Hostname: page-component-76d6cb85b7-kcxw8 Total loading time: 0 Render date: 2026-07-18T06:57:26.507Z Has data issue: false hasContentIssue false
  • English
  • Français

EUCLIDIAN DISTANCE TRANSFORMATION, MAIN AXIS ROTATION AND NOISY DILITATION SUPPORTED CROSS-SECTION CLASSIFICATION WITH CONVOLUTIONAL NEURAL NETWORKS

Published online by Cambridge University Press:  27 July 2021

Martin Denk ,
Klemens Rother ,
Tobias Höfer ,
Jan Mehlstäubl  and
Kristin Paetzold
Martin Denk*
Affiliation:
Bundeswehr University Munich;
Klemens Rother
Affiliation:
Munich University of Applied Sciences, Institute for Material and Building Research;
Tobias Höfer
Affiliation:
Munich University of Applied Sciences, Competence Center Image Processing (CCBV)
Jan Mehlstäubl
Affiliation:
Bundeswehr University Munich;
Kristin Paetzold
Affiliation:
Bundeswehr University Munich;
*
Denk, Martin, Bundeswehr University Munich, Insitute for Technical Product Development, Germany, martin.denk@unibw.de

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

Polygon meshes and particularly triangulated meshes can be used to describe the shape of different types of geometry such as bicycles, bridges, or runways. In engineering, such polygon meshes can be supplied as finite element meshes, resulting from topology optimization or from laser scanning. Especially from topology optimization, frame-like polygon meshes with slender parts are typical and often have to be converted into a CAD (Computer-Aided Design) format, e.g., for further geometrical detailing or performing additional shape optimization. Especially for such frame-like geometries, CAD designs are constructed as beams with cross-sections and beam-lines, whereby the cross-section is extruded along the beam-lines or beam skeleton. One major task in the recognition of beams is the classification of the cross-section type such as I, U, or T, which is addressed in this article. Therefore, a dataset consisting of different cross-sections represented as binary images is created. Noisy dilatation, the distance transformation, and main axis rotation are applied to these images to increase the robustness and reduce the necessary amount of samples. The resulting images are applied to a convolutional neuronal network.

Keywords

Artificial intelligenceMachine learningComputer Aided Design (CAD)Geometric Deep LearningCross-Sections

Information

Type
Article
Information
Proceedings of the Design Society , Volume 1: ICED21 , August 2021 , pp. 1401 - 1410
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2021. Published by Cambridge University Press

