Method for the automatic detection and identification of objects in multi-spectral remote sensing data

Dei invention relates to a method for the automatic detection and Identifiktion of objects in multi-spectral remote sensing data, comprising the steps of: DOLLAR A a) performing a training area allocation test (TAT), DOLLAR A b) carrying out a structural analysis testing (SAT), DOLLAR A c) performing an environmental analysis test ( UAT), DOLLAR a d) performing a Multispektralanalysetests (MST) with the aid of a-priori information weighted by characteristic spectral signatures of the objects to be identified, DOLLAR a e) combining the process results by the method claims a) -d) including a -priori information and DOLLAR A f) classification of the detected objects by means of the determined according to method step e) data base.