Brazilian Symposium on Computer Graphics and Image Processing, 1999
Summary form only given, as follows. In this paper, we discuss methods for the detection and reco... more Summary form only given, as follows. In this paper, we discuss methods for the detection and reconstruction of buildings from aerial imagery. These methods have been intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated,
We present a method for 3D surface segmentation based on watershed cuts computed on local curvatu... more We present a method for 3D surface segmentation based on watershed cuts computed on local curvatures. The segmentation algorithm is applied to artwork database classification by mean of a search engine based on 3D region descriptor bags. The comparison with a search engine based on global descriptors clearly shows an improvement of performances.
In this paper, we develop a simple Digital Elevation Models processing scheme that focuses on the... more In this paper, we develop a simple Digital Elevation Models processing scheme that focuses on the improvement of urban high resolution DEM basic properties such as density, reliability, accuracy, capacity to render 3-D landscape shapes and breaks to improve 3D-building models production but also urban orthophoto production.
We propose in this paper an original scheme to detect and localise buildings from a stereo-pair o... more We propose in this paper an original scheme to detect and localise buildings from a stereo-pair of high resolution aerial images. Our strategy is based on a close co-operation between 2D and 3D information. A multi-resolution and adaptive template matching technique provides dense, reliable a nd d epth discontinuity preserving DEM. DEM segmentation and raised structure e xtraction based o
We present a method for 3D surface segmentation based on watershed cuts computed on local curvatu... more We present a method for 3D surface segmentation based on watershed cuts computed on local curvatures. The segmentation algorithm is applied to artwork database classification by mean of a search engine based on 3D region descriptor bags. The comparison with a search engine based on global descriptors clearly shows an improvement of performances.
Digital Elevation Models (DEMs) are a central information source for scene analysis, including sp... more Digital Elevation Models (DEMs) are a central information source for scene analysis, including specific tasks such as building localization and reconstruction. Whatever application is envisaged, DEM segmentation is a critical step, due to the great variability of landscapes and above-ground structures in urban areas. Moreover, a DEM may contain erroneous isolated 3D points which have to be identified before any interpretation process can start. Designing an automatic DEM segmentation method that is successful under all circumstances can hardly be envisaged. To facilitate the segmentation process, a user-friendly, interactive software environment, called ReconLab, has been developed. Its 3D viewing and editing capabilities allow to easily detect and remove erroneous 3D points from the initial data, to efficiently smooth the DEM and perform the segmentation in real time. ReconLab's usefulness for urban scene interpretation is demonstrated by applying it to the estimation of a Digital Terrain Model (DTM) from the DEM. In particular, Recon-Lab is used to perform a fast, semi-automatic segmentation of the DEM and to provide a significant and representative sample region consisting of ground points. These points are then used to initialize a parametric model for the terrain, which is iteratively refined by a robust algorithm. The preprocessing by ReconLab reduces computation time by a factor 3, without loss of accuracy, as is demonstrated by experiments on synthetic data and on real world DEMs obtained by airborne laser altimetry as well as by stereo correspondence from imagery.
In this paper, we present first results obtained in the frame of the EROS-3D project, which aims ... more In this paper, we present first results obtained in the frame of the EROS-3D project, which aims at dealing with a collection of artwork 3D models, i.e. visualize them, classify them and compare them. Some 3D descriptors are used, in association with our active learning search engine RETIN. 3D features are described as well as our new system of classification and retrieval of objects, which we called RETIN-3D.
ABSTRACT In this paper, a strategy is presented to automatically generate 3D building models in u... more ABSTRACT In this paper, a strategy is presented to automatically generate 3D building models in urban sites from high resolution (8cm per pixel) aerial stereopairs. The entire system is based on a close cooperation between 2D and 3D processings. We have ...
