The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Em muitas áreas, como administração municipal e gestão de instalações, há um número crescente de solicitações de um Sistema de Informação Geográfica (GIS) que forneça aos usuários funções de mapeamento automatizadas. Um mecanismo que exiba vistas 3D de uma cena urbana é particularmente necessário porque permitiria a construção de um ambiente intuitivo e compreensível para o gerenciamento de objetos na cena. Neste artigo, apresentamos um novo sistema de modelagem urbana utilizando abordagens baseadas em imagens e geometria. Nosso método é baseado em um novo conceito no qual uma ampla área urbana pode ser exibida com imagens fotorrealistas naturais, e cada objeto desenhado na vista pode ser identificado apontando para ele. Primeiro, para gerar vistas urbanas naturais a partir de qualquer ponto de vista, empregamos um método de renderização baseado em imagem, Passo a passo da imageme modifique-o para lidar com imagens aéreas. Este método pode interpolar e gerar vistas naturais através da montagem de diversas fotografias de origem. A seguir, para identificar cada objeto na cena, recuperamos sua forma utilizando técnicas de visão computacional (uma abordagem baseada em geometria). A forma aproximada de cada edifício é reconstruída a partir de várias imagens aéreas e, em seguida, a sua posição desenhada na vista gerada também é determinada. Isto significa que se torna possível identificar cada edifício a partir de uma visão urbana. Combinamos essas duas abordagens gerando um novo estilo de gestão de informações urbanas. Os usuários do sistema podem desfrutar de uma compreensão intuitiva da área e identificar facilmente o seu alvo, gerando vistas naturais de qualquer ponto de vista e reconstruindo adequadamente as formas dos objetos. Fizemos um protótipo de sistema deste novo conceito de GIS, que mostrou a validade do nosso método.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Katsuyuki KAMEI, Wayne HOY, Takashi TAMADA, Kazuo SEO, "Modeling of Urban Scenes by Aerial Photographs and Simply Reconstructed Buildings" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1441-1449, July 2000, doi: .
Abstract: In many fields such as city administration and facilities management, there are an increasing number of requests for a Geographic Information System (GIS) that provides users with automated mapping functions. A mechanism which displays 3D views of an urban scene is particularly required because it would allow the construction of an intuitive and understandable environment for managing objects in the scene. In this paper, we present a new urban modeling system utilizing both image-based and geometry-based approaches. Our method is based on a new concept in which a wide urban area can be displayed with natural photo-realistic images, and each object drawn in the view can be identified by pointing to it. First, to generate natural urban views from any viewpoint, we employ an image-based rendering method, Image Walkthrough, and modify it to handle aerial images. This method can interpolate and generate natural views by assembling several source photographs. Next, to identify each object in the scene, we recover its shape using computer vision techniques (a geometry-based approach). The rough shape of each building is reconstructed from various aerial images, and then its drawn position on the generated view is also determined. This means that it becomes possible to identify each building from an urban view. We have combined both of these approaches yielding a new style of urban information management. The users of the system can enjoy an intuitive understanding of the area and easily identify their target, by generating natural views from any viewpoint and suitably reconstructing the shapes of objects. We have made a prototype system of this new concept of GIS, which have shown the validity of our method.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1441/_p
Copiar
@ARTICLE{e83-d_7_1441,
author={Katsuyuki KAMEI, Wayne HOY, Takashi TAMADA, Kazuo SEO, },
journal={IEICE TRANSACTIONS on Information},
title={Modeling of Urban Scenes by Aerial Photographs and Simply Reconstructed Buildings},
year={2000},
volume={E83-D},
number={7},
pages={1441-1449},
abstract={In many fields such as city administration and facilities management, there are an increasing number of requests for a Geographic Information System (GIS) that provides users with automated mapping functions. A mechanism which displays 3D views of an urban scene is particularly required because it would allow the construction of an intuitive and understandable environment for managing objects in the scene. In this paper, we present a new urban modeling system utilizing both image-based and geometry-based approaches. Our method is based on a new concept in which a wide urban area can be displayed with natural photo-realistic images, and each object drawn in the view can be identified by pointing to it. First, to generate natural urban views from any viewpoint, we employ an image-based rendering method, Image Walkthrough, and modify it to handle aerial images. This method can interpolate and generate natural views by assembling several source photographs. Next, to identify each object in the scene, we recover its shape using computer vision techniques (a geometry-based approach). The rough shape of each building is reconstructed from various aerial images, and then its drawn position on the generated view is also determined. This means that it becomes possible to identify each building from an urban view. We have combined both of these approaches yielding a new style of urban information management. The users of the system can enjoy an intuitive understanding of the area and easily identify their target, by generating natural views from any viewpoint and suitably reconstructing the shapes of objects. We have made a prototype system of this new concept of GIS, which have shown the validity of our method.},
keywords={},
doi={},
ISSN={},
month={July},}
Copiar
TY - JOUR
TI - Modeling of Urban Scenes by Aerial Photographs and Simply Reconstructed Buildings
T2 - IEICE TRANSACTIONS on Information
SP - 1441
EP - 1449
AU - Katsuyuki KAMEI
AU - Wayne HOY
AU - Takashi TAMADA
AU - Kazuo SEO
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - In many fields such as city administration and facilities management, there are an increasing number of requests for a Geographic Information System (GIS) that provides users with automated mapping functions. A mechanism which displays 3D views of an urban scene is particularly required because it would allow the construction of an intuitive and understandable environment for managing objects in the scene. In this paper, we present a new urban modeling system utilizing both image-based and geometry-based approaches. Our method is based on a new concept in which a wide urban area can be displayed with natural photo-realistic images, and each object drawn in the view can be identified by pointing to it. First, to generate natural urban views from any viewpoint, we employ an image-based rendering method, Image Walkthrough, and modify it to handle aerial images. This method can interpolate and generate natural views by assembling several source photographs. Next, to identify each object in the scene, we recover its shape using computer vision techniques (a geometry-based approach). The rough shape of each building is reconstructed from various aerial images, and then its drawn position on the generated view is also determined. This means that it becomes possible to identify each building from an urban view. We have combined both of these approaches yielding a new style of urban information management. The users of the system can enjoy an intuitive understanding of the area and easily identify their target, by generating natural views from any viewpoint and suitably reconstructing the shapes of objects. We have made a prototype system of this new concept of GIS, which have shown the validity of our method.
ER -