Data fusion approach for eucalyptus trees identification

Remote sensing is based on the extraction of data, acquired by satellites or aircrafts, through multispectral images, that allow their remote analysis and classification. Analysing those images with data fusion techniques a promising approach for identification classification forest types. Fusion can aggregate various sources heterogeneous information to generate value-added maps, facilitating forest-type This work applies algorithm, denoted FIF (Fuzzy Information Fusion), which combines computational intelligence multicriteria concepts techniques, automatically distinguish Eucalyptus trees from satellite images. The algorithm customization was performed Portuguese area planted Eucalyptus. After customizing validating several representative scenarios assess its suitability automatic Eucalyptus, we tested large tile obtaining sensitivity 69.61%, specificity 99.43%, an overall accuracy 98.19%. demonstrates potential our classify specific types since this novel dedicated eucalyptus trees.