We present a search engine dedicated to 3D object databases. The originality of the method is to ... more We present a search engine dedicated to 3D object databases. The originality of the method is to represent models by adjacency graphs of surfacic regions. After segmentation of the 3D surface of a model, regions are described by various shape descriptors. The similarity between graphs is computed by kernels on graphs computed from kernels on walks. These kernel functions take into account both the similarity between regions and their spatial relationship. The search engine performs interactive research in a database from a query object, by using semi-supervised classification. The system is applied to a database of 3D high resolution artwork models. We show that a graph representation outperforms a global description of the objects, when using the same descriptors.
This demonstration presents a digital media retrieval system for searching large categories in di... more This demonstration presents a digital media retrieval system for searching large categories in different media databases. The core of our system is an interactive online classification based on user labeling. The classification is obtained with a statistical learning method: kernels for similarity representation and SVM (Support Vector Machine) using binary user annotations. RETIN applies also an active learning strategy for proposing documents to the user for labeling. The system can deal with images, 3D objects and videos and other media can be added to. A graphical user interface allows easy browsing of different media, simple and user-friendly interaction and fast retrieval.
Brazilian Symposium on Computer Graphics and Image Processing, 2002
Nowadays several areas of application need a precise 3D cartographic model, specially in the urba... more Nowadays several areas of application need a precise 3D cartographic model, specially in the urban domain: telecommunications, urbanism, tourism and other ludicrous applications. The analysis of aerial stereoscopic photos provides a fast method to obtain a faithful relief of the observed scene, including its superstructures. This work presents the Navegador3D developed by NPD/UFMG, ETIS/ENSEA and Vist@erea/INFOSTRATA.
ABSTRACT This paper describes an algorithm which aims at deriving digital terrain models (DTM) fr... more ABSTRACT This paper describes an algorithm which aims at deriving digital terrain models (DTM) from dense digital elevation models (DEM). This algorithm takes place in a processing chain for building detection and modelling in urban areas from high resolution ...
This article describes the first system-wide evaluation of the Child Health Network (CHN) for the... more This article describes the first system-wide evaluation of the Child Health Network (CHN) for the Greater Toronto Area (GTA), a partnership of 29 community and hospital care providers. The CHN performance evaluation sought to identify the impact of the network on the delivery of maternal, newborn and child health services in the GTA. CHN members identified seven criteria to be evaluated (appropriate care, accessibility, effectiveness, satisfaction, integrated and coordinated care, accountability and affordability) and then collaborated in selecting measurable indicators for each criterion. Data were compiled from administrative data sets, or collected as needed. This undertaking succeeded in providing a comprehensive assessment of the network's performance, identification of strategies to improve outcomes and network sustainability, as well as practical information that will inform the important new field of network evaluation.
Three-dimensional (3-D) representation of natural scenes is a major problem of computer vision. I... more Three-dimensional (3-D) representation of natural scenes is a major problem of computer vision. In this paper, we present a method for re-building scenes from aerial photographs. The complete method involves the geometric modelling of taking of views, the automatic matching of images and the scene description as a set of vertical, oblique or horizontal planes. This method was tested on images of urban and industrial zones. The precision that we obtained allows us to introduce such a 3-D representation in a complex set of routines for the analysis of aerial photographs.
Brazilian Symposium on Computer Graphics and Image Processing, 1999
Summary form only given, as follows. In this paper, we discuss methods for the detection and reco... more Summary form only given, as follows. In this paper, we discuss methods for the detection and reconstruction of buildings from aerial imagery. These methods have been intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated,
In this paper, we discuss methods for building detection and reconstruction from aerial imagery. ... more In this paper, we discuss methods for building detection and reconstruction from aerial imagery. These methods are intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated, including hierarchical processing and new correlation schemes that have interesting properties for building recognition and building feature grouping. Cooperative combination of 2-D (monocular) and 3-D (stereoscopic) information allows the complete representation of the observed scene and particularly the detection of man-made raised structures such as buildings. A performance evaluation on simulation-based images has been considered in comparison with the corresponding ground truth reference. Our work illustrates that mid-resolution methods cannot be directly applied to high-resolution images. Classical algorithms must be adapted and new techniques have been defined to carry out dense urban area reconstruction.
