Detalhes bibliográficos
Ano de defesa: |
2011 |
Autor(a) principal: |
Fazan, Antonio Juliano [UNESP] |
Orientador(a): |
Não Informado pela instituição |
Banca de defesa: |
Não Informado pela instituição |
Tipo de documento: |
Tese
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Estadual Paulista (Unesp)
|
Programa de Pós-Graduação: |
Não Informado pela instituição
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: |
|
Link de acesso: |
http://hdl.handle.net/11449/114022
|
Resumo: |
This research presents a semi-automatic method for rectilinear building roof contours extraction, based on the integration of high resolution aerial imagery taken from dense urban scenes and light detection and ranging (LiDAR) data. 3D information derived from LiDAR data and the high roof contour delineation accuracy in the aerial imagery can be combined in order to accurately extract the building roof contours. The proposed method is organized as an optimization problem, in which a mathematical model is used to represent the building roof contours in an object-space reference frame. The global solution for the resulting problem is found by using the dynamic programming optimization technique and corresponds to 3D polygons describing the building roof contours. The mathematical model describing a building roof contour is firstly expressed in an image-space reference frame, by using a snakes energy function, and then, the resulting snakes-based mathematical model is totally reformulated in such a way to describe building roof contours directly in an object-space reference frame, by integrating the LiDAR data represented as a triangulated irregular network (TIN) structure... |