A methodology for woody crop location and discrimination in remote sensing

In this paper we provide a solution to a common problem in remote sensing when woody crops (almond and olive fields, vineyards, and so on) must be located and discriminated. Experience has taught us that, currently, the usual way to accomplish this task is with a photointerpreter digitizing on the images. Our solution is based on a widely used and accurate texture segmentation such as multichannel filtering (MCF) based on Gabor functions (GF) and on the ECHO (extraction and classification of homogeneous objects) approach to carry out the segmentation process. The test bed consisted of high-spatial-resolution images such as aerial photography and those images scanned by the Daedalus-1268 multispectral scanner on board an airborne platform. Favorable results were yielded with both types of images, in particular the discrimination between almond and olive fields was carried out in the case of multispectral images