A large-scale semi-supervised feature selection method for high-resolution remote sensing images

Abstract

The large-scale semi-supervised feature selection method for high-resolution remote sensing images belongs to the technical field of semi-supervised feature selection. When the quantity is much larger than the labeled data, it affects the rationality of the selected features. It first collects remote sensing image data, and obtains the normalized data x after processing; then constructs a measurement function based on the loss function and the probability distribution matrix {yjk} of unlabeled samples; it loops and optimizes the three parameters of the measurement function in turn to obtain A metric value corresponding to the corresponding feature; according to the metric value, the features are sorted to obtain a feature subset of the remote sensing image data, and the feature subset is selected as data obtained by a large-scale semi-supervised feature selection method. The invention is used for feature selection of remote sensing images.

Description

technical field [0001] The invention relates to a semi-supervised feature selection method, in particular to a large-scale semi-supervised feature selection method for high-resolution remote sensing images. Background technique [0002] By providing accurate and extensive land use and land cover information, high-resolution (VHR) remote sensing images play a great role in real life. The application of high-resolution remote sensing images in real life often relies on object-based image analysis (OBIA). OBIA requires various target features, including spectral, structural and shape features of the target, and too many underlying features will degrade the performance of OBIA. This contradiction can be alleviated by feature selection methods. By effectively selecting a small number of original features with higher discriminative power, feature selection methods have a direct and significant impact on the acceleration of data mining algorithms, the improvement of performance, ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that in the existing high-resolution remote sensing image supervision feature selection method, a large amount of training data is required to be marked, and when the number of unmarked objects is far greater than the marked data, the problem of affecting the rationality of the selected features , providing a large-scale semi-supervised feature selection method for high-resolution remote sensing images

Images