Frank Bignone - Academia.edu (original) (raw)
Papers by Frank Bignone
Springer eBooks, 1996
We present a technique to extract complex suburban roofs from sets of aerial images. Because we c... more We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be flat or rectilinear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available images, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that effectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis. * We acknowledge the support given to this research by ETH under project 13-1993-4.
ERS symposium on space at the service of our environment, 1997
1Spaceborne synthetic aperture radar (SAR) multi-pass interferometry is a technique based on the ... more 1Spaceborne synthetic aperture radar (SAR) multi-pass interferometry is a technique based on the exploitation of the phase differences between two complex radar images taken from two slightly separated positions on different dates. This measure contains not only geometric and topographic information, but also differential information covering land or atmospheric changes between the two scenes observed. These atmospheric artifacts can be an obstacle to the production of digital terrain models (DTMs) from multi-pass SAR interferometry.
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Aug 30, 2012
A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the w... more A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the well-known Pixel Factory system, will be introduced here, which enables existing digital orthoimages and mosaics to be quickly updated. The process extracts
Bulletin Societe Francaise De Photogrammetrie Et De Teledetection, 2001
. Several methods have been proposed to reconstruct houses from aerial images, most of them using... more . Several methods have been proposed to reconstruct houses from aerial images, most of them using rather specific models. These methods can not be applied when dealing with european-style houses and when a high level of detail is required. We present a system that works with rules instead of parameterizable shape models. This allows a larger variability of the objects to be extracted but also results in a more complex structure of the knowledge base and in a more sophisticated reasoning control. In the application section we demonstrate the use of such a system for reconstructing an object made up of planar surfaces from an aerial image. We will also explain how additional domain specific knowledge could speed up the extraction process and increase robustness. 1 Introduction The development of practical algorithms that support the robust and precise reconstruction of buildings and other man-made objects from aerial imagery is one of the aims of the project AMOBE 1 , a join...
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the w... more A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the well-known Pixel Factory system, will be introduced here, which enables existing digital orthoimages and mosaics to be quickly updated. The process extracts
Automatic Extraction of Man-Made Objects from Aerial Space Images, Aug 28, 1995
317 List of Workshop Participants Peggy Agouris, Institute of Geodesy & Photogrammetry, Swiss Fed... more 317 List of Workshop Participants Peggy Agouris, Institute of Geodesy & Photogrammetry, Swiss Federal Institute of Technology, ETH-Hoenggerrberg, CH-8093 Zurich, Switzerland Emmanuel Baltsavias, Institute of Geodesy & Photogrammetry, Swiss Federal Institute of Technology, ETH-Hoenggerrberg, CH-8093 Zurich, Switzerland Meir Barzohar, RAFAEL, 12 Lincoln Street, Haifa 34369, Israel Frank Bignone, Institute of Communications Technology, Swiss Federal Institute of Technology, ETH Zentrum, Gloriastrasse 35, CH-8092 Zurich, Switzerland ...
Processing of stereo scanner: from stereo plotter to pixel factory
. Several methods have been proposed to reconstruct houses from aerial images, most of them using... more . Several methods have been proposed to reconstruct houses from aerial images, most of them using rather specific models. These methods can not be applied when dealing with european-style houses and when a high level of detail is required. It is necessary to include additional domain specific knowledge in order to increase robustness and speed up the extraction process. We present a system that works with rules instead of parameterizable shape models. This allows a larger variability of the objects to be extracted but also results in a more complex structure of the knowledge base and in a more sophisticated reasoning control. In the application section we demonstrate the use of such a system for reconstructing an object made up of planar surfaces from an aerial image. 1 INTRODUCTION The development of practical algorithms that support the robust and precise reconstruction of buildings and other man-made objects from aerial imagery is one of the aims of the project AMOBE 2 , a joint...
Abstract. We present a technique to extract complex suburban roofs from sets of aerial images. Be... more Abstract. We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be at or recti-linear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available im-ages, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that eectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis. 1
We present a technique to extract complex suburban roofs from sets of aerial images. Because we c... more We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be flat or rectilinear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available images, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that effectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis.
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
ABSTRACT: This paper proposes a way forward on the use of 3D database by demonstrating new applic... more ABSTRACT: This paper proposes a way forward on the use of 3D database by demonstrating new applications which take full advantages of 3D accuracy, multi-view point of view, and real 3D textures. Such applications will cover classic mapping applications, advanced building information management, risk and disaster management and simulations. Exotic applications such as virtual reality and 3D printing will also be studied and the benefit for such applications will also be shown which is extending the classic mapping usage to more streamlined applications. 1.
