Polarized SAR (Synthetic Aperture Radar) image semi-supervised classification method capable of considering characteristic optimization

Abstract

The invention discloses a polarized SAR (Synthetic Aperture Radar) image semi-supervised classification method capable of considering characteristic optimization. The method comprises the following steps: firstly, adopting a refined polarized LEE filtering method to carry out filtering, extracting polarization characteristics, carrying out combination to obtain an original characteristic set, and carrying out normalization processing; selecting an initial training sample set and a no-label set, and carrying out characteristic selection and classifier parameter optimization through a hybrid coding genetic algorithm under the initial training sample set; reconstructing the training sample set and a no-label sample set; training the classifier, and selecting a candidate set from the no-label sample set; utilizing a trained SVM (Support Vector Machine) classifier to label the candidate set, and selecting and expanding sample points with a high confidence coefficient into the training sample set; repeating the training of the classifier until learning is finished; and classifying the whole image by a finally trained SVM to obtain a classification thematic map. By use of the classification method, on one hand, effective characteristics can be adaptively extracted to improve a semi-supervised classification effect; and on the other hand, the efficiency of self-training learning can be improved, and error accumulation can be effectively avoided.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, relates to applications in the field of remote sensing image classification, in particular to a semi-supervised classification method for polarimetric SAR images considering feature optimization. Background technique [0002] Synthetic Aperture Radar (SAR) is an imaging radar that has been gradually developed and put into use since the 1950s. It has the characteristics of all-day, all-weather, and strong penetrating ability. However, the early SAR system used a single-polarization working mode, which could only obtain the complex data of the echo power of the ground object target, and could not obtain the polarization information of the ground object target, which was not conducive to obtaining the azimuth, orientation, and geometric size of the ground object target. , surface roughness and other information are also not conducive to the analysis of the scattering mechanis...

AI Technical Summary

Problems solved by technology

However, because the base classifier trained with a small number of samples often has low classification accuracy, it is easy to cause error accumulation.

In addition, in the semi-supervised classification of fully polarized SAR, the effect of self-training and learning of feature sets under various polarization decompositions is different, and the clustering effect is also quite different, and the comprehensive use of all features cannot guarantee better results. effect, but increases the computational burden

Images