Descripteur
Termes IGN > sciences naturelles > physique > traitement d'image > analyse d'image numérique > extraction de traits caractéristiques
extraction de traits caractéristiquesSynonyme(s)extraction des caractéristiques extraction de primitiveVoir aussi |
Documents disponibles dans cette catégorie (653)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Automatic reconstruction of industrial installations using point clouds and images / Tahir Rabbani Shah (2006)
Titre : Automatic reconstruction of industrial installations using point clouds and images Type de document : Thèse/HDR Auteurs : Tahir Rabbani Shah, Auteur Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2006 Collection : Netherlands Geodetic Commission Publications on Geodesy, ISSN 0165-1706 num. 62 Importance : 160 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-90-6132-297-9 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie terrestre
[Termes IGN] appariement de formes
[Termes IGN] bâtiment industriel
[Termes IGN] conception assistée par ordinateur
[Termes IGN] détection d'objet
[Termes IGN] détection de contours
[Termes IGN] données localisées 3D
[Termes IGN] lissage de données
[Termes IGN] métrologie industrielle
[Termes IGN] modélisation 3D
[Termes IGN] photogrammétrie terrestre
[Termes IGN] reconstruction 3D
[Termes IGN] segmentation
[Termes IGN] segmentation d'image
[Termes IGN] semis de points
[Termes IGN] transformation de HoughIndex. décimale : 33.70 Photogrammétrie terrestre Résumé : (Auteur) Up to date and accurate 3D models of industrial sites are required for different applications like planning, documentation and training. Traditional methods for acquiring as-built information like manual measurements by tape and tacheometry are not only slow and cumbersome but most of the time they also fail to provide the amount of detail required. Many industrial facilities provide a limited personnel access because of the presence of radioactive, toxic or hazardous materials together with an unsafe working environment, which necessitates the use of non-contact measurement methods.
Traditional photogrammetry depends on point or line measurements from which it is very hard to get complete CAD models without extensive manual editing and refinement. Compared to photogrammetry laser scanning provides explicit and dense 3D measurements. There has been a rapid increase in the speed and accuracy of the laser scanners in the last decade, while their costs and sizes have been continuously shrinking. All modeling tools available on the market depend on heavy operator intervention for most of the modeling tasks. Although there are some semi-automatic tools like plane or cylinder growing even there the operator has to start the growing process for each primitive. Furthermore, the fitted surfaces must be manually edited by the operator to convert them to a CAD description.
This thesis presents new methods and techniques which can be used for automatic or efficient semiautomatic 3D modeling of existing industrial installations from point clouds and images. The goal is to use explicit 3D information from the point clouds to automatically detect the objects and structure present in the scene. The detected objects are then used as targets for model based registration, which can be automated by searching for object correspondences. To avoid manual editing the presented techniques use models from a catalogue of commonly found CAD objects as templates for model fitting. In the final fitting phase images are also included to improve the quality of parameter estimation.
Segmentation is a very important step that needs to be carried out as a pre cursor to object recognition and model fitting. We present a method for the segmentation of the point clouds, which avoids over-segmentation while partitioning the input data into mutually disjoint, smoothly connected regions. It uses a criterion based on a combination of surface normal similarity and spatial connectivity, which we call smoothness constraint. As we do not use surface curvature our algorithm is less sensitive to noise. Moreover, there are only a few parameters which can be adjusted to get a desired trade-off between under- and over-segmentation.
Segmentation is followed by a stage of object recognition based on a variation of the Hough transform for automatic plane and cylinder detection in the point clouds. For plane detection the Hough transform is three dimensional. For the cylinder detection the direct application of the Hough transform requires a 5D Hough space, which is quite impractical because of its space and computational complexity. To resolve this problem we present a two-step approach requiring a 2D and 3D Hough space. In the first step we detect strong hypotheses for the cylinder orientation. The second step estimates the remaining three parameters of the cylinder i.e. radius and position.
The problem of fitting models like planes, cylinders, spheres, cones, tori and CSG models to point clouds is very important for data reduction. For the fitting of CSG models, this thesis presents three different methods for approximating the orthogonal distance, which are compared based on speed and accuracy.
