Lama

Cocktail Demonstration

This demo describes the use of a knowledge-based system to manage a library of image processing programs which performs the computation of land cover mixing in pixels of a multi-spectral satellite image. See IJRS article

This system has been developed to help naturalists, such as geologists, pedologists, or foresters who are not specialists in computer vision. It automatically processes the data coming from satellites.

The role of such a system is to convert the requirements of a user, expressed in terms of user requests, into the correct image processing commands. Consequently, the users can concentrate their attention on the interpretation of the results and not on the data management.

Inputs Data

The input image comes from SPOT satellite or from LANDSAT one.

Screen dumps

This is a part of the Cocktail knowledge base. Cpmplex operator are in white an terminal operator are in steel blue. The decomposition link are in blue for the SEQuential one and in black for the OR. The data flow is symbolised by the red arrows.

Input image from spot
This is the input image)		 Definition of spectres
Result Image (classification)
(the white pixel is rocks, green is grass, brown is forest, black is unknow)		 Result Image (validation)
The image represents the validation coefficient (white is 100% reliable and black is 0% (in fact unknown)
Regis Vincent