Brazilian Symposium on Computer Graphics and Image Processing, 1999
Summary form only given, as follows. In this paper, we discuss methods for the detection and reco... more Summary form only given, as follows. In this paper, we discuss methods for the detection and reconstruction of buildings from aerial imagery. These methods have been intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated,
We present a method for 3D surface segmentation based on watershed cuts computed on local curvatu... more We present a method for 3D surface segmentation based on watershed cuts computed on local curvatures. The segmentation algorithm is applied to artwork database classification by mean of a search engine based on 3D region descriptor bags. The comparison with a search engine based on global descriptors clearly shows an improvement of performances.
In this paper, we develop a simple Digital Elevation Models processing scheme that focuses on the... more In this paper, we develop a simple Digital Elevation Models processing scheme that focuses on the improvement of urban high resolution DEM basic properties such as density, reliability, accuracy, capacity to render 3-D landscape shapes and breaks to improve 3D-building models production but also urban orthophoto production.
We propose in this paper an original scheme to detect and localise buildings from a stereo-pair o... more We propose in this paper an original scheme to detect and localise buildings from a stereo-pair of high resolution aerial images. Our strategy is based on a close co-operation between 2D and 3D information. A multi-resolution and adaptive template matching technique provides dense, reliable a nd d epth discontinuity preserving DEM. DEM segmentation and raised structure e xtraction based o
We present a method for 3D surface segmentation based on watershed cuts computed on local curvatu... more We present a method for 3D surface segmentation based on watershed cuts computed on local curvatures. The segmentation algorithm is applied to artwork database classification by mean of a search engine based on 3D region descriptor bags. The comparison with a search engine based on global descriptors clearly shows an improvement of performances.
Digital Elevation Models (DEMs) are a central information source for scene analysis, including sp... more Digital Elevation Models (DEMs) are a central information source for scene analysis, including specific tasks such as building localization and reconstruction. Whatever application is envisaged, DEM segmentation is a critical step, due to the great variability of landscapes and above-ground structures in urban areas. Moreover, a DEM may contain erroneous isolated 3D points which have to be identified before any interpretation process can start. Designing an automatic DEM segmentation method that is successful under all circumstances can hardly be envisaged. To facilitate the segmentation process, a user-friendly, interactive software environment, called ReconLab, has been developed. Its 3D viewing and editing capabilities allow to easily detect and remove erroneous 3D points from the initial data, to efficiently smooth the DEM and perform the segmentation in real time. ReconLab's usefulness for urban scene interpretation is demonstrated by applying it to the estimation of a Digital Terrain Model (DTM) from the DEM. In particular, Recon-Lab is used to perform a fast, semi-automatic segmentation of the DEM and to provide a significant and representative sample region consisting of ground points. These points are then used to initialize a parametric model for the terrain, which is iteratively refined by a robust algorithm. The preprocessing by ReconLab reduces computation time by a factor 3, without loss of accuracy, as is demonstrated by experiments on synthetic data and on real world DEMs obtained by airborne laser altimetry as well as by stereo correspondence from imagery.
In this paper, we present first results obtained in the frame of the EROS-3D project, which aims ... more In this paper, we present first results obtained in the frame of the EROS-3D project, which aims at dealing with a collection of artwork 3D models, i.e. visualize them, classify them and compare them. Some 3D descriptors are used, in association with our active learning search engine RETIN. 3D features are described as well as our new system of classification and retrieval of objects, which we called RETIN-3D.
ABSTRACT In this paper, a strategy is presented to automatically generate 3D building models in u... more ABSTRACT In this paper, a strategy is presented to automatically generate 3D building models in urban sites from high resolution (8cm per pixel) aerial stereopairs. The entire system is based on a close cooperation between 2D and 3D processings. We have ...
We present a search engine dedicated to 3D object databases. The originality of the method is to ... more We present a search engine dedicated to 3D object databases. The originality of the method is to represent models by adjacency graphs of surfacic regions. After segmentation of the 3D surface of a model, regions are described by various shape descriptors. The similarity between graphs is computed by kernels on graphs computed from kernels on walks. These kernel functions take into account both the similarity between regions and their spatial relationship. The search engine performs interactive research in a database from a query object, by using semi-supervised classification. The system is applied to a database of 3D high resolution artwork models. We show that a graph representation outperforms a global description of the objects, when using the same descriptors.