SUMMARY During last two years, a boom has been seen in the use of new generation of 3D database m... more SUMMARY During last two years, a boom has been seen in the use of new generation of 3D database mainly pushed by the automatic processing of oblique imageries into real 3D models, known as example as 3D Mosaic. The introduction of such product has changed the way how people are interacting with 3D information and using that 3D information into their geographic system and organization. This paper will focus on the advantages of automated processing for 3D mosaic generation with some real case applications of such final product. Indeed, introducing automatic processing for such database has changed the current paradigm that 3D realistic database can only be acquired and generated with lots of manual work and taking months to get small area. Introducing fast automatic processing gives ability to map a whole city in few weeks and then to make available such data with very dense 3D details to numerous actors which can then integrate it into their application. It opens also real possibili...
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
With the advent of airborne digital sensor, new photogrammetric softwares is needed in order to t... more With the advent of airborne digital sensor, new photogrammetric softwares is needed in order to take into account the main advantages of these sensors. Such software should be able to handle large volume of digital data, to distribute the computation over multiple computers and to produce automatically accurate end-products. If these constraints can be met, it is then possible to produce cartographic products instantly over large areas: digital data is uploaded in a PIXEL FACTORY and accurate end-products are automatically produced by this factory. Within the paper, a description of such a framework will be presented and compared to classical photogrammetric systems.
Springer eBooks, 1996
We present a technique to extract complex suburban roofs from sets of aerial images. Because we c... more We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be flat or rectilinear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available images, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that effectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis. * We acknowledge the support given to this research by ETH under project 13-1993-4.
ERS symposium on space at the service of our environment, 1997
1Spaceborne synthetic aperture radar (SAR) multi-pass interferometry is a technique based on the ... more 1Spaceborne synthetic aperture radar (SAR) multi-pass interferometry is a technique based on the exploitation of the phase differences between two complex radar images taken from two slightly separated positions on different dates. This measure contains not only geometric and topographic information, but also differential information covering land or atmospheric changes between the two scenes observed. These atmospheric artifacts can be an obstacle to the production of digital terrain models (DTMs) from multi-pass SAR interferometry.
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Aug 30, 2012
A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the w... more A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the well-known Pixel Factory system, will be introduced here, which enables existing digital orthoimages and mosaics to be quickly updated. The process extracts
Bulletin Societe Francaise De Photogrammetrie Et De Teledetection, 2001
. Several methods have been proposed to reconstruct houses from aerial images, most of them using... more . Several methods have been proposed to reconstruct houses from aerial images, most of them using rather specific models. These methods can not be applied when dealing with european-style houses and when a high level of detail is required. We present a system that works with rules instead of parameterizable shape models. This allows a larger variability of the objects to be extracted but also results in a more complex structure of the knowledge base and in a more sophisticated reasoning control. In the application section we demonstrate the use of such a system for reconstructing an object made up of planar surfaces from an aerial image. We will also explain how additional domain specific knowledge could speed up the extraction process and increase robustness. 1 Introduction The development of practical algorithms that support the robust and precise reconstruction of buildings and other man-made objects from aerial imagery is one of the aims of the project AMOBE 1 , a join...
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the w... more A totally new automatic workflow mechanism, named Second generation Mosaic module, based on the well-known Pixel Factory system, will be introduced here, which enables existing digital orthoimages and mosaics to be quickly updated. The process extracts
Automatic Extraction of Man-Made Objects from Aerial Space Images, Aug 28, 1995
317 List of Workshop Participants Peggy Agouris, Institute of Geodesy & Photogrammetry, Swiss Fed... more 317 List of Workshop Participants Peggy Agouris, Institute of Geodesy & Photogrammetry, Swiss Federal Institute of Technology, ETH-Hoenggerrberg, CH-8093 Zurich, Switzerland Emmanuel Baltsavias, Institute of Geodesy & Photogrammetry, Swiss Federal Institute of Technology, ETH-Hoenggerrberg, CH-8093 Zurich, Switzerland Meir Barzohar, RAFAEL, 12 Lincoln Street, Haifa 34369, Israel Frank Bignone, Institute of Communications Technology, Swiss Federal Institute of Technology, ETH Zentrum, Gloriastrasse 35, CH-8092 Zurich, Switzerland ...
