Hyper-spectral image classification method and device under double-branch deep structure

Abstract

The invention provides a hyper-spectral image classification method and device under a double-branch deep structure so that the image classification accuracy can be improved obviously. On the one hand, the method comprises four steps of image preprocessing, feature extraction, spatial-spectral feature fusion, and classification. At the image preprocessing step, a training set and a testing set needed by two branches are selected and the selected training set and testing set are normalized; at the feature extraction step, a double-branch deep structure is constructed to extract deep semantic information of a hyper-spectral remote-sensing image; at the spatial-spectral feature fusion step, soft-max classifiers are added at tail ends of the two branch network structures to obtain sample probability matrixes respectively, and then a spectral feature and a spatial feature that are obtained by the double-branch deep structure are fused by using a multi-source feature fusion technique; and atthe classification step, the fused features are classified by using a support vector machine. On the other hand, the corresponding device is composed of a pre-processing module, a double-branch deepstructure module, a fusion module, and a classification and evaluation module.

Description

technical field [0001] The invention relates to a hyperspectral image classification method and device under a double-branch deep structure, belonging to the technical field of remote sensing information processing. Background technique [0002] At present, the intelligent interpretation of hyperspectral remote sensing images has been widely used in agriculture, forestry, geology, star survey, military and other fields. Geological conditions; in the military, hyperspectral sensors can detect various camouflages that cannot be captured by ordinary cameras or video cameras, and can be applied to battlefield intelligence reconnaissance and target recognition (Kumar et al., 2001; Tong Qingxi et al., 2006). Feature extraction and fusion technology is a very important link in the process of intelligent image interpretation, which directly affects the accuracy of image interpretation. However, the current image feature extraction methods often ignore the deep semantic information ...

AI Technical Summary

Problems solved by technology

This fusion method is usually accompanied by redundancy and noise, and the untargeted feature selection method ignores the correlation between features

Images