We also present methods for using modeled objects in individual scans as targets for registration. As the available geometrie structure is used, there is no need to place artificial targets. We present two different methods for this purpose called Indirect and Direct method. The Indirect method is a quick way to get approximate values while the Direct method is then used to refine the approximate solution. We also present techniques for automatically finding the corresponding objects for registration of scans. The presented techniques are based on constraint propagation which use the geometric information available from the previously made correspondence decision to filter out the possibilites for future correspondences.
Although point clouds are very important for the automation because of their explicit 3D information, images provide a complementary source of information as they contain well-defined edges of the bounded objects. We present methods for the fitting of CSG models to a combination of point clouds and images. We also present techniques for the specification of geometric constraints between sub-parts of a CSG tree and their inclusion in the model estimation process. A taxonomy of commonly encountered geometric constraints and their mathematical formulation is also given.
We hope that the techniques presented in this thesis will lead to an improvement in efficiency and quality of the models obtained for industrial installations from point clouds and images.Note de contenu : 1 Introduction
1.1 Literature survey
1.2 Objectives and modeling pipeline
1.3 Outline of the thesis
2 Segmentation using smoothness constraint
2.1 Introduction
2.2 Segmentation algorithm
2.3 Results
2.4 Conclusions
3 Object recognition
3.1 Introduction
3.2 Plane detection
3.3 Cylinder detection
3.4 Ambiguity resolution by hypothesis testing
3.5 Results
3.6 Conclusions
4 Model fitting to point clouds
4.1 Introduction
4.2 Problem definition
4.3 Fitting of simple géométrie objects
4.4 CSG Fitting
4.5 Results
4.6 Conclusions
5 Model-based registration
5.1 Introduction
5.2 Notation.
5.3 Indirect Method.
5.4 Direct Method
5.5 Results and discussion
5.6 Conclusions.
6 Automatic correspondence search
6.1 Introduction
6.2 Algorithm outline
6.3 Constrained Search for Correspondences
6.4 Comparison
6.5 Results
6.6 Conclusions
7 Constrained CSG fitting
7.1 Introduction
7.2 Model Fitting
7.3 Types of constraints
7.4 Examples of constraints
7.5 Fitting Experiments
7.6 Results .
7.7 Conclusions
8 Conclusions
8.1 Achievements
8.2 Directions for future workNuméro de notice : 15184 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère En ligne : https://www.ncgeo.nl/index.php/en/publicatiesgb/publications-on-geodesy/item/251 [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=55091 Réservation
Réserver ce documentExemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 15184-01 33.70 Livre Centre de documentation Photogrammétrie - Lasergrammétrie Disponible 15184-02 33.70 Livre Centre de documentation Photogrammétrie - Lasergrammétrie Disponible Extraction of tidal channel networks from aerial photographs alone and combined with laser altimetry / Bharat Lohani in International Journal of Remote Sensing IJRS, vol 27 n°1-2 (January 2006)
[article]
Titre : Extraction of tidal channel networks from aerial photographs alone and combined with laser altimetry Type de document : Article/Communication Auteurs : Bharat Lohani, Auteur ; D.C. Mason, Auteur ; T.R. Scott, Auteur ; B. Sreenivas, Auteur Année de publication : 2006 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] détection de contours
[Termes IGN] données lidar
[Termes IGN] fusion d'images
[Termes IGN] fusion de données
[Termes IGN] identification automatique
[Termes IGN] image multibande
[Termes IGN] marais salé
[Termes IGN] océanographie dynamique
[Termes IGN] sédimentationRésumé : (Auteur) Tidal channel networks play an important role in the intertidal zone, exerting substantial control over the hydrodynamics and sediment transport of the region and hence over the evolution of the salt marshes and tidal flats. The study of the morphodynamics of tidal channels is currently an active area of research, and a number of theories have been proposed which require for their validation measurement of channels over extensive areas. Remotely sensed data provide a suitable means for such channel mapping. The paper describes a technique that may be adapted to extract tidal channels from either aerial photographs or LiDAR data separately, or from both types of data used together in a fusion approach. Application of the technique to channel extraction from LiDAR data has been described previously. However, aerial photographs of intertidal zones are much more commonly available than LiDAR data, and most LiDAR flights now involve acquisition of multispectral images to complement the LiDAR data. In view of this, the paper investigates the use of multispectral data for semiautomatic identification of tidal channels, firstly from only aerial photographs or linescanner data, and secondly from fused linescanner and LiDAR data sets. A multi-level, knowledge-based approach is employed. The algorithm based on aerial photography can achieve a useful channel extraction, though may fail to detect some of the smaller channels, partly because the spectral response of parts of the non-channel areas may be similar to that of the channels. The algorithm for channel extraction from fused LiDAR and spectral data gives an increased accuracy, though only slightly higher than that obtained using LiDAR data alone. The results illustrate the difficulty of developing a fully automated method, and justify the semi-automatic approach adopted. Numéro de notice : A2006-058 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160500206692 En ligne : https://doi.org/10.1080/01431160500206692 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27785
