Estimativa de falhas em semeadura de soja (Glycine Max (L) Merrill) a partir de imagens de sensoriamento remoto

• Ano de defesa: 2020
• Autor(a) principal: Wouters, Jonathas Mateus
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Santa Maria; Brasil; Agronomia; UFSM; Programa de Pós-Graduação em Agricultura de Precisão; Centro de Ciências Rurais
• Palavras-chave em Português: Drone; Alta resolução espacial; Processamento digital de imagens; Análise estatística; Agricultura de precisão; High spatial resolution; Digital image processing; Statistical analysis; Precision agriculture; CNPQ::CIENCIAS AGRARIAS::AGRONOMIA
• Link de acesso: http://repositorio.ufsm.br/handle/1/23562

Currently, there is a great use of remotely controlled aircraft in agriculture and the need to increasingly optimize the production of Brazilian crops. To this end, the work seeks to analyze the failures in sowing / planting in soybean crops from the interpretation of images obtained with this type of equipment. In this work, the images were obtained at flight heights of 60, 90 and 120 meters, and on four post-planting dates, 15, 22, 32 and 37 days after sowing, the processing was performed in the QGIS software generating images with the percentage of coverage by soybean plants. Analyzing the classified images it was possible to estimate the development of soybean plants, it was found that there was no significant difference between the flight heights, so the best time to evaluate sowing failures was 120 meters, as it allows a larger area covered on the same flight. The flight that best represented the coverage percentage of soybean plants was the fourth (37 after sowing), since it occurred right after the effect of a herbicide application making the classification more efficient without the presence of weeds.