{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:31:39Z","timestamp":1762353099963},"reference-count":36,"publisher":"Walter de Gruyter GmbH","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Image processing techniques are widely used within automotive series production, including production of electronic control units (ECUs). Deep learning approaches have made rapid advances during the last years, but are not prominent in those industrial settings yet. One major obstacle is the lack of suitable training data. We adapt the recently developed method of domain randomization to our use case of 3D pose estimation of ECU housings. We create purely synthetic data with high visual diversity to train artificial neural networks (ANNs). This enables ANNs to estimate the 3D pose of a real sample part with high accuracy from a single low-resolution RGB image in a production-like setting. Requirements regarding measurement hardware are very low. Our entire setup is fully automated and can be transferred to related industrial use cases.<\/jats:p>","DOI":"10.1515\/auto-2021-0020","type":"journal-article","created":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T23:30:31Z","timestamp":1633044631000},"page":"880-891","source":"Crossref","is-referenced-by-count":2,"title":["CAD-to-real: enabling deep neural networks for 3D pose estimation of electronic control units"],"prefix":"10.1515","volume":"69","author":[{"given":"Simon","family":"B\u00e4uerle","sequence":"first","affiliation":[{"name":"Institute for Automation and Applied Informatics (IAI) , Karlsruhe Institute of Technology (KIT) , Eggenstein-Leopoldshafen , Germany"}]},{"given":"Moritz","family":"B\u00f6hland","sequence":"additional","affiliation":[{"name":"Institute for Automation and Applied Informatics (IAI) , Karlsruhe Institute of Technology (KIT) , Eggenstein-Leopoldshafen , Germany"}]},{"given":"Jonas","family":"Barth","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH , Reutlingen , Germany"}]},{"given":"Markus","family":"Reischl","sequence":"additional","affiliation":[{"name":"Institute for Automation and Applied Informatics (IAI) , Karlsruhe Institute of Technology (KIT) , Eggenstein-Leopoldshafen , Germany"}]},{"given":"Andreas","family":"Steimer","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence (BCAI) , Robert Bosch GmbH , Renningen , Germany"}]},{"given":"Ralf","family":"Mikut","sequence":"additional","affiliation":[{"name":"Institute for Automation and Applied Informatics (IAI) , Karlsruhe Institute of Technology (KIT) , Eggenstein-Leopoldshafen , Germany"}]}],"member":"374","published-online":{"date-parts":[[2021,10,1]]},"reference":[{"key":"2023033110072211894_j_auto-2021-0020_ref_001","doi-asserted-by":"crossref","unstructured":"Ammirato, P.; Tremblay, J.; Liu, M.-Y.; Berg, A.; Fox, D.: Symgan: Orientation estimation without annotation for symmetric objects. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), p.\u20091668\u20131677, 2020.","DOI":"10.1109\/WACV45572.2020.9093450"},{"key":"2023033110072211894_j_auto-2021-0020_ref_002","doi-asserted-by":"crossref","unstructured":"Andrychowicz, O.\u2009M.; Baker, B.; Chociej, M.; J\u00f3zefowicz, R.; McGrew, B.; Pachocki, J.; Petron, A.; Plappert, M.; Powell, G.; Ray, A.; Schneider, J.; Sidor, S.; Tobin, J.; Welinder, P.; Weng, L.; Zaremba, W.: Learning dexterous in-hand manipulation. The International Journal of Robotics Research 39 (2020) 1, p.\u20093\u201320.","DOI":"10.1177\/0278364919887447"},{"key":"2023033110072211894_j_auto-2021-0020_ref_003","unstructured":"Baeuerle, S.; Barth, J.; Tavares de Menezes, E.\u2009R.; Steimer, A.; Mikut, R.: CAD2Real: Deep learning with domain randomization of CAD data for 3D pose estimation of electronic control unit housings. In: Proceedings \u2013 30. Workshop Computational Intelligence, p.\u200933\u201352, KIT Scientific Publishing, 2020."},{"key":"2023033110072211894_j_auto-2021-0020_ref_004","doi-asserted-by":"crossref","unstructured":"Brand, A.; Allen, L.; Altman, M.; Hlava, M.; Scott, J.: Beyond authorship: attribution, contribution, collaboration, and credit. Learned Publishing 28 (2015) 2, p.\u2009151\u2013155.","DOI":"10.1087\/20150211"},{"key":"2023033110072211894_j_auto-2021-0020_ref_005","unstructured":"B\u00e4uerle, A.; Ropinski, T.: Net2Vis: Transforming Deep Convolutional Networks into Publication-Ready Visualizations. Techn. Rep., arXiv:1902.04394, 2019."},{"key":"2023033110072211894_j_auto-2021-0020_ref_006","unstructured":"B\u00f6hland, M.; Scherr, T.; Bartschat, A.; Mikut, R.; Reischl, M.: Influence of synthetic label image object properties on GAN supported segmentation pipelines. In: Proceedings \u2013 29. Workshop Computational Intelligence, p.\u2009289\u2013309, KIT Scientific Publishing, 2019."},{"key":"2023033110072211894_j_auto-2021-0020_ref_007","unstructured":"Chollet, F.; et\u2009al.: Keras. https:\/\/keras.io, 2015."