jj_kan

I can to offer the example of of practice experience results. RS Chief specialists have recommend in classification Landsat data use the principle: 30 - 50 training plots (AOI or ROI) for 1 class. Minimum size one plot - 3x3 pixels (1 ha).

Very thanks for the information. I'll try to do it.

Hello everybody Maybe someone had the experience how to separate the sand pits or open-cut mines with using high-resolution images? In ENVI I made MNF transformation of satellite image, after that I carried out unsupervised classification and had separated alone layer. This layer have objects which I looking for. But It contain and other objects like: roads, home.... Usual classification did not gave good result. In addition I did Object-oriented classification. But I had the same result. I will be glad any information..(Articles, methods.....) Thanks