in International Journal of Remote Sensing IJRS > vol 27 n°1-2 (January 2006)[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 080-06011 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : Geo-information and computational geometry Type de document : Monographie Auteurs : Peter J. M. Van Oosterom, Éditeur scientifique ; M.J. Van Kreveld, Éditeur scientifique Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2006 Collection : Netherlands Geodetic Commission Green series num. 44 Importance : 51 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-90-6132-299-3 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] analyse spatiale
[Termes IGN] détection du bâti
[Termes IGN] données lidar
[Termes IGN] données localisées
[Termes IGN] données topographiques
[Termes IGN] géomètrie algorithmique
[Termes IGN] méthode de Monte-Carlo
[Termes IGN] reconstruction 3D du bâti
[Termes IGN] système d'information géographiqueRésumé : (Editeur) The contributions reflect the diversity of the possible interactions between computational geometry and GIS. The topics of the contributions range from overviews of relevant techniques and tools to solving specific spatial problems in either the object-based (vector) or field-based (raster) domain. This publication is a reflection of the different seminar contributions. The first paper 'Computational Geometry: its objectives and relation to GIS' is by Marc van Kreveld (Utrecht University). The analysis of algorithms involves understanding how efficiently an algorithm solves a problem. One of the main objectives of computational geometry is finding the most efficient algorithms for all sorts of geometric problems. He introduces the main concepts and ideas in computational geometry, including efficiency analysis, intractability, output-sensitive algorithms, and approximation algorithms. The basic problems of computational geometry all have a direct or indirect use to GIS. He also indicates why computational geometry is not as useful to GIS as it could be (complicated algorithms, focus on worst-case efficiency, and on well-defined, simple to state problems) and how this is currently improving (available software libraries, simpler algorithms provably efficient under realistic assumptions).
Mark de Berg (TU Eindhoven) addresses one of the issues to make computational geometry techniques more applicable in practice, namely the handling of large data sets that do not fit in main memory (as often more or less implicitly assumed in the description of many data structures and algorithms). In his paper 'I/O- and Cache-efficient Algorithms for Spatial Data', he explains how the hierarchical memory consisting of a disk, main memory, and several levels of cache should be included in data structure and algorithm design. The difference between the times to access these different levels of memory is quite large: the disk is typically about 100,000 times slower than accessing the main memory. In the paper some of the recent results that have been obtained on I/O- and cache-efficient algorithms are discussed with focus on spatial data.
One specific data structure, based on quad-edges, and applied to creating and editing three-dimensional models, is described by Christopher Gold and Rebecca Tse (University of Glamorgan, UK) in their paper 'Quad-Edges and Euler Operators for Automatic Building Extrusion Using LiDAR Data' (LIght Detection And Ranging). The long-term research objective for their models is to integrate man-made objects with the landscape, so that topological properties, such as connectedness, may be used in applications such as flood modeling. Man-made objects such as build-ings, as well as terrain elevation, should be extracted directly from LiDAR data. Their model is a triangle-based boundary description of the relevant objects and earth surface. The model creation and local modifications (updates) is performed on the Quad-Edge data structure by using Euler operators. These operators permit various extrusion operations as well as the manual insertion of bridges and tunnels.
A description of the use computational geometry tools used to solve a few specific cartographic problems is given by Bettina Speckmann (TU Eindhoven) in her paper 'Algorithms for cartograms and other specialized maps'. Cartograms are a useful and intuitive tool to visualize statistical data about a set of regions like countries, states or counties. The size of a region in a cartogram corresponds to a particular geographic variable and therefore the regions generally cannot keep both their shape and their adjacencies. A good cartogram, however, preserves the recognizability in some way. The paper gives a short overview of cartogram algorithms, and focuses in particular on the computation of rectangular cartograms. In a rectangular cartogram each region is represented by a rectangle. An implementation and various tests show that in practice, visually pleasing rectangular cartograms with small cartographic error can be generated effectively. Furthermore, the computation of proportional symbol maps is also discussed briefly.
