Extração de linhas de imagens de sensoriamento remoto.

• Autor(a) principal: Abreu, Márcia Luzia Correia de
• Data de Publicação: 2012
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da UERJ
• Texto Completo: http://www.bdtd.uerj.br/handle/1/10823
• topic: Detection of lines; Detection of edges; Power lines; Canny filter; Hough transform; Radon transform; Detector SUSAN; Mathematical morphology; Extração de linhas; Detecção de bordas; Filtro Canny; Linhas de transmissão; Transformada de Hough; Transformada de Radon; Detector SUSAN; Morfologia matemática; CNPQ::ENGENHARIAS

This dissertation has the objective to verify the contribution of different tips for line detection, to the classification of multispectral images, with the possible use in the discrimination and mapping of class of covering of the land. In this context, the comparison between different techniques of detection of characteristics for extraction of power lines in agricultural areas is affected, namely, distinction techniques using variation of contrast and morphologic filtering, and detection of edges using filter Canny and detector SUSAN. In this case were used techniques of extraction of lines with Hough Transform and Radon Transform too, using different algorithms in aerial images of remote sensing. These results had evaluated and compared producing tables of efficiency for each procedure. These tables direct the different solutions that change of boarding depending of the final objective of the detection of the Power Lines.