Abstract
The capability to adapt a manufacturing plant to changing requirements gains increasing importance in industrial production environments, e. g., triggered by Industrie 4.0 scenarios. A virtual as-built model of a manufacturing plant and its surrounding factory building provides important decision support and relevant information for digital twins, e. g., to trace assets and asset types across their whole lifetime, planning of renovations, plant and machine topology changes, or the simulation-based analysis of production processes. Based on point clouds obtained by terrestrial laser scanning or photogrammetric acquisition, reverse engineering can be applied to extract and to reconstruct relevant objects in a form suitable for CAD programs. In this article, we review approaches to capture a scene by point measurements and to reconstruct the geometry of its components given specific object models. This comprises the discussion of various representation schemes for objects and their relations, strategies for object recognition, and the explication of methods for model instantiation. Furthermore, depending on the requirements for specific tasks, we identify technology gaps and specify the degree of maturity of the related techniques.
Zusammenfassung
Die Fähigkeit, Produktionsanlagen an sich ändernde Umgebungen anzupassen, gewinnt im Kontext „Industrie 4.0“ zunehmend an Bedeutung. Ein virtuelles Bestandsmodell einer Produktionsanlage und des umgebenden Fabrikgebäudes stellt eine wichtige Grundlage dar, z. B. für die verbesserte Verfolgung von Produkten und Ressourcen (assets) über ihre komplette Lebenszeit, die Informationsgewinnung für Digitale Zwillinge, die Planung und Änderungen von Fertigungsanlagen und Maschinen sowie die simulationsgestützte Analyse von Produktionsprozessen. Basierend auf Punktwolken, die durch terrestrisches Laserscanning oder photogrammetrische Erfassungen erstellt wurden, kann ein Reverse Engineering durchgeführt werden, um relevante Objekte zu extrahieren, zu rekonstruieren und in geeigneter Form für CAD-Programme zu repräsentieren. In diesem Aufsatz werden Ansätze betrachtet, mit denen eine Szene durch Punktmessungen erfasst werden kann, und mit denen die Geometrie der Komponenten rekonstruiert werden kann. Daran schließt sich eine Diskussion verschiedener Repräsentationsschemata für Objekte und ihrer Relationen, Strategien zur Objekterkennung sowie die Erläuterung von Methoden zur Modellinstanziierung an. Abhängig von den aufgabenspezifischen Randbedingungen werden Technologielücken identifiziert und der Reifegrad der entsprechenden Technologien spezifiziert.
About the authors
Jochen Meidow is research associate at Fraunhofer IOSB, Ettlingen, since 2004. His main interests are statistics, solid modelling, and geometric reasoning. He holds a teaching position at the Karlsruhe Institute of Technology (KIT).
Thomas Usländer is head of the department “Information Management and Production Control” at Fraunhofer IOSB, Karlsruhe. His research, publications and standardization contributions include service-oriented analysis and design, reference models, and open geospatial service architectures.
Karsten Schulz is head of the department “Scene Analysis” at Fraunhofer IOSB, Ettlingen. His area of expertise comprises SAR image analysis, SAR interferometry, and remote sensing.
References
1. Jürgen Beyerer and Thomas Usländer (Eds.): Special Issue: Industrial Internet of Things supporting Factory Automation, at – Automatisierungstechnik 64 (2016).10.1515/auto-2016-0104Search in Google Scholar
2. DIN SPEC 91345:2016-04 Reference Architecture Model for Industrie 4.0, https://www.beuth.de/en/technical-rule/din-spec-91345-en/250940128.Search in Google Scholar
3. M. Fischler and R. Bolles: Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Communications of the ACM 24 (1981), 381–395.10.1145/358669.358692Search in Google Scholar
4. J.F. Hullo and G. Thibaut: Scaling up close-range surveys, a challenge for the generalization of as-built data in industrial applications, in: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-5, pp. 293–299, 2014.10.5194/isprsarchives-XL-5-293-2014Search in Google Scholar
5. Boris Jutzi, Martin Weinmann and Jochen Meidow: Weighted data fusion for UAV-borne 3D mapping with camera and line laser scanner, International Journal of Image and Data Fusion 5 (2014), 226–243.10.1080/19479832.2014.889228Search in Google Scholar
6. Kazuaki Kawashima, Satoshi Kanai and Hiroaki Date: As-built modeling of piping system from terrestrial laser-scanned point clouds using normal-based region growing, Journal of Computational Design and Engineering 1 (2014), 13–26.10.7315/JCDE.2014.002Search in Google Scholar
7. Jan Knopp et al.: Hough Transform and 3D SURF for Robust Three Dimensional Classification, in: Proceedings of the 11th European Conference on Computer Vision: Part VI, pp. 589–602, 2010.10.1007/978-3-642-15567-3_43Search in Google Scholar
8. Martti Mäntylä: An Introduction to Solid Modeling, Computer Science Press, Inc., New York, 1987. ISBN: 0-88175-108-1.Search in Google Scholar
9. Jochen Meidow: Geometric Reasoning for Uncertain Observations of Man-Made Structures, in: Pattern Recognition (Xiaoyi Jiang, Joachim Hornegger and Reinhard Koch, eds.), Lecture Notes in Computer Science 8753, pp. 558–568, Springer, 2014.10.1007/978-3-319-11752-2_46Search in Google Scholar
10. Jochen Meidow et al.: Enhancement of generic building models by recognition and enforcement of geometric constraints, in: ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, III-3, International Society for Photogrammetry and Remote Sensing, pp. 333–338, Prague, Czech Republic, 2016.10.5194/isprsannals-III-3-333-2016Search in Google Scholar
11. Viorica Patraucean et al.: State of Research in Automatic As-Built Modelling, in: Proceedings of the 32nd International Symposium on Automation and Robotics in Construction (ISARC 2015), pp. 1–7, 2015.10.22260/ISARC2015/0024Search in Google Scholar
12. T. Rabbani and F. Heuvel: 3D Industrial Reconstruction by Fitting CSG Models to a combination of Images and Point Clouds, in: International Archives of Photogrammetry and Remote Sensing, XXXV, B5, pp. 7–12, 2004.Search in Google Scholar
13. Szymon Rusinkiewicz and Marc Levoy: Efficient Variants of the ICP Algorithm, in: Proceedings of the Third Intl. Conf. on 3D Digital Imaging and Modeling, pp. 145–152, 2001.10.1109/IM.2001.924423Search in Google Scholar
14. Ruwen Schnabel, Roland Wahl and Reinhard Klein: Efficient RANSAC for Point-Cloud Shape Detection, Computer Graphics Forum 26 (2007), 214–226.10.1111/j.1467-8659.2007.01016.xSearch in Google Scholar
15. Pingbo Tang et al.: Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniques, Automation in Construction 19 (2010), 829–843.10.1016/j.autcon.2010.06.007Search in Google Scholar
© 2018 Walter de Gruyter GmbH, Berlin/Boston
