Multispectral remote sensing image terrain classification method based on deep and semi-supervised transfer learning

Abstract

The invention discloses a multispectral remote sensing image terrain classification method based on deep and semi-supervised transfer learning. A training data set and kNN data are extracted according to ground truth; the training data set is divided into two parts to be trained respectively; a multispectral image to be classified is inputted, and two classification result images are obtained from two CNN models; two kNN nearest neighbor algorithm images are constructed according to the training samples; the tested data are extracted by using the two classification result images, and the data are classified by using the kNN nearest neighbor algorithm; the classification result images are updated; the training samples and the kNN training samples of cooperative training are updated; and two cooperative training CNN networks are trained again, and the points having the class label of the test data set are classified by using the trained model so that the class of partial pixel points in the test data set is obtained and compared with the real class label. The k nearest neighbor algorithm and the sample similarity are introduced so that deviation of cooperative training can be prevented, the classification accuracy in case of insufficient training samples can be enhanced and thus the method can be used for target recognition.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a multispectral remote sensing image ground object classification method based on deep semi-supervised transfer learning, which classifies multispectral images with a small number of marked samples based on pixel levels, and can also be used for target recognition. Background technique [0002] Multispectral remote sensing image is an image obtained by observing the same object (territory or target) in multiple narrow spectral bands at the same time, which reflects the reflection, transmission or radiation characteristics of the observed object in each narrow spectral band, so it includes more information about the observed objects. With the continuous improvement of the quality and quantity of satellite sensors, the classification research theory for multispectral remote sensing images has gradually matured. Compared with traditional remote se...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a multi-spectral remote sensing image classification method based on deep semi-supervised transfer learning to improve the classification accuracy of the target domain and solve the problem of insufficient training samples and training problems. Problems with inconsistent distribution of test samples

Images