Processing of stereo scanner: from stereo plotter to pixel factory
. Several methods have been proposed to reconstruct houses from aerial images, most of them using... more . Several methods have been proposed to reconstruct houses from aerial images, most of them using rather specific models. These methods can not be applied when dealing with european-style houses and when a high level of detail is required. It is necessary to include additional domain specific knowledge in order to increase robustness and speed up the extraction process. We present a system that works with rules instead of parameterizable shape models. This allows a larger variability of the objects to be extracted but also results in a more complex structure of the knowledge base and in a more sophisticated reasoning control. In the application section we demonstrate the use of such a system for reconstructing an object made up of planar surfaces from an aerial image. 1 INTRODUCTION The development of practical algorithms that support the robust and precise reconstruction of buildings and other man-made objects from aerial imagery is one of the aims of the project AMOBE 2 , a joint...
Abstract. We present a technique to extract complex suburban roofs from sets of aerial images. Be... more Abstract. We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be at or recti-linear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available im-ages, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that eectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis. 1
We present a technique to extract complex suburban roofs from sets of aerial images. Because we c... more We present a technique to extract complex suburban roofs from sets of aerial images. Because we combine 2-D edge information, photometric and chromatic attributes and 3-D information, we can deal with complex houses. Neither do we assume the roofs to be flat or rectilinear nor do we require parameterized building models. From only one image, 2-D edges and their corresponding attributes and relations are extracted. Using a segment stereo matching based on all available images, the 3-D location of these edges are computed. The 3-D segments are then grouped into planes and 2-D enclosures are extracted, thereby allowing to infer adjoining 3-D patches describing roofs of houses. To achieve this, we have developed a hierarchical procedure that effectively pools the information while keeping the combinatorics under control. Of particular importance is the tight coupling of 2-D and 3-D analysis.
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
ABSTRACT: This paper proposes a way forward on the use of 3D database by demonstrating new applic... more ABSTRACT: This paper proposes a way forward on the use of 3D database by demonstrating new applications which take full advantages of 3D accuracy, multi-view point of view, and real 3D textures. Such applications will cover classic mapping applications, advanced building information management, risk and disaster management and simulations. Exotic applications such as virtual reality and 3D printing will also be studied and the benefit for such applications will also be shown which is extending the classic mapping usage to more streamlined applications. 1.
SUMMARY During last two years, a boom has been seen in the use of new generation of 3D database m... more SUMMARY During last two years, a boom has been seen in the use of new generation of 3D database mainly pushed by the automatic processing of oblique imageries into real 3D models, known as example as 3D Mosaic. The introduction of such product has changed the way how people are interacting with 3D information and using that 3D information into their geographic system and organization. This paper will focus on the advantages of automated processing for 3D mosaic generation with some real case applications of such final product. Indeed, introducing automatic processing for such database has changed the current paradigm that 3D realistic database can only be acquired and generated with lots of manual work and taking months to get small area. Introducing fast automatic processing gives ability to map a whole city in few weeks and then to make available such data with very dense 3D details to numerous actors which can then integrate it into their application. It opens also real possibili...
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images ... more Automation of Digital Terrain Model Generation and Man-Made Object Extraction from Aerial Images (AMOBE) is a joint project between the Institute of Geodesy and Photogrammetry (IGP) and the Institute of Communications Technology (Image Science Group) (IKT) at the Swiss Federal Institute of Technology in Zurich. In the project we develop methods and algorithms to detect and reconstruct man-made objects, such as buildings and roads, and to generate Digital Surface Models (DSMs) from high resolution aerial images. Primary attention in AMOBE focuses on high quality reconstruction of buildings as being one of the more predominantly and frequently occurring 3-D man-made objects in high-resolution aerial imagery. In this paper we present our research strategy, current results, and make an outlook onto future work.
With the advent of airborne digital sensor, new photogrammetric softwares is needed in order to t... more With the advent of airborne digital sensor, new photogrammetric softwares is needed in order to take into account the main advantages of these sensors. Such software should be able to handle large volume of digital data, to distribute the computation over multiple computers and to produce automatically accurate end-products. If these constraints can be met, it is then possible to produce cartographic products instantly over large areas: digital data is uploaded in a PIXEL FACTORY and accurate end-products are automatically produced by this factory. Within the paper, a description of such a framework will be presented and compared to classical photogrammetric systems.