{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:05:52Z","timestamp":1753891552816,"version":"3.41.2"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T00:00:00Z","timestamp":1690934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFE03170001"],"award-info":[{"award-number":["2022YFE03170001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>A hot cell is generally deployed with a teleoperation power manipulator to complete tests, operations, and maintenance. The position and pose of the manipulator are mostly acquired through radiation-resistant video cameras arranged in the hot cell. In this paper, deep learning-based target detection technology is used to establish an experimental platform to test the methods for target detection and pose estimation of teleoperation power manipulators using two cameras.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In view of the fact that a complex environment affects the precision of manipulator pose estimation, the dilated-fully convolutional one-stage object detection (dilated-FCOS) teleoperation power manipulator target detection algorithm is proposed based on the scale of the teleoperation power manipulator. Model pruning is used to improve the real-time performance of the dilated-FCOS teleoperation power manipulator target detection model. To improve the detection speed for the key points of the teleoperation power manipulator, the keypoint detection precision and model inference speed of different lightweight backbone networks were tested based on the SimpleBaseline algorithm. MobileNetv1 was selected as the backbone network to perform channel compression and pose distillation on the upsampling module so as to further optimize the inference speed of the model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results and discussion<\/jats:title><jats:p>Compared with the original model, the proposed model was experimentally proven to reach basically the same precision within a shorter inference time (only 58% of that of the original model). The experimental results show that the compressed model basically retains the precision of the original model and that its inference time is 48% of that of the original model.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2023.1193823","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T10:15:31Z","timestamp":1690971331000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An improved model for target detection and pose estimation of a teleoperation power manipulator"],"prefix":"10.3389","volume":"17","author":[{"given":"Li","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,8,2]]},"reference":[{"key":"B1","article-title":"\u201c2D human pose estimation: new benchmark and state of the art analysis,\u201d","author":"Andriluka","year":"2014","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B2","first-page":"30","article-title":"Hot cell robot","volume":"59","author":"Assem","year":"2014","journal-title":"Nuc. Engin. Int"},{"key":"B3","doi-asserted-by":"publisher","first-page":"13034","DOI":"10.1109.\/CVPR46437.2021.01284","article-title":"\u201cYou only look one level feature,\u201d","author":"Chen","year":"2021","journal-title":"IEEE International Conference on Computer Vision and Pattern Recognition"},{"unstructured":"V-REP Simulator2022","key":"B4"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1992","DOI":"10.1016\/j.fusengdes.10008","article-title":"Localization of cask and plug remote handling system in ITER using multiple video cameras","volume":"88","author":"Ferreira","year":"2012","journal-title":"Fusion Engin. Design"},{"key":"B6","first-page":"95","article-title":"\u201c3D robot pose estimation from 2D images,\u201d","author":"Heindl","year":"2019","journal-title":"IEEE International Conference on Service Operations and Logistics, and Informatics"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007.\/978-3-319-54193-8_13","article-title":"\u201cEnd-to-end training of object class detectors for mean average precision,\u201d","author":"Henderson","year":"2017","journal-title":"Computer Vision\u2013ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20\u201324, 2016, Revised Selected Papers, Part V 13"},{"key":"B8","first-page":"38","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2014","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140","article-title":"\u201cSearching for mobileNetV3,\u201d","author":"Howard","year":"2020","journal-title":"IEEE\/CVF International Conference on Computer Vision"},{"key":"B10","first-page":"6812","article-title":"\u201cMobileNets: efficient convolutional neural networks for mobile vision applications,\u201d","author":"Howard","year":"2017","journal-title":"IEEE International Conference on Computer Vision and Pattern Recognition"},{"year":"2017","author":"Kehl","doi-asserted-by":"publisher","key":"B11","DOI":"10.1109.\/ICCV.2017.169"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural. Inform. Proc. Sys"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1016\/j.fusengdes.05004","article-title":"Virtual reality: lessons learned from west design and perspectives for nuclear environment","volume":"136","author":"Lionel","year":"2018","journal-title":"Fusion Engin. Design."