},{"key":"2023033110072211894_j_auto-2021-0020_ref_008","unstructured":"Do, T.-T.; Cai, M.; Pham, T.; Reid, I.: Deep-6Dpose: Recovering 6D object pose from a single RGB image. Techn. Rep., arXiv:1802.10367, 2018."},{"key":"2023033110072211894_j_auto-2021-0020_ref_009","doi-asserted-by":"crossref","unstructured":"Gr\u00fcn, S.; H\u00f6ninger, S.; Scheikl, P.\u2009M.; Hein, B.; Kr\u00f6ger, T.: Evaluation of domain randomization techniques for transfer learning. In: 2019 19th International Conference on Advanced Robotics (ICAR), p.\u2009481\u2013486, IEEE, 2019.","DOI":"10.1109\/ICAR46387.2019.8981654"},{"key":"2023033110072211894_j_auto-2021-0020_ref_010","doi-asserted-by":"crossref","unstructured":"He, K.; Zhang, X.; Ren, S.; Sun, J.: Deep residual learning for image recognition. Techn. Rep., arXiv:1512.03385, 2015.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2023033110072211894_j_auto-2021-0020_ref_011","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S.; Pauly, O.; Heibel, H.; Martina, M.; Bokeloh, M.: An annotation saved is an annotation earned: Using fully synthetic training for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00340"},{"key":"2023033110072211894_j_auto-2021-0020_ref_012","doi-asserted-by":"crossref","unstructured":"James, S.; Wohlhart, P.; Kalakrishnan, M.; Kalashnikov, D.; Irpan, A.; Ibarz, J.; Levine, S.; Hadsell, R.; Bousmalis, K.: Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), p.\u200912627\u201312637, 2019.","DOI":"10.1109\/CVPR.2019.01291"},{"key":"2023033110072211894_j_auto-2021-0020_ref_013","doi-asserted-by":"crossref","unstructured":"Kehl, W.; Manhardt, F.; Tombari, F.; Ilic, S.; Navab, N.: SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), p.\u20091521\u20131529, 2017.","DOI":"10.1109\/ICCV.2017.169"},{"key":"2023033110072211894_j_auto-2021-0020_ref_014","doi-asserted-by":"crossref","unstructured":"Kendall, A.; Grimes, M.; Cipolla, R.: PoseNet: A convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), p.\u20092938\u20132946, 2015.","DOI":"10.1109\/ICCV.2015.336"},{"key":"2023033110072211894_j_auto-2021-0020_ref_015","doi-asserted-by":"crossref","unstructured":"Khirodkar, R.; Yoo, D.; Kitani, K.: Domain randomization for scene-specific car detection and pose estimation. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), p.\u20091932\u20131940, IEEE, 2019.","DOI":"10.1109\/WACV.2019.00210"},{"key":"2023033110072211894_j_auto-2021-0020_ref_016","doi-asserted-by":"crossref","unstructured":"Kleeberger, K.; Huber, M.\u2009F.: Single shot 6D object pose estimation. Techn. Rep., arXiv:2004.12729, 2020.","DOI":"10.1109\/ICRA40945.2020.9197207"},{"key":"2023033110072211894_j_auto-2021-0020_ref_017","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A.; Rom, H.; Alldrin, N.; Uijlings, J.; Krasin, I.; Pont-Tuset, J.; Kamali, S.; Popov, S.; Malloci, M.; Kolesnikov, A.; Duerig, T.; Ferrari, V.: The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale. IJCV (2020).","DOI":"10.1007\/s11263-020-01316-z"},{"key":"2023033110072211894_j_auto-2021-0020_ref_018","unstructured":"Liu, M.-Y.; Breuel, T.; Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems (Guyon, I.; Luxburg, U.\u2009V.; Bengio, S.; Wallach, H.; Fergus, R.; Vishwanathan, S.; Garnett, R., Eds.), Vol.\u200930, p.\u2009700\u2013708, Curran Associates, Inc., 2017."},{"key":"2023033110072211894_j_auto-2021-0020_ref_019","doi-asserted-by":"crossref","unstructured":"Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.-Y.; Berg, A.\u2009C.: SSD: Single Shot MultiBox Detector. In: Computer Vision \u2013 ECCV 2016 (Leibe, B.; Matas, J.; Sebe, N.; Welling, M., Eds.), p.\u200921\u201337, Cham: Springer International Publishing, 2016.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2023033110072211894_j_auto-2021-0020_ref_020","doi-asserted-by":"crossref","unstructured":"Mahendran, S.; Ali, H.; Vidal, R.: 3D pose regression using convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops, p.\u20092174\u20132182, 2017.","DOI":"10.1109\/ICCVW.2017.254"},{"key":"2023033110072211894_j_auto-2021-0020_ref_021","doi-asserted-by":"crossref","unstructured":"Peng, X.\u2009B.; Andrychowicz, M.; Zaremba, W.; Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), p.\u20093803\u20133810, IEEE, 2018.","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"2023033110072211894_j_auto-2021-0020_ref_022","doi-asserted-by":"crossref","unstructured":"Rad, M.; Lepetit, V.: BB8: A scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: Proceedings of the IEEE International Conference on Computer Vision, p.\u20093828\u20133836, 2017.","DOI":"10.1109\/ICCV.2017.413"},{"key":"2023033110072211894_j_auto-2021-0020_ref_023","doi-asserted-by":"crossref","unstructured":"Ren, X.; Luo, J.; SolowjoW, E.; Ojea, J.