Remote sensing image characteristic dimension reduction method based on mRMR and KPCA

Abstract

The invention discloses an remote sensing image characteristic dimension reduction method based on mRMR and KPCA, belonging to the remote sensing image processing technology field. The remote sensing image characteristic dimension reduction method firstly uses an mRMR method to perform characteristic selection on an original characteristic set of the remote sensing image to obtain an original set of the remote sensing image characteristics and then uses a KPCA method to perform further dimension reduction on the original subset of the remote sensing image characteristics to obtain an optimized subset of the remote sensing image characteristics. The invention also discloses a remote sensing image characteristic dimension reduction device based on the mRMR and KPCA and a remote sensing image classification method and device. The remote sensing image characteristic dimension reduction method organically combines a characteristic selection method and a characteristic conversion method to perform remote sensing image characteristic dimension reduction, and can effectively improve classification accuracy of the remote sensing image while effectively solving a problem of dimension disaster of the remote sensing image.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a dimensionality reduction method for remote sensing image features. Background technique [0002] With the development of earth observation technology, remote sensing data has become more and more diversified, showing the obvious characteristics of "big data" such as large volume, strong timeliness, miscellaneous types, difficulty in distinguishing authenticity and great potential value. According to the latest research by International Data Corporation (IDC), 95% of the newly added data in the world in the past few years is imprecise and unstructured data that far exceeds the scale of normal data processing. Moreover, the utilization rate of remote sensing data has not yet reached 10%, resulting in an extreme waste of resources and the problem of "dimension disaster". Therefore, how to efficiently mine discriminative information from high-resolution rem...

AI Technical Summary

Problems solved by technology

However, remote sensing images do not have a unified fixed structure, and are characterized by fuzziness, high resolution, and ambiguity in image understanding.

[0004] In summary, there are some shortcomings in the method of dimensionality reduction of high-dimensional remote sensing image features using feature selection method or feature transformation method alone.

Images