Hyper-spectral image classification method based on recurrent neural network

Abstract

The invention discloses a hyper-spectral image classification method based on recurrent neural network with the object to solving the problems that in prior art, the input characteristic determination ability is weak and that the extraction of local spatial characteristics is not complete. The method comprises the following steps: 1) extracting the spatial texture characteristics and the sparse representation characteristics of a hyper-spectral image and piling and combining them as the low-level characteristics; 2) extracting from the low-level characteristics the sample local spatial sequence characteristics; 3) according to the local spatial sequence characteristics, creating a recurrent neural network model; and utilizing the training sample local spatial sequence characteristics to train the recurrent neural network model parameters; and 4) inputting the testing sample local spatial sequence characteristics into the well-trained recurrent neural network model; obtaining the highly abstract high-level semantic characteristics and obtaining the classification information of the testing sample. According to the deep learning method of the invention, the correct efficiency for hyper-spectral image classification is increased and the method can be used for vegetation investigation, disaster monitoring, map making and intelligence obtaining.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a hyperspectral image classification method, which can be used for the classification of hyperspectral remote sensing images. Background technique [0002] At present, with the continuous improvement of the spectral resolution of remote sensing sensors, people's cognition of the spectral properties and characteristics of ground objects is also deepening. Many features of ground objects hidden in the narrow spectral range are gradually discovered, which greatly accelerates the development of remote sensing technology. , making hyperspectral remote sensing one of the most important research directions in the field of remote sensing in the 21st century. [0003] Different from multi-spectral remote sensing, spectral remote sensing uses imaging spectrometers with nanoscale spectral resolution to simultaneously image surface objects with dozens or hundreds of bands, and can obt...

AI Technical Summary

Problems solved by technology

The classification effect of this method is average, the correct rate is not high, and there are many shortcomings, such as directly using spectral features as input features, which contains too much messy noise and weak discrimination, and cannot achieve good classification results; and in In the extraction of local spatial features, simply select all the pixels in the neighborhood without processing, and the pixels that are significantly different from the central pixel will seriously affect the classification accuracy

Images