{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T05:23:11Z","timestamp":1762924991391,"version":"3.45.0"},"reference-count":54,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Omani Ministry of Higher Education, Research, and Innovation","award":["BFP\/RGP\/ICT\/23\/382"],"award-info":[{"award-number":["BFP\/RGP\/ICT\/23\/382"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Human Pose Estimation (HPE) models have varied applications and represent a cutting-edge branch of study, whose systems such as MediaPipe (MP), OpenPose (OP), and AlphaPose (ALP) show marked success. One of these areas, however, that is inadequately researched is the impact of image degradation on the accuracy of HPE models. Image degradation refers to images whose visual quality has been purposefully degraded by means of techniques, such as brightness adjustments (which can lead to an increase or a decrease in the intensity levels), geometric rotations, or resolution downscaling. The study of how these types of degradation impact the performance functionality of HPE models is an under-researched domaina that is a virtually unexplored area. In addition, current methods of the efficacy of existing image restoration techniques have not been rigorously evaluated and improving degraded images to a high quality has not been well examined in relation to improving HPE models. In this study, we explicitly clearly demonstrate a decline in the precision of the HPE model when image quality is degraded. Our qualitative and quantitative measurements identify a wide difference in performance in identifying landmarks as images undergo changes in brightness, rotation, or reductions in resolution. Additionally, we have tested a variety of existing image enhancement methods in an attempt to enhance their capability in restoring low-quality images, hence supporting improved functionality of HPE. Interestingly, for rotated images, using Pillow of OpenCV improves landmark recognition precision drastically, nearly restoring it to levels we see in high-quality images. In instances of brightness variation and in low-quality images, however, existing methods of enhancement fail to yield the improvements anticipated, highlighting a large direction of study that warrants further investigation and calls for additional research. In this regard, we proposed a wide-ranging system for classifying different types of image degradation systematically and for selecting appropriate algorithms for image restoration, in an effort to restore image quality. A key finding is that in a related study of current methods, the Tuned RotNet model achieves 92.04% accuracy, significantly outperforming the baseline model and surpassing the official RotNet model in predicting rotation degree of images, where the accuracy of official RotNet and Tuned RotNet classifiers were 61.59% and 92.04%, respectively. Furthermore, in an effort to facilitate future research and make it easier for other studies, we provide a new dataset of reference images and corresponding degenerated images, addressing a notable gap in controlled comparative studies, since currently there is a lack of controlled comparatives.<\/jats:p>","DOI":"10.3390\/info16110970","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T17:45:34Z","timestamp":1762796734000},"page":"970","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Robust Human Pose Estimation Under Real-World Image Degradations and Restoration Scenarios"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2530-5041","authenticated-orcid":false,"given":"Nada E.","family":"Elshami","sequence":"first","affiliation":[{"name":"College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt"},{"name":"Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3433-7640","authenticated-orcid":false,"given":"Ahmad","family":"Salah","sequence":"additional","affiliation":[{"name":"College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 516, Oman"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1153-8538","authenticated-orcid":false,"given":"Amr","family":"Abdellatif","sequence":"additional","affiliation":[{"name":"College of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2003-0357","authenticated-orcid":false,"given":"Heba","family":"Mohsen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo 11835, Egypt"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"ref_1","unstructured":"Guo, W., Pan, Z., Xi, Z., Tuerxun, A., Feng, J., and Zhou, J. (2024). Sports analysis and VR viewing system based on player tracking and pose estimation with multimodal and multiview sensors. arXiv."},{"key":"ref_2","unstructured":"Zhou, L., Meng, X., Liu, Z., Wu, M., Gao, Z., and Wang, P. (2023). Human pose-based estimation, tracking and action recognition with deep learning: A survey. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3115","DOI":"10.1007\/s00530-022-01019-0","article-title":"2D human pose estimation: A survey","volume":"29","author":"Chen","year":"2023","journal-title":"Multimed. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Stenum, J., Cherry-Allen, K.M., Pyles, C.O., Reetzke, R.D., Vignos, M.F., and Roemmich, R.T. (2021). Applications of pose estimation in human health and performance across the lifespan. Sensors, 21.","DOI":"10.3390\/s21217315"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., and Schiele, B. (2014, January 23\u201328). 2D human pose estimation: New benchmark and state of the art analysis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sapp, B., and Taskar, B. (2013, January 23\u201328). Modec: Multimodal decomposable models for human pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.471"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e37072","DOI":"10.1016\/j.heliyon.2024.e37072","article-title":"Foreign object detection in urban rail transit based on deep differentiation segmentation neural network","volume":"10","author":"Tan","year":"2024","journal-title":"Heliyon"},{"key":"ref_8","first-page":"463","article-title":"Facial micro-expression recognition method based on CNN and transformer mixed model","volume":"16","author":"Tang","year":"2024","journal-title":"Int. J. Biom."