The development of an object-oriented classification model for operational burned area mapping on the Mediterranean island of Thasos using LANDSAT TM images

Multispectral classification, one of the most commonly used methods for mapping burned areas, is based on the spectral properties of different classes of interest and employs special algorithms designed to perform various types of spectral analysis. However, the use of these classifications has been repeatedly reported to create confusion between burned areas and nonvegetation categories, especially water bodies and shaded areas. As a result of the aforementioned, spectral based classification methods cannot be used operationally for the mapping of burned areas from satellite images. On the other hand, object-oriented image classification, which is based on fuzzy logic, allows the integration of a broad spectrum of different object features, such as spectral values, shape and texture. Sophisticated classification, incorporating contextual and semantic information, can be performed by utilizing not only image object attributes but also the relationship between networked image objects. In this study the synergy of all these features allowed us to address image analysis tasks that, up till now, have not been possible. The aim of this work was to develop an object-oriented classification model for operational burned area mapping on the Mediterranean island of Thasos using LANDSAT TM images. An objectoriented specified model was used to map burned areas in two different Mediterranean areas after the LANDSAT TM images had been radiometrically, geometrically and topographically corrected. The combination of the object-oriented approach and the multispectral resolution data of LANDSAT TM showed very promising results in burned area mapping and in discriminating between burned and the other classes of confusion.