Centre de documentation
scientifique

Automatic reconstruction of industrial installations using point clouds and images / Tahir Rabbani Shah (2006)  

Public 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 Hough Index. 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 work Numéro de notice : 15184 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère DOI : sans En ligne : https://www.ncgeo.nl/downloads/62Rabbani.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=55091

Exemplaires(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