Multistage decision fusing and classifying method for hyperspectrum and infrared data

Abstract

The invention discloses a multistage decision fusing and classifying method for hyperspectrum and infrared data. The multistage decision fusing and classifying method comprises the following steps of: firstly, carrying out noise suppression processing and spatial adjustment on the hyperspectrum and infrared data; secondly, establishing a hyperspectrum and infrared data combined characteristic space according to the characteristics of the hyperspectrum and infrared data; thirdly, monitoring and classifying the combined characteristic space established in the second step to obtain a ground object classification decision according to the ground object categories to be classified and a training sample; fourthly, determining ground object classes required to be subjected to small-object strengthening decision extraction according to the object size and carrying out small-object strengthening decision extraction by using the combined characteristic space established in the second step; fifthly, carrying out end member extraction and abundance estimation on hyperspectrum data subjected to noise suppression in the first step to obtain an abundance decision; and sixthly, designing a fusingrule and fusing the classification decision acquired in the third step, the small-object strengthening decision acquired in the fourth step and the abundance decision acquired in the fifth step to obtain a fusion and classifying result.

Description

technical field [0001] The invention relates to a multi-level decision fusion classification method for hyperspectral and infrared data, which belongs to the field of multi-source remote sensing data processing methods and application technology, and is suitable for research on theoretical methods and application technologies for high-precision classification of hyperspectral and infrared data. Background technique [0002] With the development and application of aerospace remote sensing technology, a multi-level, multi-angle, all-round and all-weather earth information acquisition system has gradually been established, which has brought about a rapid increase in the amount of earth observation data. How to effectively integrate these information The application of multi-source remote sensing data to complement each other is one of the hot issues in current remote sensing research. [0003] Hyperspectral remote sensing technology overcomes the limitations of traditional sing...

AI Technical Summary

Problems solved by technology

However, as the core input parameter in the MNF transformation-the hyperspectral data band noise covariance estimation method still has problems

Spectral and Spatial Decorrelation Method (SSDC) is currently recognized as a noise extraction algorithm with strong adaptability and stable precision. However, due to the limitation of the algorithm theory, it is effective for noise extraction of uniform ground object images. However, the accuracy of noise extraction in the case of mixed ground objects on the image decreases.

Images