Remote-sensing image one-class classification method based on one-class normalization

Abstract

The invention provides a remote-sensing image one-class classification method based on one-class normalization. One-class samples are selected from a remote-sensing image, one-class normalization transformation is carried out, a suprasphere is determined with an original point as a center for one-class classification after normalization transformation is finished, and the sample away from the original point by the distance smaller than the radius of the suprasphere is the positive class. Compared with other one-class classification technologies, the remote-sensing image one-class classification method based on one-class normalization has the advantages that no parameter is needed, namely one-class classification is carried out directly without setting any parameters, the effect is good, and performance is stable.

Description

Technical field [0001] The invention relates to the field of remote sensing information extraction, in particular to the analysis and application of remote sensing image information. Background technique [0002] Single-class classification requires the extraction of a specific category in remote sensing images, regardless of other ground feature types, such as wetland extraction, vegetation extraction, water extraction, etc., which has gradually become a research hotspot in the field of remote sensing information extraction. At present, the single-class information extraction technology mainly focuses on two aspects, one is the feature selection and analysis for specific feature category extraction, and the other is the design of the single-class classifier. Among them, feature selection and analysis are very specific to the extracted categories, such as water information extraction. Some methods combine image aggregation, adjacent spatial features and spectral analysis of high-...

AI Technical Summary

Problems solved by technology

There is also a method based on support vector data description (SVDD), which uses a sphere as small as possible containing the target data for discrimination, and can get better classification results by training with small samples. The main disadvantage of the SVDD method is also Parameter setting is more complicated

There are also single-class classifiers such as PUL (positive and unlabeled learning) and MAXENT methods, which all need to set more complex parameters, and the effect will be affected in practical applications.

Images