Research on Classification Method of Airborne Geophysical Remote Sensing Data Based on Self-Coding Neural Network
The collection process of airborne geophysical remote sensing data is affected by external factors such as electromag-netic wave radiation,resulting in low classification accuracy of airborne geophysical remote sensing data.Therefore,a classification method for airborne geophysical remote sensing data based on self-coding neural network is proposed.The classification standards for remote sensing data are set according to the basic characteristics of aerial geophysical exploration objects,The preprocessing of air-borne geophysical remote sensing data is completed through the steps such as the radiation correction,geometric correction,and noise elimination,and the self-coding neural network is built,the self-coding neural network algorithms are used to extract remote sensing data features from spectrum,shape,texture,and other aspects,and the type of aerial geophysical remote sensing data is determined through feature matching.Through classification performance testing experiments,it is concluded that the average success and error rates of the proposed method for global remote sensing data classification are 99.8％and 0.6％,respectively.The average success and error rates for local remote sensing data classification are 99.8％and 0.3％,respectively,indicating that the proposed method has a significant advantage in classification performance.
万方数据
维普
