基于自组织神经元网络的可见光与热红外遥感数据融合方法

Up to now, there are a few methods of fusion of visible and thermal infrared data among approaches of multi-source remote sensing fusing. As a result, the potential of two different kinds of data were not entirely dug and accuracy is not good. In this paper, an approach which can take advantage of high spatial resolution feature of visible data and high temporal resolution feature of thermal infrared data, was adapted that is a nonlinear fusion method based on GA-SOFM (Genetic Algorithms & Self-Organizing Feature Maps) -Artificial Neural Network (ANN). According to this method, a result of fusing both visible data with spatial resolution feature and thermal infrared data with temporal feature was finished. Finally, a case of testing method was showed, utilizing the data. The conclusions show it is a new approach to quickly estimate and acquire high resolution land surface temperature.