Decomposition Mixed Pixel of Remote Sensing Image Based on Tray Neural Network Model

Aiming at the characteristics of remote sensing image classification, the mixed pixel problem is one of the main factors that affect the improvement of classification precision in remote sensing classification. In this paper, A tray neural network model was established to solve the mixed pixel classification problems. ETM+ data of DaLi in May 2001 is selected in the study. The results show that this method effectively solves mixed pixel classification problem, improves network learning speed and classification accuracy, so it is one kind of effective remote sensing imagery classifying method.