},{"key":"ref_9","unstructured":"Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.L., Yong, M.G., and Lee, J. (2019). MediaPipe: A framework for building perception pipelines. arXiv."},{"key":"ref_10","unstructured":"Singh, A.K., Kumbhare, V.A., and Arthi, K. (2021). Real-time human pose detection and recognition using MediaPipe. Advances in Intelligent Systems and Computing, Proceedings of the International Conference on Soft Computing and Signal Processing, Hyderabad, India, 18\u201319 June 2021, Springer."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1007\/s42979-022-01567-2","article-title":"Poseanalyser: A survey on human pose estimation","volume":"4","author":"Kulkarni","year":"2023","journal-title":"SN Comput. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., and Sheikh, Y. (2017, January 21\u201326). Realtime multi-person 2D pose estimation using part affinity fields. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kitamura, T., Teshima, H., Thomas, D., and Kawasaki, H. (2022, January 3\u20138). Refining OpenPose with a new sports dataset for robust 2D pose estimation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACVW54805.2022.00074"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e39977","DOI":"10.1016\/j.heliyon.2024.e39977","article-title":"A comprehensive analysis of the machine learning pose estimation models used in human movement and posture analyses: A narrative review","volume":"10","author":"Roggio","year":"2024","journal-title":"Heliyon"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dedhia, U., Bhoir, P., Ranka, P., and Kanani, P. (2023, January 1\u20132). Pose estimation and virtual gym assistant using MediaPipe and machine learning. Proceedings of the 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), Bengaluru, India.","DOI":"10.1109\/NMITCON58196.2023.10275938"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7157","DOI":"10.1109\/TPAMI.2022.3222784","article-title":"Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time","volume":"45","author":"Fang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107192","DOI":"10.1016\/j.compeleceng.2021.107192","article-title":"Estimating a 2D pose from a tiny person image with super-resolution reconstruction","volume":"93","author":"Zhang","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"ref_18","unstructured":"Johnson, S., and Everingham, M. (September, January 31). Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation. Proceedings of the British Machine Vision Conference (BMVC), Aberystwyth, UK."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, X., Li, F., Bai, H., Ni, R., and Zhao, Y. (2022). SRPose: Low-resolution human pose estimation with super-resolution. Smart Innovation, Systems and Technologies, Proceedings of the International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Kitakyushu, Japan, 16\u201318 December 2022, Springer.","DOI":"10.1007\/978-981-99-0605-5_33"},{"key":"ref_20","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft COCO: Common objects in context. Computer Vision\u2014Proceedings of the ECCV 2014: 13th European Conference, Zurich, Switzerland, 6\u201312 September 2014, Springer. Proceedings, Part V 13."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tran, T.Q., Nguyen, G.V., and Kim, D. (2021, January 10\u201315). Simple multi-resolution representation learning for human pose estimation. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412729"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"32502","DOI":"10.1109\/ACCESS.2020.2973390","article-title":"Robust human pose estimation for rotation via self-supervised learning","volume":"8","author":"Yun","year":"2020","journal-title":"IEEE Access"},{"key":"ref_23","unstructured":"Gidaris, S., Singh, P., and Komodakis, N. (2018). Unsupervised representation learning by predicting image rotations. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kim, J.W., Choi, J.Y., Ha, E.J., and Choi, J.H. (2023). Human pose estimation using MediaPipe pose and optimization method based on a humanoid model. Appl. Sci., 13.","DOI":"10.3390\/app13042700"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.procs.2024.11.132","article-title":"Accuracy assessment of 2D pose estimation with MediaPipe for physiotherapy exercises","volume":"251","author":"SIMOES","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9541","DOI":"10.1109\/LRA.2022.3192200","article-title":"An end-to-end cascaded image deraining and object detection neural network","volume":"7","author":"Wang","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"104820","DOI":"10.1016\/j.imavis.2023.104820","article-title":"Frequency and content dual stream network for image dehazing","volume":"139","author":"Wang","year":"2023","journal-title":"Image Vis. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"881","DOI":"10.28991\/ESJ-2022-06-04-015","article-title":"Brightness as an augmentation technique for image classification","volume":"6","author":"Kandel","year":"2022","journal-title":"Emerg. Sci. J."},{"key":"ref_29","first-page":"4606828","article-title":"Sharpness and brightness quality assessment of face images for recognition","volume":"2021","author":"Li","year":"2021","journal-title":"Sci. Program."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Bengtsson Bernander, K., Sintorn, I.M., Strand, R., and Nystr\u00f6m, I. (2024). Classification of rotation-invariant biomedical images using equivariant neural networks. