Estimating of surface spectral values by feed-forward neural networks training with remote-field radiometer data
暂无分享,去创建一个
A new method (ES2N2) for estimating surface spectral values based on feed-forward neural networks, has been developed. The neural network has been trained with pairs of remote-field data. Good estimations have been obtained, especially for land covers with low spectral response.
[1] María Amparo Gilabert,et al. An atmospheric correction method for the automatic retrieval of surface reflectances from TM images , 1994 .
[2] Didier Tanré,et al. Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: an overview , 1997, IEEE Trans. Geosci. Remote. Sens..
[3] P. Chavez. An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data , 1988 .
[4] J. L. Barker,et al. Landsat MSS and TM post-calibration dynamic ranges , 1986 .