Processamento digital de imagens para inferência de risco de doença fúngica da bananicultura

• Ano de defesa: 2012
• Autor(a) principal: Bendini, Hugo do Nascimento
• Orientador(a): Cruvinel, Paulo Estevão
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• País: BR
• Palavras-chave em Português: Processamento de imagens; Fusão de imagens; Sensoriamento remoto; Modelos de risco; Krigagem; Modelos de probabilidade; Risco climático; Sigatoka-Negra
• Palavras-chave em Inglês: Image processing; Image Fusion; Remote Sensing; Models of Probability; Climatic Risk; Black Sigatoka; Risk Model
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://repositorio.ufscar.br/handle/ufscar/518

The digital image processing has been used to solve a significant number of problems in the agricultural sector, especially with the evolution of remote sensing systems. This work presents a computational model based on digital image processing and remote sensing to infer about the risk in the agricultural environment. To validate the method, a experimental study was conducted about the risk of fungal disease in banana plantations. Temporal series of meteorological and monitoring data of the disease, organized in classes for the definition of probability distribution models, based on polynomial functions were used to validate results as well as satellite images integrated by fusion techniques, geometric corrections and re-sampling with interpolators based on kriging techniques. Fusion methods by IHS (Intensity, Hue, and Saturation) and PCA (Principal Component Analysis) and the Gaussian models, exponential and cylindrical for the ordinary kriging were tested. The IHS fusion technique demonstrated to be more interesting in relation the PCA technique, with correlation coefficients between bands 2, 3 and 4 originals and hybrids, of 0.2318, 0.0304 and 0.1800, respectively. The method of ordinary kriging for re-sampling of the images showed better results when adjusted by the Gaussian model. The proposed method is feasible to the development of risk maps of disease occurrence, since confer spatial and temporal variability in relation to the model existing on the literature for the region.