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-65597-x"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Dong, W., Zhang, J., Zhou, Y., Gao, L., and Zhang, X. (2022). Blind detection of circular image rotation angle based on ensemble transfer regression and fused HOG. Front. Neurorobot., 16.","DOI":"10.3389\/fnbot.2022.1037381"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Szczuko, P. (2017, January 20\u201322). ANN for human pose estimation in low resolution depth images. Proceedings of the 2017 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, Poland.","DOI":"10.23919\/SPA.2017.8166892"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Szczuko, P. (2018, January 4\u20136). CNN architectures for human pose estimation from a very low resolution depth image. Proceedings of the 2018 11th International Conference on Human System Interaction (HSI), Gdansk, Poland.","DOI":"10.1109\/HSI.2018.8431338"},{"key":"ref_34","unstructured":"Szczuko, P. (2025, October 25). Very Low Resolution Depth Images of 200,000 Poses\u2013Open Repository. Available online: https:\/\/github.com\/szczuko\/poses."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"102525","DOI":"10.1016\/j.media.2022.102525","article-title":"Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room","volume":"80","author":"Srivastav","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_36","unstructured":"Srivastav, V., Issenhuth, T., Kadkhodamohammadi, A., de Mathelin, M., Gangi, A., and Padoy, N. (2018). MVOR: A multi-view RGB-D operating room dataset for 2D and 3D human pose estimation. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Srivastav, V., Gangi, A., and Padoy, N. (2020). Self-supervision on unlabelled OR data for multi-person 2D\/3D human pose estimation. Lecture Notes in Computer Science, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Lima, Peru, 4\u20138 October 2020, Springer.","DOI":"10.1007\/978-3-030-59710-8_74"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1007\/s00138-016-0792-4","article-title":"Parsing human skeletons in an operating room","volume":"27","author":"Belagiannis","year":"2016","journal-title":"Mach. Vis. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"29357","DOI":"10.1007\/s11042-019-7433-7","article-title":"Deep neural networks for human pose estimation from a very low resolution depth image","volume":"78","author":"Szczuko","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_40","unstructured":"Cloudinary (2024). Techniques for Image Enhancement with Cloudinary: A Primer, Cloudinary."},{"key":"ref_41","unstructured":"Bradski, G., and The OpenCV Team (2025, September 14). OpenCV: Open Source Computer Vision Library. Available online: https:\/\/opencv.org\/."},{"key":"ref_42","unstructured":"Dong, C., Loy, C.C., and Tang, X. (2016). Accelerating the super-resolution convolutional neural network. Computer Vision\u2014Proceedings of the ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11\u201314 October 2016, Springer. Proceedings, Part II 14."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (2016, January 27\u201330). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., and Lee, K.M. (2017, January 21\u201326). Enhanced deep residual networks for single image super-resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Agustsson, E., and Timofte, R. (2017, January 21\u201326). NTIRE 2017 challenge on single image super-resolution: Dataset and study. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref_46","unstructured":"Reidy, L. (2025, October 25). Rotate Images Function in Python. Available online: https:\/\/gist.github.com\/leonardreidy\/2dcca95a7c14b485dcee06792c6f14e9."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Szeliski, R. (2022). Computer Vision: Algorithms and Applications, Springer Nature.","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.3390\/make5040081","article-title":"Human pose estimation using deep learning: A systematic literature review","volume":"5","author":"Samkari","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Yu, B., Fan, Z., Xiang, X., Chen, J., and Huang, D. (2024). Universal Image Restoration with Text Prompt Diffusion. Sensors, 24.","DOI":"10.3390\/s24123917"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Su, Y., Chen, D., Xing, M., Oh, C., Liu, X., and Li, J. (2025, January 16\u201322). Coming Out of the Dark: Human Pose Estimation in Low-light Conditions. Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI), Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2025\/210"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Yoon, J.h., and Kwon, S.k. (2025). Robust Human Pose Estimation Method for Body-to-Body Occlusion Using RGB-D Fusion Neural Network. Appl. Sci., 15.","DOI":"10.3390\/app15158746"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Zhang, Z., and Shin, S.Y. (2025). Two-Dimensional Human Pose Estimation with Deep Learning: A Review. Appl. Sci., 15.","DOI":"10.3390\/app15137344"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Kareem, I., Ali, S.F., Bilal, M., and Hanif, M.S. (2024). Exploiting the features of deep residual network with SVM classifier for human posture recognition. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0314959"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1049\/ipr2.12667","article-title":"Fall detection based on OpenPose and MobileNetV2 network","volume":"17","author":"Gao","year":"2023","journal-title":"IET Image Process."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/970\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T05:19:47Z","timestamp":1762924787000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":54,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["info16110970"],"URL":"https:\/\/doi.org\/10.3390\/info16110970","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2025,11,10]]}}}