Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-23T20:02:06Z No. of bitstreams: 1 RafaellaCristianneAlvesDoNascimento_DISSERT.pdf: 1896894 bytes, checksum: 7c8df9fd5eb6694e9ab97eb6419d27ec (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-27T19:57:21Z (GMT) No. of bitstreams: 1 RafaellaCristianneAlvesDoNascimento_DISSERT.pdf: 1896894 bytes, checksum: 7c8df9fd5eb6694e9ab97eb6419d27ec (MD5) / Made available in DSpace on 2016-06-27T19:57:21Z (GMT). No. of bitstreams: 1 RafaellaCristianneAlvesDoNascimento_DISSERT.pdf: 1896894 bytes, checksum: 7c8df9fd5eb6694e9ab97eb6419d27ec (MD5) Previous issue date: 2014-01-23 / Propomos um sistema de localiza??o de rob?s m?veis em ambientes fechados utilizando a t?cnica de vis?o global. Uma aplica??o pode ser em museus virtuais, que podem ser acessados por usu?rios do mundo inteiro, usando um avatar rob?tico, possibilitando ainda a esses mesmos usu?rios a oportunidade de estabelecer uma presen?a virtual dentro do museu real, a atrav?s de uma plataforma rob?tica m?vel colocada dentro do espa?o f?sico real, permitindo a esse usu?rio locomover-se virtualmente dentro do museu real. O sistema aqui proposto visa melhorar o processo de localiza??o desse guia rob?tico dentro do ambiente interno, j? que os sensores instalados no mesmo acumulam erros, sem contar o fato de que as constantes mudan?as ocorridas nesse tipo de ambiente acaba muitas vezes por introduzir ainda mais erros, ou mesmo at? invalidar os dados obtidos devido a um total bloqueio de um determinado sensor. Por ser um m?todo de localiza??o que s? leva em considera??es informa??es do momento atual, a localiza??o de rob?s atrav?s de imagens adequa-se bem a esse tipo de ambiente. Al?m disso ela proporciona tamb?m resultados mais acurados em tempo real. / The localization of mobile robots in indoor environments finds lots of problems such as accumulated errors and the constant changes that occur at these places. A technique called global vision intends to localize robots using images acquired by cameras placed in such a way that covers the place where the robots movement takes place. Localization is obtained by marks put on top of the robot. Algorithms applied to the images search for the mark on top of the robot and by finding the mark they are able to get the position and orientation of the robot. Such techniques used to face some difficulties related with the hardware capacity, fact that limited their execution in real time. However, the technological advances of the last years changed that situation and enabling the development and execution of such algorithms in plain capacity. The proposal specified here intends to develop a mobile robot localization system at indoor environments using a technique called global vision to track the robot and acquire the images, all in real time, intending to improve the robot localization process inside the environment. Being a localization method that takes just actual information in its calculations, the robot localization using images fit into the needs of this kind of place. Besides, it enables more accurate results and in real time, what is exactly the museum application needs.