Abstract
One of the most monotonous activities in using convolutional neural networks for image recognition is preparation of the learning data. It involves creating samples (2D images of object) at different angles of view, different backgrounds/materials and partial overlay of the object. Input data must include a relatively large number of frames, typically about 100 and more images per object to make the learning precision useful. In the paper there is proposed a new approach to creating these data fully automated based on a virtual 3D model of the standardized parts. Automation principle is generating 2D images from the imported 3D construction model, including the following variable parameters: the angle of rotation, background and the material of the component. We used for verification pretrained DNN model Faster RCNN Inception v2 with single shot detection (SSD). The learned convolutional network was next tested by real samples to verify a new approach of learning by virtual models and recognition of real objects (parts).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Židek, K., Maxim, V., Piteľ, J., Hošovský, A.: Embedded vision equipment of industrial robot for inline detection of product errors by clustering-classification algorithms. Int. J. Adv. Rob. Syst. 13(5), 1–10 (2016)
Židek, K., Piteľ, J., Hošovský, A.: Machine learning algorithms implementation into embedded systems with web application user interface. In: Proceedings of the IEEE 21st International Conference on Intelligent Engineering Systems 2017 (INES 2017), pp. 77–81. IEEE (2017)
Pavlenko, I., Trojanowska, J., Ivanov, V., Liaposhchenko, O.: Scientific and methodological approach for the identification of mathematical models of mechanical systems by using artificial neural networks. Lecture Notes in Electrical Engineering, pp. 299–306. Springer, Cham (2019)
Pavlenko, I., Simonovskiy, V., Ivanov, V., Zajac, J., Pitel, J.: Application of artificial neural network for identification of bearing stiffness characteristics in rotor dynamics analysis. Lecture Notes in Mechanical Engineering, pp. 325–335. Springer, Cham (2019)
Židek, K., Hosovsky, A., Piteľ, J., Bednár, S.: Recognition of assembly parts by convolutional neural networks. Lecture Notes in Mechanical Engineering, pp. 281–289. Springer, Cham (2018)
Sarkar, K., Varanasi, K., Stricker, D.: Trained 3D models for CNN based object recognition. In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Visigrapp 2017), vol 5, pp. 130–137 (2017)
Socher, R., Huval, B., Bhat, B., Manning, C.D., Ng, A.Y.: Convolutional-recursive deep learning for 3D object classification. In: NIPS (2012)
Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Tian, Y., Li, X., Wang, K., Wang, F.Y.: Training and testing object detectors with virtual images. IEEE/CAA J. Autom. Sin. 5, 539–546 (2018)
Nie, W.Z., Cao, Q., Liu, A.A., Su, Y.T.: Convolutional deep learning for 3D object retrieval. Multimed. Syst. 23, 325–332 (2017)
Peng, X.C., Sun, B.C., Ali, K., Saenko, K.: Learning deep object detectors from 3D models. In: IEEE International Conference on Computer Vision, pp. 1278–1286 (2015)
Karwasz, A., Trojanowska, J.: Using CAD 3D system in ecodesign - case study. In: Golinska-Dawson, P., Kolinski, A. (eds.) Efficiency in Sustainable Supply Chain. EcoProduction (Environmental Issues in Logistics and Manufacturing), pp. 137–160. Springer, Cham (2017)
Nguyen, C.H.P., Choi, Y.: Triangular mesh and boundary representation combined approach for 3D CAD lightweight representation for collaborative product development. J. Comput. Inf. Sci. Eng. 19, 9–11 (2018)
Cucos, M.M., Pista, I.M., Ripanu, M.I.: Product engineering design enhancing by parameterizing the 3D solid model. In: MATEC Web Conference, vol. 178, p. 05011 (2018)
Gao, Q.H., Wan, T.R., Tang, W., Chen, L., Zhang, K.B.: An improved augmented reality registration method based on Visual SLAM. In: International Conference on Technologies for E-Learning and Digital Entertainment, pp. 11–19. Springer, Cham (2017)
Liu, H., Wang, L.: An AR-based worker support system for human-robot collaboration. Procedia Manuf. 11, 22–30 (2017)
Takaseki, R., Nagashima, R., Kashima, H., Okazaki, T.: Development of anchoring support system using with AR toolkit. In: 2015 7th International Conference on Emerging Trends in Engineering & Technology (ICETET), pp. 123–127. IEEE (2015)
Židek, K., Janáčová, D., Hošovský, A., Piteľ, J., Lazorík, P.: Data optimization for communication between wireless IoT devices and cloud platforms in production process. In: 3rd EAI International Conference on Management of Manufacturing Systems (MMS 2018), pp. 1–8. EAI (2018)
Acknowledgments
This work was supported by the Slovak Research and Development Agency under the contract No. APVV-15-0602 and also by the Project of the Structural Funds of the EU, ITMS code: 26220220103.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Židek, K., Lazorík, P., Piteľ, J., Pavlenko, I., Hošovský, A. (2019). Automated Training of Convolutional Networks by Virtual 3D Models for Parts Recognition in Assembly Process. In: Trojanowska, J., Ciszak, O., Machado, J., Pavlenko, I. (eds) Advances in Manufacturing II. MANUFACTURING 2019. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-030-18715-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-18715-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-18714-9
Online ISBN: 978-3-030-18715-6
eBook Packages: EngineeringEngineering (R0)