Remote sensing image classification method based on AGA-PKF-SVM

Abstract

The invention provides a remote sensing image classification method based on the AGA-PKF-SVM, and relates to the field of remote sensing image processing technology. In this method, a global polynomial kernel function (PKF) is used as the kernel function of a support vector machine (SVM), an SVM remote sensing image classification model is trained by cross validation, and an adaptive genetic algorithm (AGA) is used for combinatorial optimization of a penalty factor of the SVM, parameters of the PKF and the number of folds of the cross validation. The remote sensing image classification method based on the AGA-PKF-SVM provided by the invention can effectively avoid the falling into a local optimal solution in the combinatorial optimization of the SVM parameters and enable the classification model to have better generalization performance and prevent overfitting.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to an AGA-PKF-SVM-based remote sensing image classification method. Background technique [0002] When the support vector machine is used to classify remote sensing images, the classification effect is affected by the kernel function and parameters. At present, the RBF kernel function is mainly used when selecting the kernel function. The optimization of the support vector machine parameters is mainly the penalty factor C and RBF of the support vector machine. The combined optimization of the gamma parameters in the kernel function, however, the RBF kernel function is a local kernel function, and the support vector machine using the RBF kernel function has a good training effect, but its generalization performance is slightly poor, and it is not sufficient in the parameter training process. Considering the overfitting problem of the support vector machine cla...

AI Technical Summary

Problems solved by technology

[0002] When the support vector machine is used to classify remote sensing images, the classification effect is affected by the kernel function and parameters. At present, the RBF kernel function is mainly used when selecting the kernel function. The optimization of the support vector machine parameters is mainly the penalty factor C and RBF of the support vector machine. The combined optimization of the gamma parameters in the kernel function, however, the RBF kernel function is a local kernel function, and the support vector machine using the RBF kernel function has a good training effect, but its generalization performance is slightly poor, and it is not sufficient in the parameter training process. Consider the overfitting problem of the support vector machine classification model, so that the established remote sensing image classification model cannot guarantee the classification effect when classifying new unknown remote sensing image data

Images