MÉTODO DE CÁLCULO DE TRAJETÓRIA DE MÁQUINAS AGRÍCOLAS UTILIZANDO PROCESSAMENTO DE IMAGENS EM SMARTPHONES

Detalhes bibliográficos
Ano de defesa: 2015
Autor(a) principal: Monteiro Junior, Marcos lattes
Orientador(a): Vaz, Maria Salete Marcon Gomes lattes
Banca de defesa: Britto Junior, Alceu de Souza lattes, Weirich Neto, Pedro Henrique lattes
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: UNIVERSIDADE ESTADUAL DE PONTA GROSSA
Programa de Pós-Graduação: Programa de Pós Graduação Computação Aplicada
Departamento: Computação para Tecnologias em Agricultura
País: BR
Palavras-chave em Português:
Palavras-chave em Inglês:
Área do conhecimento CNPq:
Link de acesso: http://tede2.uepg.br/jspui/handle/prefix/131
Resumo: Agricultural machinery has mechanisms which automate them; however, it is still an expensive GPS based resource. The use of computational vision is an alternative or an addition to the use of GPS. Not long ago, the use of computational vision was exclusive to computers with huge processing capabilities, and its use in agricultural machinery was impracticable due to adverse field conditions. The evolution of the processors made computational vision possible in cellphones, whose hardware is robust for not having mechanical components and for being dust and, some models, humidity proof. This work describes the creation of a method developed for smartphone based mobile devices with the Android operational system. This system has the purpose of providing the calculation of the trajectories of agricultural machinery or robots, at pulverization lines. The method uses cameras that are present on the smartphones themselves in order to capture the image of the route to be calculated and processed by the phone. The process uses methods of computational vision with the aid of an algorithm to smooth the movements and to take decisions in order to not perform unnecessary movements. The method uses open-source softwares, like the Openvc library, the Android system and its tools of the programming, and in the IOIO hardware platform. The system was field tested, in a robot named NAVIGO, developed in the graduation program of Applied Computation at the Universidade Estadual de Ponta Grossa. The smartphone is coupled to the NAVIGO and it communicates with IOIO through Bluetooth. . Computer vision processing was performed on the smartphone , obtaining satisfactory results , proving that smart phones , are robust , and have the advantage of having numerous sensors embedded in the hardware and are able to perform tasks that were previously exclusive to computers. Furthermore small devices that use computer vision , as proposed in the work can be great tools in agriculture large areas of difficult access machinery .