References

Agathos, A., Pratikakis, I., Perantonis, S., Sapidis, N., Azariadis, P., 2007. 3D Mesh Segmentation Methodologies for CAD applications. Comput.-Aided Des. Appl. 4, 827–841. https://doi.org/10.1080/16864360.2007.10738515CrossRefGoogle Scholar
Atabay, Agh, H., 2016. Binary shape classification using Convolutional Neural Networks. IIOAB J. 7, 332–336.Google Scholar
Ahmed, E., Saint, A., Shabayek, A.E.R., Cherenkova, K., Das, R., Gusev, G., Aouada, D., Ottersten, B., 2019. A survey on Deep Learning Advances on Different 3D Data Representations. ArXiv180801462 Cs.Google Scholar
Arcelli, C., Baja, G.S. di, Serino, L., 2011. Distance-Driven Skeletonization in Voxel Images. IEEE Trans. Pattern Anal. Mach. Intell. 33, 709–720. https://doi.org/10.1109/TPAMI.2010.140CrossRefGoogle ScholarPubMed
Bansal, M., Kumar, Munish, Kumar, Manish, 2020. 2D Object Recognition Techniques: State-of-the-Art Work. Arch. Comput. Methods Eng. https://doi.org/10.1007/s11831-020-09409-1CrossRefGoogle Scholar
Makhlouf, Ben, Louhichi, A., Mahjoub, B., Deneux, M.A., D., 2019. Reconstruction of a CAD model from the deformed mesh using B-spline surfaces. Int. J. Comput. Integr. Manuf. 32, 669–681. https://doi.org/10.1080/0951192X.2019.1599442CrossRefGoogle Scholar
Bénière, R., Subsol, G., Gesquière, G., Le Breton, F., Puech, W., 2013. A comprehensive process of reverse engineering from 3D meshes to CAD models. Comput.-Aided Des. 45, 1382–1393. https://doi.org/10.1016/j.cad.2013.06.004CrossRefGoogle Scholar
Bremicker, M., Chirehdast, M., Kikuchi, N., Papalambros, P.Y., 1991. Integrated Topology and Shape Optimization in Structural Design∗. Mech. Struct. Mach. 19, 551–587. https://doi.org/10.1080/08905459108905156CrossRefGoogle Scholar
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P., 2017. Geometric deep learning: going beyond Euclidean data. IEEE Signal Process. Mag. 34, 18–42. https://doi.org/10.1109/MSP.2017.2693418CrossRefGoogle Scholar
Cao, W., Yan, Z., He, Zhiquan, He, Zhihai, 2020. A Comprehensive Survey on Geometric Deep Learning. IEEE Access 8, 35929–35949. https://doi.org/10.1109/ACCESS.2020.2975067Google Scholar
Changizi, N., Warn, G.P., 2020. Topology optimization of structural systems based on a nonlinear beam finite element model. Struct. Multidiscip. Optim. https://doi.org/10.1007/s00158-020-02636-xCrossRefGoogle Scholar
Cuillière, J.-C., François, V., Nana, A., 2018. Automatic construction of structural CAD models from 3D topology optimization. Comput.-Aided Des. Appl. 15, 107–121. https://doi.org/10.1080/16864360.2017.1353726CrossRefGoogle Scholar
Denk, M., 2021. Cross-Section Dataset. URL https://github.com/Foxelmanian/CrossSectionClassificationGoogle Scholar
Denk, M., Paetzold, K., Rother, K., 2019. Feature line detection of noisy triangulated CSGbased objects using deep learning, in: Proceedings of the 30th Symposium Design for X (DFX 2019), DfX. Presented at the DfX Symposium 2019, The Design Society, Jesteburg, Germany, pp. 239–250. https://doi.org/10.35199/dfx2019.21CrossRefGoogle Scholar
Denk, M., Rother, K., Paetzold, K., 2020a. Fully Automated Subdivision Surface Parametrization for Topology Optimized Structures and Frame Structures using Euclidean Distance Transformation and Homotopic Thinning, in: Proceedings of the Munich Symposium on Lightweight Design 2020. Springer Nature, Munich, Germany. https://doi.org/10.1007/978-3-662-63143-0CrossRefGoogle Scholar
Denk, M., Rother, K., Paetzold, K., 2020b. Multi-Objective Topology Optimization of Heat Conduction and Linear Elastostatic using Weighted Global Criteria Method, in: Proceedings of the 31st Symposium Design for X (DFX2020), DFX. Presented at the DfX Symposium 2020, The Design Society, Bamberg, pp. 91–100. https://doi.org/10.35199/dfx2020.10CrossRefGoogle Scholar
Feng, C., Jalba, A.C., Telea, A.C., 2015. Part-Based Segmentation by Skeleton Cut Space Analysis, in: Benediktsson, J.A., Chanussot, J., Najman, L., Talbot, H. (Eds.), Mathematical Morphology and Its Applications to Signal and Image Processing, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 607–618. https://doi.org/10.1007/978-3-319-18720-4_51CrossRefGoogle Scholar
Gauthier, S., Puech, W., Bénière, R., Subsol, G., 2017. Analysis of digitized 3D mesh curvature histograms for reverse engineering. Comput. Ind. 92-93, 67–83. https://doi.org/10.1016/j.compind.2017.06.008CrossRefGoogle Scholar
Gomez-Donoso, F., Garcia-Garcia, A., Garcia-Rodriguez, J., Orts-Escolano, S., Cazorla, M., 2017. LonchaNet: A sliced-based CNN architecture for real-time 3D object recognition, in: 2017 International Joint Conference on Neural Networks (IJCNN). Presented at the 2017 International Joint Conference on Neural Networks (IJCNN), pp. 412–418. https://doi.org/10.1109/IJCNN.2017.7965883CrossRefGoogle Scholar
Hua Li, Yezzi, A., 2006. Vessels as 4D Curves: Global Minimal 4D Paths to Extract 3D Tubular Surfaces, in: 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06). Presented at the 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06), pp. 82–82. https://doi.org/10.1109/CVPRW.2006.210CrossRefGoogle Scholar
Kresslein, J., Haghighi, P., Park, J., Ramnath, S., Sutradhar, A., Shah, J.J., 2018. Automated cross-sectional shape recovery of 3D branching structures from point cloud. J. Comput. Des. Eng. 5, 368–378. https://doi.org/10.1016/j.jcde.2017.11.010Google Scholar
