Multi-feature Bp Neural Network Remote Sensing Image Classification Combined With DT-CWT Decomposition

Remote sensing technology is of great significance for the collection of geophysical data and change information.Remote sensing technology plays an important role in the macro decision-making of national economy,social development and national defense construction because of the characteristics of comprehensive,macro,dynamic and rapid.It shows a broad prospect of industrialization.High resolution remote sensing image data are mainly multi-source,spatial macroscopical,time cyclical,and multi spatial resolution.Traditional remote sensing image classification methods,such as the minimum distance method,maximum likelihood classification method,overcome the disadvantages of long time and subjective influence on visual interpretation.However,the classification results of traditional methods have many problems such as more miscellaneous points and poor regional consistency.The classification accuracy is not satisfactory,and the results need further processing.The above problems bring inconvenience to remote sensing image classification.In order to solve the ambiguity and uncertainty of high resolution multi-spectral remote sensing image classification and to better overcome the influence of noise,a new BPNN(Back Propagation Neural Network)classification method of multi-spectral image,based on DT-CWT decomposition,is presented in this paper.First,the NDVI and texture features of the image are extracted to reduce the classification uncertainty caused by the problem of different objects having the same spectrum and the same objects having different spectrum in the image,then,the original spectral band,NDVI and texture features of the image are decomposed by DT-CWT to extract the Low-frequency information of the image,as well as to reduce the image noise and the presence of "salt and pepper" in the classification.Finally,the extracted low-frequency sub-graphs are input to the BP neural network and classified according to the trained network to obtain the final classification result.The results of the comparison show that the proposed method with less miscellaneous points has stronger regional consistency,higher classification accuracy and better robustness.In this paper,a BP neural network remote sensing image classification method based on DT-CWT is proposed.The research shows that this method is better than the image classification method using only multi spectral information and BP neural network.The research proves that using DT-CWT decomposition and BP neural network to classify images is an effective classification method.The research also shows that the DT-CWT decomposition of image multi features has certain effect on optimizing the operation of neural network.