Polarization SAR image classification method for polarization scattering non-stationary modeling

Abstract

The present invention discloses a polarization SAR image classification method based on non-stationary modeling of a polarization scattering mechanism, in order to solve the problems that the existingpolarization SAR image classification is affected by noise and has low accuracy for the mixed pixels with no obvious main scattering mechanism. The implementation steps are: initially classifying measured images; estimating the auxiliary random field according to the polarization scattering characteristics, and associating the polarization scattering characteristics with the non-stationarity; dividing the pixel point stationarity by using the auxiliary random field; calculating correlation functions for the stationary pixel points to obtain a unitary potential energy function, a data item, and a binary potential energy function; calculating the membership degree for non-stationary pixel points; constructing a posterior probability model of a fuzzy triple-recognition random field (FTDF) model by using the obtained functions, and performing classification by using the maximum posterior probability criterion; and if it is marked that the random field converges, outputting a result, and otherwise repeatedly constructing the classification model according the iterative rule until the termination iteration requirement is reached, and outputting a classification result. The method disclosed by the present invention has high detection precision and good anti-noise performance, and can be used for polarization SAR image classification.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to image classification, in particular to a polarization SAR image classification method based on polarization scattering non-stationary modeling, which is used for polarization SAR image classification. Background technique [0002] Using polarization target decomposition to extract the polarization scattering features of the target is the key point of the polarization SAR image classification technology. It is hoped to find a way to make full use of the polarization scattering information of the target to improve the accuracy of the polarization SAR image classification. The current polarization target decomposition is divided into three-component decomposition method, four-component decomposition method and multi-component decomposition method, such as Pauli decomposition, SDH decomposition, Freeman decomposition, Cameron decomposition, Cloude decomposition, etc., among whic...

AI Technical Summary

Problems solved by technology

However, due to the extreme complexity of the scene and the diversity of ground objects, coupled with the noise of the data itself and the limited image resolution, there will be many mixed pixels in the image, and the type of scattering mechanism at the mixed pixels is extremely complex. One or both of the scattering components may have close scattering powers, and there is no obvious dominant scattering mechanism, and it is imprecise to use the dominant scattering mechanism to represent the current target's scattering mechanism class

[0004] In the current commonly used image classification technology, for the mixed pixels with complex scattering mechanism, in the absence of significant main scattering mechanism, the classification result is greatly affected by noise, the misclassification rate is high, and the accuracy and computing time cannot be balanced

Images