Métodos de classificação de imagens na identificação de áreas cultivadas com citros

• Autor(a) principal: Barbosa, Ana Paula [UNESP]
• Data de Publicação: 2011
• Outros Autores: Campos, Sergio [UNESP], Zimback, Célia Regina Lopes [UNESP], Barros, Zacarias Xavier de [UNESP]
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.17224/EnergAgric.2011v26n3p14-25; http://hdl.handle.net/11449/137483
• topic: LANDSAT; Images classifiers; GIS; LANDSAT; Classificadores de imagens; SIG

Image classification is the process of extraction of information to recognize patterns and homogeneous objects in remote sensing products to map themes of interest in areas of the surface. This study aimed to compare the efficiency of classification methods of orbital images in areas cultivated with citrus. The study area is located at Água Branca Farm, Bariri City/SP. The GIS - Idrisi 15.0 was used in the image processing of TM LANDSAT-5 satellite images, path/row 221/75, 05/26/2007. The evaluation results of the classification accuracy were satisfactory and the classification of the CLUSTER algorithm had very good quality (0.6485) and the MAXVER algorithm had excellent rating, with kappa of 0.8818. The methods used for the discrimination of areas cultivated with citrus showed different efficiencies in the classification of images. The classifications had satisfactory performance and the CLUSTER classifier was the one that is closer to the real area.