Detecção e restauração de áreas sombreadas em imagens digitais de alta resolução espacial

• Ano de defesa: 2014
• Autor(a) principal: Azevedo, Samara Calçado [UNESP]
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual Paulista (Unesp)
• Palavras-chave em Português: Cartografia; Sombras e sombreados; Radiometria; Morfologia matemática; Imagens digitais; Cartography
• Link de acesso: http://hdl.handle.net/11449/124062; http://www.athena.biblioteca.unesp.br/exlibris/bd/cathedra/02-06-2015/000831684.pdf

New possibilities for urban mapping have been created by improved level of detailing in images. High spatial, spectral and radiometric resolution provides advantages in identifying individual elements in urban areas, such as houses, trees, buildings, etc. However, these tall objects often throw up unwanted information as shadows, which influence visual image degradation and the spectral response of targets. This research aims to establish a methodology to detect and restore shadows in high spatial resolution digital images in urban areas in order to reduce radiometric differences caused by shadows. The proposed algorithm was implemented in Matlab and applies morphological operators based on the low intensity property they present in the images. The black top-hat by area closing is used to highlight shadows detected in the following with automatic binarization. In the restoration step, objects defined by the labelling of binary images are corrected by local histogram matching, which combines statistical parameters extracted from each shadow area and their neighborhood non-shadow areas...