by not considering spatial correlation. question. The main steps are: (1), input image; (2), preprocessing; (3), extracting image features; (4), sparse coding; (5), selecting training samples and test samples; (6), training Wavelet sparse autoencoder; (7), training softmax classifier; (8), adjusting network parameters; (9), image classification; (10), coloring; (11), output classification result map. The present invention has a good denoising effect, and considering the neighborhood information of the data, it can better learn higher-level features from low-dimensional features, making the outline and edge of the classification result map of the present invention clearer, and improving the polarization Classification performance for SAR images.

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