Method and device for classifying remote images by integrating edge information and support vector machine

Abstract

The invention relates to a method and a device for classifying remote images by integrating edge information and a support vector machine. The method includes the steps: performing pixel-wise support vector machine classification for the remote images which are subjected to preprocessing and characteristic extraction; performing edge detection for the remote images which are subjected to preprocessing and characteristic extraction so as to obtain a discontinuous one-pixel wide edge map; performing edge connection for the discontinuous one-pixel wide edge map subjected to noise edge removal so as to obtain a closed edge map; and integrating the closed edge map to a map subjected to pixel-wise support vector machine classification so as to obtain a classified result map integrating the edge information. By the aid of the method and the device, non-robustness of existing partitional-clustering-segmentation-based classification of the hyperspectral images by integrating space and spectral information is overcome, and the problem of dimensional proportion selection of common fixed-window-size-based methods such as morphology filtering by integrating the space and spectral information is solved.

Description

technical field [0001] The present invention relates to a method and a device for classifying remote sensing images, more specifically, to a method and device for classifying remote sensing images by fusing edge information and support vector machines. Background technique [0002] Hyperspectral images with high spectral resolution have a wide range of applications, such as mineral detection, pollution monitoring, precision agriculture, etc. Classification is one of the very important processing procedures of hyperspectral images. Traditional hyperspectral image classification methods are mainly based on spectral information, and rarely consider spatial information. [0003] The existing commonly used hyperspectral image fusion spatial information and spectral information classification methods include Markov random field, morphological pointer and morphological filtering. However, these methods use a fixed-size window to obtain spatial information, which leads to the prob...

AI Technical Summary

Problems solved by technology

However, these methods use a fixed-size window to obtain spatial information, which leads to the problem of choosing the size ratio

Another classification method is to integrate spatial information into a multi-kernel learning method, which also has the problem of size ratio selection, and the computational cost of this method is very high

[0004] Another way to fuse spatial information is to fuse the pixel-by-pixel classification results with the segmentation results obtained by Partitional Clustering, but the results of this method are not robust.

Images