\u2009A.; Gupta, A.; Tamar, A.; Abbeel, P.: Domain randomization for active pose estimation. In: 2019 International Conference on Robotics and Automation (ICRA), p.\u20097228\u20137234, IEEE, 2019.","DOI":"10.1109\/ICRA.2019.8794126"},{"key":"2023033110072211894_j_auto-2021-0020_ref_024","doi-asserted-by":"crossref","unstructured":"Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; Berg, A.\u2009C.; Fei-Fei, L.: ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV) 115 (2015) 3, p.\u2009211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"2023033110072211894_j_auto-2021-0020_ref_025","doi-asserted-by":"crossref","unstructured":"Sadeghi, F.; Levine, S.: Cad2RL: Real single-image flight without a single real image. Techn. Rep., arXiv:1611.04201, 2016.","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"2023033110072211894_j_auto-2021-0020_ref_026","doi-asserted-by":"crossref","unstructured":"Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C.: MobilenetV2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p.\u20094510\u20134520, 2018.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2023033110072211894_j_auto-2021-0020_ref_027","doi-asserted-by":"crossref","unstructured":"Schutera, M.; Hussein, M.; Abhau, J.; Mikut, R.; Reischl, M.: Night-to-Day: Online image-to-image translation for object detection within autonomous driving by night. IEEE Transactions on Intelligent Vehicles (2020).","DOI":"10.1109\/TIV.2020.3039456"},{"key":"2023033110072211894_j_auto-2021-0020_ref_028","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M.; Durner, M.; Puang, E.\u2009Y.; Marton, Z.-C.; Vaskevicius, N.; Arras, K.\u2009O.; Triebel, R.: Multi-path learning for object pose estimation across domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), p.\u200913916\u201313925, 2020.","DOI":"10.1109\/CVPR42600.2020.01393"},{"key":"2023033110072211894_j_auto-2021-0020_ref_029","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M.; Marton, Z.-C.; Durner, M.; Brucker, M.; Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), p.\u2009699\u2013715, 2018.","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"2023033110072211894_j_auto-2021-0020_ref_030","doi-asserted-by":"crossref","unstructured":"Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p.\u20092818\u20132826, 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"2023033110072211894_j_auto-2021-0020_ref_031","doi-asserted-by":"crossref","unstructured":"Tobin, J.; Fong, R.; Ray, A.; Schneider, J.; Zaremba, W.; Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), p.\u200923\u201330, IEEE, 2017.","DOI":"10.1109\/IROS.2017.8202133"},{"key":"2023033110072211894_j_auto-2021-0020_ref_032","doi-asserted-by":"crossref","unstructured":"Tremblay, J.; Prakash, A.; Acuna, D.; Brophy, M.; Jampani, V.; Anil, C.; To, T.; Cameracci, E.; Boochoon, S.; Birchfield, S.: Training deep networks with synthetic data: Bridging the reality gap by domain randomization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, p.\u2009969\u2013977, 2018.","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"2023033110072211894_j_auto-2021-0020_ref_033","unstructured":"Tremblay, J.; To, T.; Sundaralingam, B.; Xiang, Y.; Fox, D.; Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. Techn. Rep., arXiv:1809.10790, 2018."},{"key":"2023033110072211894_j_auto-2021-0020_ref_034","doi-asserted-by":"crossref","unstructured":"Wang, M.; Deng, W.: Deep visual domain adaptation: A survey. Neurocomputing 312 (2018), p.\u2009135\u2013153.","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"2023033110072211894_j_auto-2021-0020_ref_035","doi-asserted-by":"crossref","unstructured":"Xiang, Y.; Schmidt, T.; Narayanan, V.; Fox, D.: PoseCNN: A convolutional neural network for 6D object pose estimation in cluttered scenes. Techn. Rep., arXiv:1711.00199, 2017.","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"2023033110072211894_j_auto-2021-0020_ref_036","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y.; Park, T.; Isola, P.; Efros, A.\u2009A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), p.\u20092223\u20132232, 2017.","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2021-0020\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2021-0020\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T11:11:24Z","timestamp":1680261084000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2021-0020\/html"}},"subtitle":["A transferable and automated approach for industrial use cases"],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10,1]]},"published-print":{"date-parts":[[2021,10,26]]}},"alternative-id":["10.1515\/auto-2021-0020"],"URL":"https:\/\/doi.org\/10.1515\/auto-2021-0020","relation":{},"ISSN":["2196-677X","0178-2312"],"issn-type":[{"value":"2196-677X","type":"electronic"},{"value":"0178-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2021,10,1]]}}}