Remote sensing image lake ice classification and recognition method based on neural network

Abstract

The invention discloses a remote sensing image lake ice classification and recognition method based on a neural network. The method includes: firstly obtaining a remote sensing image of an annual winter ice period from a database, and performing radiometric calibration processing on the obtained remote sensing image to obtain a preliminary remote sensing image; performing FLAASH atmospheric correction on the obtained remote sensing image after radiometric calibration processing, and obtaining the final processed remote sensing image; constructing a BP neural network model; training the neuralnetwork model constructed in the step (3), and testing the trained neural network model to determine whether the accuracy requirement is satisfied, going to the step (5) if so, and returning to reconstruct the neural network model if not; and adding the final processed remote sensing image to the constructed neural network model, and classifying lake ice in the remote sensing image. The classification accuracy obtained by the invention is high.

Description

technical field [0001] The invention belongs to the technical field of neural network classification application, in particular to a neural network-based remote sensing image lake ice classification and recognition method. Background technique [0002] Common techniques for classification and identification of lake ice in remote sensing images are based on traditional statistical analysis, and specific algorithms include parallelepiped, minimum distance, Mahalanobis distance, and maximum likelihood. The parallelepiped has "corners" that can easily lead to misclassification; whether the classification of the minimum distance algorithm is correct or not depends largely on the average value of the sample; if the covariance matrix in the Mahalanobis distance uses a large value, it is easy to cause transitional classification and every The numerical requirement of an input band must obey the normal distribution; when the number of bands increases slightly during the maximum likel...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a neural network-based neural network model that applies the technology based on the BP neural network model to the field of remote sensing image lake ice classification to solve the problems of low classification accuracy in the prior art. Classification and recognition method of lake ice in remote sensing image based on network

Images