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.fusengdes.2019.111422","article-title":"Vision-based tile recognition algorithms for robot grasping task in EAST","author":"Liu","year":"2020","journal-title":"Fusion Engin. Design"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4025","DOI":"10.1109\/CVPR.2018.00474","article-title":"\u201cInverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation,\u201d","author":"Liu","year":"2018","journal-title":"IEEE International Conference on Computer Vision and Pattern Recognition"},{"key":"B16","first-page":"2755","article-title":"Learning efficient convolutional networks through network slimming","author":"Liu","year":"2017","journal-title":"IEEE International Conference on Computer Vision"},{"key":"B17","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"\u201cV2: practical guidelines for efficient CNN architecture design,\u201d","author":"Ma","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2404","DOI":"10.1016\/j.fusengdes.01004","article-title":"Robot vision system RandD for ITER blanket remote-handling system","volume":"89","author":"Maruyama","year":"2014","journal-title":"Fusion Engin. Design"},{"key":"B19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/IISR.2018.8535937","author":"Mi\u0161eikis","year":""},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441813","article-title":"Multi-objective convolutional neural networks for robot localisation and 3D position estimation in 2D camera images","author":"Mi\u0161eikis","year":"","journal-title":"IEEE International Conference on Ubiquitous Robots"},{"unstructured":"2023","key":"B21"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1109\/LSP.2020.3032277","article-title":"Real-time 3D face alignment using an encoder-decoder network with an efficient deconvolution layer","volume":"27","author":"Ning","year":"2020","journal-title":"IEEE Sig. Process. Lett."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2604","DOI":"10.1016\/j.jbiomech.12","article-title":"An inertial and magnetic sensor based technique for joint angle measurement","volume":"40","author":"O'Donovan","year":"2006","journal-title":"J. Biomech"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2119","DOI":"10.1016\/j.fusengdes.11006","article-title":"Haptic shared control improves hot cell remote handling despite controller inaccuracies","volume":"88","author":"Oosterhout","year":"2012","journal-title":"Fusion Engin. Design"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1016\/j.anucene.06021","article-title":"novel approach to develop the control of Telbot using ANFIS for nuclear hotcells","volume":"38","author":"Pezhman","year":"2011","journal-title":"Annals Nuc. Energy"},{"key":"B26","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.fusengdes.01006","article-title":"Hand-eye coordinative remote maintenance in a tokamak vessel","volume":"104","author":"Qiu","year":"2016","journal-title":"Fusion Engin. Design"},{"key":"B27","doi-asserted-by":"publisher","first-page":"7263","DOI":"10.1109\/CVPR.2017.690","article-title":"YOLO9000: better, faster, stronger","author":"Redmon","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"year":"2016","author":"Ren","doi-asserted-by":"publisher","key":"B28","DOI":"10.1109.\/TPAMI.2016.2577031"},{"key":"B29","doi-asserted-by":"publisher","first-page":"112080","DOI":"10.1016\/j.fusengdes.2020.112080","article-title":"Robust vision using retro reflective markers for remote handling in ITER","volume":"161","author":"Ribeiro","year":"2020","journal-title":"Fusion Engin. Design"},{"key":"B30","first-page":"3124","article-title":"\u201cImageNet pre-trained models with batch normalization,\u201d","author":"Simon","year":"2016","journal-title":"IEEE International Conference on Computer Vision and Pattern Recognition"},{"key":"B31","first-page":"5686","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2017","journal-title":"IEEE International Conference on Computer Vision and Pattern Recognition"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1609.\/aaai.v31i1.11231","article-title":"\u201cInception-v4, inceptionresnet and the impact of residual connections on learning,\u201d","author":"Szegedy","year":"2016","journal-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109.\/ICCV.2019.00972","article-title":"Fully convolutional one-stage object detection","author":"Tian","year":"2020","journal-title":"IEEE International Conference on Computer Vision"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1109.\/CVPR.2014.214","article-title":"DeepPose: human pose estimation via deep neural networks","year":"2014","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511","article-title":"Convolutional Pose Machines","author":"Wei","year":"2016","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12138","article-title":"Age-compensated makeup transfer based on homologous continuity generative adversarial network model","author":"Wu","year":"2022","journal-title":"IET Comp. Vis"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007.\/978-3-030-01231-1_29","article-title":"\u201cSimple baselines for human pose estimation and tracking,\u201d","author":"Xiao","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1016\/S0143-8166(99)00043-3","article-title":"A two-beam laser triangulation for measuring the position of a moving object","volume":"31","author":"Zeng","year":"1999","journal-title":"Optics Lasers Engin"},{"key":"B39","doi-asserted-by":"publisher","first-page":"108752","DOI":"10.1016\/j.anucene.2021.108752","article-title":"Study on neutron shielding performance of hot cell shielding door for nuclear power plant","volume":"166","author":"Zhang","year":"2022","journal-title":"Ann. Nuc. Energy"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1109.\/ROBIO54168.2021.9739245","article-title":"Design of power manipulator for hot cell facility","author":"Zhang","year":"2021","journal-title":"2021 IEEE International Conference on Robotics and Biomimetic"},{"key":"B41","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.fusengdes.06088","article-title":"Conceptual layout design of CFETR Hot cell facility","volume":"100","author":"Zheng","year":"2015","journal-title":"Fusion Engin. Design"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1193823\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T10:15:36Z","timestamp":1690971336000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1193823\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,2]]},"references-count":41,"alternative-id":["10.3389\/fnbot.2023.1193823"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1193823","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2023,8,2]]},"article-number":"1193823"}}