In this data structure, multiimage fusion is realized by several different area based feature selection methods, including the energy based criterion, edge detection method and using wavelet coefficient direction information in feature selection.

There are many pixel-level fusion methods for remote sensing images,but the differences of those are ambiguous because of lacking a unique description,which makes it difficult to apply image fusion purposefully.

The generalized model characterizing most remotely sensed data pixel-level fusion techniques is very important for theory analysis and application.

From the D-S(Dempster-Shafer)evidential theory for image element level data fusion to the Analytic Hierar-chy Process general evaluation method for decision making level data fusion,it provides a new so-lution for multi-factor substat.