Polarized SAR image classification method based on tensor and sparse self-coder

Abstract

The invention discloses a polarized SAR image classification method based on a tensor and a sparse self-coder, and the method comprises the implementation steps: (1) inputting a polarized SAR image T matrix; (2) generating three-order tensors which are respectively corresponding to each pixel; (3) calculating the similarity of a selected pixel with an adjacent pixel; (4) generating scattering vectors which are respectively corresponding to each pixel; (5) generating characteristic vectors which are respectively corresponding to each pixel; (6) selecting training data; (7) training the sparse self-coder; (8) obtaining a final classification result. The method employs the tensors for representing raw data, employs the sparse self-coder to extract features, irons out defects in the prior art that a mode of representing data through vectors causes the loss of raw data, neighborhood information is lost, and the regional consistency is poor, makes the most of the raw data information of an image, and maintains the good regional consistency.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar (Synthetic Aperture Rader, SAR) image classification method based on tensor and sparse autoencoder in the technical field of image classification. The invention adopts the classification method based on tensor and sparse self-encoder, and can be used for the ground object classification of the polarimetric synthetic aperture radar SAR image. Background technique [0002] Polarization synthetic aperture radar (SAR) is a new type of radar that can measure the polarization characteristics of target scattering signals. Its advantage is that it can obtain multi-channel polarization images, which is conducive to understanding the scattering mechanism of targets and improving the detection of targets. , Distinguishing and classification capabilities, so that it is convenient to effectively suppress clutter and improve the ability to...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it does not take into account the neighborhood information of pixels, which may destroy the consistency of the region and affect the classification results.

The disadvantage of this method is that each point in the polarimetric SAR image is processed corresponding to a scattering vector, which makes the data in the original T matrix lost and changes the polarimetric SAR SAR data The natural structure of the multidimensional array affects the subsequent feature extraction and classification results

Images