Method and device for Hyperspectral image semi-supervised classification

Abstract

The invention relates to a method and a device for remote-sensed hyperspectral image classification. The method comprises the following steps of step 1: carrying out spectral angle weighted clustering based on kernel function vague C mean value on the hyperspectral image to obtain clustered indication characteristics; step 2: carrying out support vector machine (SVM) semi-supervised classification on the hyperspectral image to obtain a first classified image Image 1, and carrying out the SVM semi-supervised classification on the clustered indication characteristics to obtain a second calssified image Image 2; and step 3: establishing a clustering and SVM cooperation framework, inserting classification results of the Image 1 and the Image 2 into the clustering and SVM cooperation framework to be cooperatively analyzed so as to obtain a final hyperspectral classified image. The device comprises a clustering module, a classification module and a cooperative analysis module. The method and device for the hyperspectral image semi-supervised classification are feasible, capable of performing high-precise clustering and SVM-cooperative.

Description

Technical field [0001] The invention relates to a classification method and device for remote sensing hyperspectral images, and more specifically, to a semi-supervised classification method and device for hyperspectral images in collaboration with clustering and support vector machine (SVM). Background technique [0002] Currently commonly used hyperspectral image classification algorithms can be divided into supervised and unsupervised algorithms. Traditional supervised classification methods include spectral angle mapping method, parallelepiped method, maximum likelihood method, minimum distance method, Mahalanobis distance method; traditional unsupervised classification methods include IsoData method, K-Means method, etc. In addition to the above traditional methods, there are new classification methods, such as neural networks, decision trees, SVM, and expert systems. [0003] However, the hyperspectral image has many bands and large data volume, and the acquisition cost of cl...

AI Technical Summary

Problems solved by technology

Clustering largely reflects the internal data structure of hyperspectral images, and there is no semi-supervised classification method for hyperspectral images that can effectively combine clustering information

Images