Three-dimensional topographic modeling is also the topic of the paper by Friso Penninga (TU Delft): 'Constrained tetrahedral models and update algorithms for topographic data'. In contrast to the work of Gold and Tse he does not do this by representing the bounding surfaces, but he represents the three-dimensional objects by sets of tetrahedrons. The whole model then becomes a tetrahedronized irregular network (TEN), the 3D version of the more generally known triangulated irregular network (TIN). The TEN is a well-defined and robust data structure which enables complex processing by separate processing on each primitive first and afterwards joining all these partial results into a final result. In order to represent their borders several edges and faces will be handled as constraints. Updating a topographic dataset therefore equals the addition and removal of constraints within the network. One of the biggest challenges in the realization of such a data structure and corresponding algorithms is to reach acceptable performance, despite the potentially enormous amount of data. The last paper 'Towards improved solution schemes for Monte Carlo simulation in environmental modeling languages' is by Derek Karssenberg and Kor de Jong (Utrecht University). They deal with the field-based representation of spatial data, in contrast to the object-based representation of spatial data in the other papers. On the most often used field-based data structure, the regular grid, the algorithmic challenges are quite different than their counterparts in the object-based approaches. Environmental modeling languages such as PCRaster are programming languages embedded in GIS to simulate environmental processes. These languages are used to construct dynamic models, also called forward models, which are simulations run forward in time, where the state of the model at time t is defined as a function of its state in a time step preceding t. For future applications, at least two extensions to the languages are required: support of three spatial dimensions (as the real world is often 3D), and inclusion of Monte Carlo simulation techniques (to calculate how input errors propagate to the output of a model).Note de contenu : Editorial - Peter van Oosterom and Marc van Kreveld
- Computational Geometry: Ils objectives and relation to GIS - Marc van Kreveld
- I/O- and Cache-Efficient Algorithms for Spatial Data - Mark de Berg
- Quad-Edges and Euler Operators for Automatic Building Extrusion Using LIDAR Data - Christopher
Gold and Rebecca Tse
- Algorithms for cartograms and other specialized maps - Bettina Speckmann
- Constrained tetrahedral models and update algorithms for topographie data - Friso Penninga
- Towards improved solution schemes for Monte Carlo simulation in environmental modeling languages - Derek Karssenberg and Kor de JongNuméro de notice : 15213 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Recueil / ouvrage collectif En ligne : https://www.ncgeo.nl/index.php/en/publicatiesgb/green-series/item/2363-gs-44-pet [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=55100 Réservation
Réserver ce documentExemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 15213-02 37.20 Livre Centre de documentation Géomatique Disponible 15213-01 37.20 Livre Centre de documentation Géomatique Disponible Documents numériques
en open access
Geo-information and computational geometry - pdf éditeurAdobe Acrobat PDF Improving building footprints in InSAR data comparison with a Lidar DSM / Paolo Gamba in Photogrammetric Engineering & Remote Sensing, PERS, vol 72 n° 1 (January 2006)
[article]
Titre : Improving building footprints in InSAR data comparison with a Lidar DSM Type de document : Article/Communication Auteurs : Paolo Gamba, Auteur ; F. Dell'acqua, Auteur ; G. Lisini, Auteur ; F. Cisotta, Auteur Année de publication : 2006 Article en page(s) : pp 63 - 70 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] correction géométrique
[Termes IGN] détection du bâti
[Termes IGN] données lidar
[Termes IGN] étalement d'histogramme
[Termes IGN] image 3D
[Termes IGN] image radar moirée
[Termes IGN] milieu urbain
[Termes IGN] modèle numérique de surfaceRésumé : (Auteur) The first aim of this paper is to show how the joint use of Digital Surface Models (Dsms) coming from different sources may improve the understanding of an urban environment. More specifically, we consider laser and radar three-dimensional data over the same urban area and show that they can be profitably combined to improve building extraction. We exploit the better vertical and horizontal accuracy of the laser DSM, assumed to be available only for a small area, to ease the deformation of Interferometric Synthetic Aperture Radar (INSAR) DSM with built structures. To achieve this, we propose a method based on subsequent steps of geometrical correction, and mainly on a simple "stretching step" that uses laser data as a reference to adjust INSAR-derived building footprints. We show quantitative results obtained from two different urban areas, using different laser and radar data sets, to assess advantages and drawbacks of the proposed method. Numéro de notice : A2006-002 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.72.1.63 En ligne : https://doi.org/10.14358/PERS.72.1.63 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27730
