Mapeado de invernaderos mediante teledetección orientada a objetos: Relación entre la calidad de la segmentación y precisión de la clasificación.

Object based image analysis (OBIA) approach has been proved as the best option when working with very high resolution (VHR) satellite imagery. The first step of OBIA, referred to as segmentation, is to delineate objects of interest. Determination of an optimal segmentation is crucial for a good performance of the second stage inOBIA, the classification process. The main goal of this work is to assess the multiresolution segmentation algorithm provided by eCognition software for delineating greenhouses fromWorld- View-2 multispectral orthoimages and to find the relationship between the goodness of the segmentation and the accuracy of the supervised classification. The focus is on finding the optimal parameters of the multiresolution segmentation approach (i.e., Sca- le, Shape and Compactness parameters) for plastic greenhouses. Assessment of segmentation quality was based on the Euclidean Distance 2 (ED2). Finally, we demonstrated that there was a clear relationship between the goodness of the segmentation on plastic greenhouses and the OBIA classification accuracy attained when features such as spectral, textural and vegetation indices were used. The best overall accuracy attained with the best multiresolution segmentation was slightly better than 95%