Marsh vegetation stack ensemble learning classification method integrating hyperspectral and multi-band full-polarization SAR (Synthetic Aperture Radar) images

Abstract

The invention discloses a marsh vegetation stack ensemble learning classification method integrating hyperspectral and multi-band full-polarization SAR images, and the method comprises the steps: integrating a hyperspectral image and different-band full-polarization SAR images, carrying out the variable optimization through multi-scale segmentation, high-correlation variable elimination and a Boruta algorithm, constructing a multi-dimensional variable data set, and carrying out the classification of the marsh vegetation stack. And carrying out stack integration on the classification models after different parameter optimization by using a Stacking algorithm, constructing a marsh vegetation identification and classification model, finally classifying data to be classified by using the model to obtain a marsh wetland vegetation classification result, and carrying out quantitative evaluation on the classification result by using an evaluation index. According to the method, the rich spectral information advantage of the hyperspectral image and the advantage that the polarimetric SAR image can penetrate through the vegetation canopies are integrated to realize high-precision recognition and classification of the marsh vegetation.

Description

Technical field [0001] The present invention relates to the technical field of plant classification, and more particularly to an integrated learning classification method for integrated high spectroscopy and multi-band prefore SAR images. Background technique [0002] Wetland internal biological species is rich, but human beings are difficult to in depth in wetlands, and traditional methods are consumed, while utilizing remote sensing for wetlands is a very efficient way. High-spectral image data has high spectral resolution but is susceptible to cloud rain weather. The polarized SAR image is not afraid of cloud rain, and Different frequency band SAR data has different penetration capabilities, but it lacks rich spectral information. The conventional segmentation has a single split scale, and the segmentation effect is not good enough to lead to a problem that the classification accuracy is not high. Due to high heterogeneity of wetland, it is complicated, and the wetland classif...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above problems, the object of the present invention is to provide a swamp vegetation stack integrated learning classification method that integrates hyperspectral and multi-band full-polarization SAR images. Through the integration of recognition capabilities, it solves the problem that a single data source or a single classifier can cause swamp wetland vegetation to be incorrectly identified and easily confused

Images