in Photogrammetric Engineering & Remote Sensing, PERS > vol 72 n° 1 (January 2006) . - pp 63 - 70[article]On the optimization and selection of wavelet texture for feature extraction from high-resolution satellite imagery with application towards urban-tree delineation / Y.O. Ouma in International Journal of Remote Sensing IJRS, vol 27 n°1-2 (January 2006)
[article]
Titre : On the optimization and selection of wavelet texture for feature extraction from high-resolution satellite imagery with application towards urban-tree delineation Type de document : Article/Communication Auteurs : Y.O. Ouma, Auteur ; T.G. Ngigi, Auteur ; et al., Auteur Année de publication : 2006 Article en page(s) : pp 73 - 104 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse texturale
[Termes IGN] arbre urbain
[Termes IGN] données multiéchelles
[Termes IGN] extraction automatique
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image à très haute résolution
[Termes IGN] image multibande
[Termes IGN] image Quickbird
[Termes IGN] optimisation (mathématiques)
[Termes IGN] texture d'image
[Termes IGN] transformation en ondelettesRésumé : (Auteur) Integration of spectral and multi-scale texture is proposed in order to improve the detection and classification of urban-trees from Quickbird imagery. Arguing that spatial -structure semantic information exits at a hierarchy of scales and that texture is a consequence of objects in the hierarchy, multi-scale wavelets decomposition is proposed for the extraction of vertical, horizontal and diagonal texture components. Pre-selection of texture sub-bands is achieved via mean, entropy, variance and second angular moment. The resulting sub-bands are analysed for separability between trees and similarly reflecting features, such as rice-paddy, grass/lawns, open ground and playground, based on KuIlbackLeibler (KL) divergence and Battacharyya distance. The results are ranked and classified with k-means. In comparison with the field data, KL gave the best results with omission and commission error of 4.4%. The proposed methodology has the ability to capture the increased natural variability in reflectance and improved the accuracy by 23.6%, in comparison with spectral-only. Numéro de notice : A2006-059 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160500295885 En ligne : https://doi.org/10.1080/01431160500295885 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27786
in International Journal of Remote Sensing IJRS > vol 27 n°1-2 (January 2006) . - pp 73 - 104[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 080-06011 RAB Revue Centre de documentation En réserve L003 Disponible PermalinkUtilisation conjointe de données image et laser pour la segmentation et la modélisation 3D / Matthieu Deveau (2006)PermalinkThe recognition of road network from high-resolution satellite remotely sensed data using image morphological characteristics / C. Zhu in International Journal of Remote Sensing IJRS, vol 26 n° 24 (December 2005)PermalinkExtraction semi-automatique de bâtiments par contours actifs surfaciques : adaptation au contexte Pléiades / P. Cornic in Revue Française de Photogrammétrie et de Télédétection, n° 180 (Décembre 2005)PermalinkMapping impervious surface type and sub-pixel abundance using Hyperion hyperspectral imagery / J. Falcone in Geocarto international, vol 20 n° 4 (December 2005 - February 2006)PermalinkRectangular building extraction from stereoscopic airborne Radar images / Elisabeth Simonetto in IEEE Transactions on geoscience and remote sensing, vol 43 n° 10 (October 2005)PermalinkAutomatic change detection and updating of topographic databases by using satellite imagery : a level set approach / M.S. Allili in Geomatica, vol 59 n° 3 (September 2005)PermalinkSPOT 5 pour la détection d'urbanisation / V. Lacroix in Revue Française de Photogrammétrie et de Télédétection, n° 178 (Septembre 2005)PermalinkDEM generation and building detection from Lidar data / R. Ma in Photogrammetric Engineering & Remote Sensing, PERS, vol 71 n° 7 (July 2005)PermalinkThe use of remote sensing techniques and empirical tectonic models for inference of geological structures: bridging from regional to local scales / P.C. Fernandes Da Silva in Remote sensing of environment, vol 96 n° 1 (15/05/2005)Permalink