{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:00:41Z","timestamp":1780290041083,"version":"3.54.0"},"reference-count":44,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human pose estimation in orbit is critical for astronaut health monitoring, task assistance, and intelligent human\u2013robot interaction aboard space stations. However, in microgravity, human poses exhibit arbitrary orientations and are often affected by severe occlusion and complex background interference, while the scarcity of annotated in-orbit data makes it difficult to directly transfer models trained on ground-based datasets. Existing semi-supervised methods also lack explicit constraints from human structural topology and pose-related physical priors, which often leads to unreasonable pseudo-labels and limits performance gains. To address these issues, we propose a physics-inspired semi-supervised pose estimation framework for microgravity scenarios. Specifically, a Canonical Orientation Constraint is introduced to alleviate orientation ambiguity; a Structure-aware Pseudo-Label Refinement module is designed to improve pseudo-label quality; and an Uncertainty-guided Rotational Consistency Framework is proposed to adaptively weight consistency learning under multi-view rotation augmentation. Within a Mean Teacher architecture, the proposed method jointly optimizes the supervised loss, orientation constraint, pseudo-label refinement, and rotational consistency objectives. Experiments on the Astro-Pose dataset show that the proposed method consistently outperforms both fully supervised and semi-supervised baselines under various extreme poses and occlusion conditions, improving AP from 47.6 to 55.6 and AR from 52.4 to 60.1, demonstrating its potential for space-station visual monitoring.<\/jats:p>","DOI":"10.3390\/s26113406","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T08:00:36Z","timestamp":1779955236000},"page":"3406","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PhysAstro-Pose: Physics-Inspired Semi-Supervised Human Pose Estimation in Microgravity Environments"],"prefix":"10.3390","volume":"26","author":[{"given":"Youhui","family":"Cui","sequence":"first","affiliation":[{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201304, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Chang","sequence":"additional","affiliation":[{"name":"Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201304, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.neubiorev.2020.11.017","article-title":"Microgravity Effects on the Human Brain and Behavior: Dysfunction and Adaptive Plasticity","volume":"122","author":"Hupfeld","year":"2021","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1109\/TIE.2020.3048285","article-title":"ROpenPose: A Rapider OpenPose Model for Astronaut Operation Attitude Detection","volume":"69","author":"Wu","year":"2022","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","unstructured":"Xu, Y., Zhang, J., Zhang, Q., and Tao, D. (2022). ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation. Proceedings of the 36th International Conference on Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"130877","DOI":"10.1016\/j.neucom.2025.130877","article-title":"H3-Astronaut Pose Net: A Multiview 3D Astronaut Pose Estimation System for Spacecraft","volume":"650","author":"Xun","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"De Souza Cardoso, L.F., Schwandt, T., and Broll, W. (2024). \u03bcPose: Synthetic Dataset for Human Pose Estimation in Microgravity Environments. Proceedings of the 2024 IEEE Conference on Artificial Intelligence (CAI), IEEE.","DOI":"10.1109\/CAI59869.2024.00282"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gan, S., Zhang, X., Zhuge, S., Ning, C., Zhong, L., and Li, Y. (2023). A Multi-View Vision System for Astronaut Postural Reconstruction with Self-Calibration. Aerospace, 10.","DOI":"10.3390\/aerospace10030298"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gupta, D.K., Arya, D., and Gavves, E. (2021). Rotation Equivariant Siamese Networks for Tracking. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.01218"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3603618","article-title":"Deep Learning-Based Human Pose Estimation: A Survey","volume":"56","author":"Zheng","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X.-S., Liu, L., and Yang, J. (2017). Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2017.137"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/978-3-030-01216-8_44","article-title":"Multi-Scale Structure-Aware Network for Human Pose Estimation","volume":"Volume 11206","author":"Ferrari","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_12","unstructured":"Lee, D.-H. (2013, January 17\u201319). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. Proceedings of the ICML 2013 Workshop on Challenges in Representation Learning, Atlanta, GA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J. (2019). Deep High-Resolution Representation Learning for Human Pose Estimation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., and Murphy, K. (2017). Towards Accurate Multi-Person Pose Estimation in the Wild. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.395"},{"key":"ref_15","unstructured":"Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., and Grundmann, M. (2020). BlazePose: On-Device Real-Time Body Pose Tracking. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022). YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xie, R., Wang, C., Zeng, W., and Wang, Y. (2021). An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.01105"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, L., Li, Y., Tian, H., Yang, Y., Li, X., Deng, W., and Ye, J. (2023). Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.00074"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhou, H., Luo, M., Jiang, F., Ding, Y., Lu, H., and Jia, K. (2025). Boosting Semi-Supervised 2d Human Pose Estimation by Revisiting Data Augmentation and Consistency Training. arXiv.","DOI":"10.2139\/ssrn.5180670"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1933","DOI":"10.1007\/s11431-023-2599-8","article-title":"AstroPose: Astronaut Pose Estimation Using a Monocular Camera during Extravehicular Activities","volume":"67","author":"Liu","year":"2024","journal-title":"Sci. China Technol. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"108875","DOI":"10.1016\/j.neunet.2026.108875","article-title":"AstroHSP: A Hybrid Supervision Framework for Robust Monocular Astronaut Pose Estimation","volume":"200","author":"Jian","year":"2026","journal-title":"Neural Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., and Sun, J. (2018). Cascaded Pyramid Network for Multi-Person Pose Estimation. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref_23","first-page":"606","article-title":"Adversarial Semantic Data Augmentation for Human Pose Estimation","volume":"Volume 12364","author":"Vedaldi","year":"2020","journal-title":"Computer Vision\u2014ECCV 2020"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"10687","DOI":"10.1109\/TPAMI.2023.3264742","article-title":"Bias-Compensated Integral Regression for Human Pose Estimation","volume":"45","author":"Gu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-981-96-0885-0_11","article-title":"Learning 2D Human Poses for Better 3D Lifting via Multi-Model 3D-Guidance","volume":"Volume 15472","author":"Cho","year":"2025","journal-title":"Computer Vision\u2014ACCV 2024"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Toshev, A., and Szegedy, C. (2014). DeepPose: Human Pose Estimation via Deep Neural Networks. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","article-title":"Simple Baselines for Human Pose Estimation and Tracking","volume":"Volume 11210","author":"Ferrari","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft COCO: Common Objects in Context","volume":"Volume 8693","author":"Fleet","year":"2014","journal-title":"Computer Vision\u2014ECCV 2014"},{"key":"ref_29","unstructured":"Sajjadi, M., Javanmardi, M., and Tasdizen, T. (2016). Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Dollar, P., Girshick, R., Gkioxari, G., and He, K. (2018). Data Distillation: Towards Omni-Supervised Learning. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00433"},{"key":"ref_31","unstructured":"Laine, S., and Aila, T. (2017). Temporal Ensembling for Semi-Supervised Learning. arXiv."},{"key":"ref_32","unstructured":"Tarvainen, A., and Valpola, H. (2017). Mean Teachers Are Better Role Models: Weight-Averaged Consistency Targets Improve Semi-Supervised Deep Learning Results. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Raychaudhuri, D.S., Ta, C.-K., Dutta, A., Lal, R., and Roy-Chowdhury, A.K. (2023). Prior-Guided Source-Free Domain Adaptation for Human Pose Estimation. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01377"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3307","DOI":"10.1109\/LRA.2024.3364834","article-title":"Astrobee ISS Free-Flyer Datasets for Space Intra-Vehicular Robot Navigation Research","volume":"9","author":"Kang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"42883","DOI":"10.1038\/s41598-025-26972-4","article-title":"Deep Learning-Based Approaches for Human Pose Estimation in Interdisciplinary Physics Applications","volume":"15","author":"Zhiliang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"68787","DOI":"10.1109\/ACCESS.2020.2986473","article-title":"Hierarchical Attention-Based Astronaut Gesture Recognition: A Dataset and CNN Model","volume":"8","author":"Lingyun","year":"2020","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110925","DOI":"10.1016\/j.patcog.2024.110925","article-title":"GraphMLP: A Graph MLP-like Architecture for 3D Human Pose Estimation","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_38","unstructured":"Wen, D., Qi, L., Peng, K., Yang, K., Teng, F., Luo, A., Fu, J., Chen, Y., Liu, R., and Shi, Y. (2025). Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Yu, Z., Wang, M., Chen, Y., Favaro, P., and Modolo, D. (2024). Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation. Proceedings of the 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE.","DOI":"10.1109\/WACV57701.2024.00616"},{"key":"ref_40","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., and Azar, M.G. (2020). Bootstrap Your Own Latent A New Approach to Self-Supervised Learning. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rudolph, M., Zell, P., Rhodin, H., and Rosenhahn, B. (2021). CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.01309"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., and Lin, D. (2018, January 2\u20137). Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"102476","DOI":"10.1016\/j.artmed.2022.102476","article-title":"Uncertainty-Guided Mutual Consistency Learning for Semi-Supervised Medical Image Segmentation","volume":"138","author":"Zhang","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Xu, C., Chen, S., Li, M., and Zhang, Y. (2021, January 2\u20139). Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i4.16409"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3406\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T04:11:24Z","timestamp":1780287084000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":44,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26113406"],"URL":"https:\/\/doi.org\/10.3390\/s26113406","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]}}}