Method for classifying remote sensing images

Abstract

The invention provides a method for classifying remote sensing images, comprising the following steps of: firstly acquiring samples of surface features in a remote sensing image, then constructing a semi-supervised neural network model used for surface feature classification, and finally classifying the surface features based on a semi-supervised neural network. According to the method for classifying the remote sensing images provided by the invention, a structural error is introduced into the semi-supervised neural network for substituting an experience error, so that classification error caused by local minimum locally obtained by a target function is effectively avoided; and a quasi-Newton extreme value solving algorithm used for solving non-linear optimization is introduced in an extreme value solving process, so that surface feature classification accuracy is effectively improved, and beneficial guarantee is provided for applications such as environmental monitoring and topographic mapping which are further carried out subsequently.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to a method for classifying remote sensing image features. Background technique [0002] Remote sensing images are playing an increasingly important role in various fields of the national economy. Among them, the classification of remote sensing images is particularly important, such as monitoring soil and water loss based on vegetation coverage, calculating and estimating losses based on classified marine oil spill areas, and environmental protection. , The results obtained through remote sensing image classification can automatically generate surveying and mapping maps, etc. In image processing, according to whether the samples used in the classification process are marked or not, the existing remote sensing image classification methods are divided into three types: fully supervised, semi-supervised and unsupervised methods. The document "Semisupervised Neural Netwo...

AI Technical Summary

Problems solved by technology

However, the classification training process of this method is complicated, the estimation error is large, and the discriminant function is determined by empirical error, the classification accuracy is not high and it will fall into a local optimum, and its generalization ability still has room for improvement

Images