Lee, T.C., Kashyap, R.L., Chu, C.N., 1994. Building Skeleton Models via 3-D Medial Surface Axis Thinning Algorithms. CVGIP Graph. Models Image Process. 56, 462–478. https://doi.org/10.1006/cgip.1994.1042CrossRefGoogle Scholar
Lidayová, K., Frimmel, H., Wang, C., Bengtsson, E., Smedby, Ö., 2016. Fast vascular skeleton extraction algorithm. Pattern Recognit. Lett., Special Issue on Skeletonization and its Application 76, 67–75. https://doi.org/10.1016/j.patrec.2015.06.024Google Scholar
Lidayová, K., Gupta, A., Frimmel, H., Sintorn, I.-M., Bengtsson, E., Smedby, Ö., 2017. Classification of Cross-sections for Vascular Skeleton Extraction Using Convolutional Neural Networks, in: Valdés Hernández, M., González-Castro, V. (Eds.), Medical Image Understanding and Analysis. Springer International Publishing, Cham, pp. 182–194.CrossRefGoogle Scholar
Louhichi, B., Abenhaim, G.N., Tahan, A.S., 2015. CAD/CAE integration: updating the CAD model after a FEM analysis. Int. J. Adv. Manuf. Technol. 76, 391–400. https://doi.org/10.1007/s00170-014-6248-yCrossRefGoogle Scholar
Maturana, D., Scherer, S., 2015. VoxNet: A 3D Convolutional Neural Network for real-time object recognition, in: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Presented at the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928. https://doi.org/10.1109/IROS.2015.7353481CrossRefGoogle Scholar
Mayer, J., Wartzack, S., 2020. Ermittlung eines Skelettierungsverfahrens zur Konvertierung von Topologieoptimierungsergebnissen, in: Proceedings of the 31st Symposium Design for X (DFX2020). Presented at the Symposium Design for X 2020, Bamberg, pp. 111–120. https://doi.org/10.35199/dfx2020.12CrossRefGoogle Scholar
Mikołajczyk, A., Grochowski, M., 2018. Data augmentation for improving deep learning in image classification problem, in: 2018 International Interdisciplinary PhD Workshop (IIPhDW). Presented at the 2018 International Interdisciplinary PhD Workshop (IIPhDW), pp. 117–122. https://doi.org/10.1109/IIPHDW.2018.8388338CrossRefGoogle Scholar
Nana, A., Cuillière, J.-C., Francois, V., 2017. Automatic reconstruction of beam structures from 3D topology optimization results. Comput. Struct. 189, 62–82. https://doi.org/10.1016/j.compstruc.2017.04.018CrossRefGoogle Scholar
Qi, C.R., Su, H., Niessner, M., Dai, A., Yan, M., Guibas, L.J., 2016. Volumetric and Multi-View CNNs for Object Classification on 3D Data. ArXiv160403265 Cs.CrossRefGoogle Scholar
Reniers, D., Telea, A., 2008. Part-type Segmentation of Articulated Voxel-Shapes using the Junction Rule. Comput. Graph. Forum 27, 1845–1852. https://doi.org/10.1111/j.1467-8659.2008.01331.xCrossRefGoogle Scholar
Sedaghat, N., Zolfaghari, M., Amiri, E., Brox, T., 2017. Orientation-boosted Voxel Nets for 3D Object Recognition. ArXiv160403351 Cs.CrossRefGoogle Scholar
Shekar, B.H., Pilar, B., 2014. Shape Representation and Classification through Pattern Spectrum and Local Binary Pattern – A Decision Level Fusion Approach, in: 2014 Fifth International Conference on Signal and Image Processing. Presented at the 2014 Fifth International Conference on Signal and Image Processing, pp. 218–224. https://doi.org/10.1109/ICSIP.2014.41CrossRefGoogle Scholar
Shen, W., Jiang, Y., Gao, W., Zeng, D., Wang, X., 2014. Shape Recognition by Bag of Skeleton-associated Contour Parts. ArXiv160506417 Cs 483, 391–400. https://doi.org/10.1007/978-3-662-45646-0_40CrossRefGoogle Scholar
Stangl, T., Wartzack, S., 2015. Feature based interpretation and reconstruction of structural topology optimization results, in: Weber, M., C.;. Husung, S.;. Cascini, G.;. Cantamessa, M.;. Marjanovic, D.;. Bordegoni, (Ed.), Proceedings of the 20th International Conference on Engineering Design (ICED15). Design Society, p. Vol. 6, 235–245.Google Scholar
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.G., 2015. Multi-view convolutional neural networks for 3d shape recognition, in: Proc. ICCV.CrossRefGoogle Scholar
Tagliasacchi, A., Delame, T., Spagnuolo, M., Amenta, N., Telea, A., 2016. 3D Skeletons: A State-of-the-Art Report. Comput. Graph. Forum 35, 573–597. https://doi.org/10.1111/cgf.12865CrossRefGoogle Scholar
Tang, P.-S., Chang, K.-H., 2001. Integration of topology and shape optimization for design of structural components. Struct. Multidiscip. Optim. 22, 65–82. https://doi.org/10.1007/PL00013282CrossRefGoogle Scholar
Vidal, V., Wolf, C., Dupont, F., 2014. Mechanical Mesh Segmentation and Global 3D Shape Extraction.Google Scholar
Yang, C., Tiebe, O., Pietsch, P., Feinen, C., Kelter, U., Grzegorzek, M., 2014. Shape-based object retrieval by contour segment matching, in: 2014 IEEE International Conference on Image Processing (ICIP). Presented at the 2014 IEEE International Conference on Image Processing (ICIP), pp. 2202–2206. https://doi.org/10.1109/ICIP.2014.7025446CrossRefGoogle Scholar
Yin, G., Xiao, X., Cirak, F., 2020. Topologically robust CAD model generation for structural optimisation. Comput. Methods Appl. Mech. Eng. 369, 113102. https://doi.org/10.1016/j.cma.2020.113102CrossRefGoogle Scholar
Yoely, Y.M., Amir, O., Hanniel, I., 2018. Topology and shape optimization with explicit geometric constraints using a spline-based representation and a fixed grid. Procedia Manuf., 15th Global Conference on Sustainable Manufacturing 21, 189–196. https://doi.org/10.1016/j.promfg.2018.02.110CrossRefGoogle Scholar