The application of GF-2 satellite images is becoming increasingly diversified,and how to obtain high-quality fusion images has become an important issue that needs to be studied.In order to obtain high spatial resolution and high spectral resolution images from the original panchromatic images and multispectral images,the Nonsubsampled Contourlet Transform algorithm is improved by combining orientation information and Pulse Coupled Neural Network.Based on the GF-2 panchromatic images and multispectral images of Lanzhou,Gansu Province as the data source,a remote sensing image fusion method combining PCNN and NSCT is proposed.Through qualitative evaluation and quantitative evaluation,compared with IHS method,BT method,PCA method and GS method,the improved method has better effect in improving spatial details and preserving spectral information.
维普
万方数据