Remote sensing image ground object classification method based on superpixel coding and convolution neural network

Abstract

The invention discloses a remote sensing image ground object classification method based on superpixel coding and convolution neural network, using adaptive superpixel coding and double channel convolution neural network. The remote sensing image ground object classification method based on superpixel coding and convolution neural network includes the steps: utilizing a superpixel algorithm to perform image pre-segmentation; using a cluster method to merge neighboring and similar superpixel blocks, setting the size of the taken blocks, constructing three double channel convolution neural networks with different input size; inputting samples with different taken block size into the corresponding network; using the convolution neural networks to extract the data characteristics of two sensors respectively; merging the extracted characteristics for classification; and according to the size of the merged pixel block, determining the size of the taken blocks of the samples, and realizing adaptive selection of the utilized neighborhood information. The remote sensing image ground object classification method based on superpixel coding and convolution neural network can realize adaptive selection of the utilized neighborhood information to enable the neighborhood information to realize positive feedback effect and preferably utilize the neighborhood information to send the samples to different networks according to the neighborhood information so as to enable the samples with similar distribution to enter the same network, thus effectively improving the classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a ground object classification method based on superpixel coding and convolutional neural network, which can be used for multi-city multi-spectral remote sensing images. Background technique [0002] Feature extraction and classification technology based on multispectral data has always been one of the hot issues in the field of remote sensing. The convolutional neural network model based on deep learning is widely used in multispectral image classification, which utilizes multiple convolutional and pooling layers to extract nonlinear features that are highly invariant to multiple deformations from multispectral data, Then realize the object classification of multispectral data. In order to make full use of the spatial information provided by multispectral sensing, the neighborhood information of pixels is taken into account, that is, all the spectral inform...

AI Technical Summary

Problems solved by technology

[0003] It is relatively easy for the classification task that the training data and the test data belong to the same area, and the classification accuracy of the convolutional neural network model can reach more than 95%, but it is very difficult for the classification task of the ground objects that the training data and the test data belong to different cities , the classification accuracy is very low

Images