This demonstration presents a digital media retrieval system for searching large categories in di... more This demonstration presents a digital media retrieval system for searching large categories in different media databases. The core of our system is an interactive online classification based on user labeling. The classification is obtained with a statistical learning method: kernels for similarity representation and SVM (Support Vector Machine) using binary user annotations. RETIN applies also an active learning strategy for proposing documents to the user for labeling. The system can deal with images, 3D objects and videos and other media can be added to. A graphical user interface allows easy browsing of different media, simple and user-friendly interaction and fast retrieval.
Brazilian Symposium on Computer Graphics and Image Processing, 2002
Nowadays several areas of application need a precise 3D cartographic model, specially in the urba... more Nowadays several areas of application need a precise 3D cartographic model, specially in the urban domain: telecommunications, urbanism, tourism and other ludicrous applications. The analysis of aerial stereoscopic photos provides a fast method to obtain a faithful relief of the observed scene, including its superstructures. This work presents the Navegador3D developed by NPD/UFMG, ETIS/ENSEA and Vist@erea/INFOSTRATA.
ABSTRACT This paper describes an algorithm which aims at deriving digital terrain models (DTM) fr... more ABSTRACT This paper describes an algorithm which aims at deriving digital terrain models (DTM) from dense digital elevation models (DEM). This algorithm takes place in a processing chain for building detection and modelling in urban areas from high resolution ...
This article describes the first system-wide evaluation of the Child Health Network (CHN) for the... more This article describes the first system-wide evaluation of the Child Health Network (CHN) for the Greater Toronto Area (GTA), a partnership of 29 community and hospital care providers. The CHN performance evaluation sought to identify the impact of the network on the delivery of maternal, newborn and child health services in the GTA. CHN members identified seven criteria to be evaluated (appropriate care, accessibility, effectiveness, satisfaction, integrated and coordinated care, accountability and affordability) and then collaborated in selecting measurable indicators for each criterion. Data were compiled from administrative data sets, or collected as needed. This undertaking succeeded in providing a comprehensive assessment of the network's performance, identification of strategies to improve outcomes and network sustainability, as well as practical information that will inform the important new field of network evaluation.
Three-dimensional (3-D) representation of natural scenes is a major problem of computer vision. I... more Three-dimensional (3-D) representation of natural scenes is a major problem of computer vision. In this paper, we present a method for re-building scenes from aerial photographs. The complete method involves the geometric modelling of taking of views, the automatic matching of images and the scene description as a set of vertical, oblique or horizontal planes. This method was tested on images of urban and industrial zones. The precision that we obtained allows us to introduce such a 3-D representation in a complex set of routines for the analysis of aerial photographs.
Brazilian Symposium on Computer Graphics and Image Processing, 1999
Summary form only given, as follows. In this paper, we discuss methods for the detection and reco... more Summary form only given, as follows. In this paper, we discuss methods for the detection and reconstruction of buildings from aerial imagery. These methods have been intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated,
In this paper, we discuss methods for building detection and reconstruction from aerial imagery. ... more In this paper, we discuss methods for building detection and reconstruction from aerial imagery. These methods are intended for the analysis of urban and suburban areas and have been applied to images of different resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated, including hierarchical processing and new correlation schemes that have interesting properties for building recognition and building feature grouping. Cooperative combination of 2-D (monocular) and 3-D (stereoscopic) information allows the complete representation of the observed scene and particularly the detection of man-made raised structures such as buildings. A performance evaluation on simulation-based images has been considered in comparison with the corresponding ground truth reference. Our work illustrates that mid-resolution methods cannot be directly applied to high-resolution images. Classical algorithms must be adapted and new techniques have been defined to carry out dense urban area reconstruction.
Uploads
Papers by michel jordan