{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T08:43:22Z","timestamp":1791535402950,"version":"4.3.4"},"reference-count":31,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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>Capturing kinematic data in outdoor sports is challenging, as motions span large capture volumes and occur under difficult environmental conditions. Video-based approaches, particularly with pan\u2013tilt\u2013zoom cameras, offer a practical solution, but the extensive manual post-processing required limits their use to short sequences and few athletes. This study presents a motion capture pipeline that automates the detection of both reference points and sport-specific keypoints to overcome this limitation. The field test employed eight cameras covering a 250\u00d780\u00d730\u00a0m capture volume with nearly 300 reference points. Ten state-certified ski instructors performed eight standardized maneuvers. Reference points were localized through a hybrid approach combining YOLO object detection and ArUco marker identification. AlphaPose was fine-tuned on a new manually annotated dataset to detect skier-specific keypoints (e.g., skis, poles) alongside anatomical landmarks. Continuous frame-wise calibration and 3D reconstruction were performed using Direct Linear Transformation. Evaluation compared automated detections with manual annotations. Automated reference point detection achieved a mean localization error of 4.1 pixels (0.1% of 4K width) and reduced 3D segment-length variation by 23%. The skier-specific keypoint model reached 98% PCK, mAP of 0.97, and an MPJPE of 10.3 pixels while lowering 3D segment-length variation by 0.5\u00a0cm compared to manual digitization and 0.6\u00a0cm relative to a pretrained model. Replacing manual digitization with automated detection improves accuracy and facilitates kinematic data collection in large outdoor fields with many athletes and trials. The approach also enables the creation of sport-specific datasets valuable for biomechanical research and training next-generation 3D pose estimation models.<\/jats:p>","DOI":"10.3390\/s26061951","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:44:41Z","timestamp":1773999881000},"page":"1951","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Outdoor Motion Capture at Scale"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0869-2862","authenticated-orcid":false,"given":"Michael","family":"Zw\u00f6lfer","sequence":"first","affiliation":[{"name":"Department of Sport Science, University of Innsbruck, 6020 Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7939-832X","authenticated-orcid":false,"given":"Martin","family":"M\u00f6ssner","sequence":"additional","affiliation":[{"name":"Department of Sport Science, University of Innsbruck, 6020 Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2692-0801","authenticated-orcid":false,"given":"Helge","family":"Rhodin","sequence":"additional","affiliation":[{"name":"Faculty of Technology, Bielefeld University, 33615 Bielefeld, Germany"},{"name":"Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3327-0555","authenticated-orcid":false,"given":"Werner","family":"Nachbauer","sequence":"additional","affiliation":[{"name":"Department of Sport Science, University of Innsbruck, 6020 Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Fasel, B., Sp\u00f6rri, J., Gilgien, M., Boffi, G., Chardonnens, J., M\u00fcller, E., and Aminian, K. (2016). Three-Dimensional Body and Centre of Mass Kinematics in Alpine Ski Racing Using Differential GNSS and Inertial Sensors. Remote Sens., 8.","DOI":"10.3390\/rs8080671"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1109\/JBHI.2017.2659758","article-title":"Joint inertial sensor orientation drift reduction for highly dynamic movements","volume":"22","author":"Fasel","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1080\/02640414.2010.507253","article-title":"Collecting kinematic data on a ski\/snowboard track with panning, tilting, and zooming cameras: Is there sufficient accuracy for a biomechanical analysis?","volume":"28","author":"Klous","year":"2010","journal-title":"J. Sports Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"9821","DOI":"10.3390\/s130809821","article-title":"Determination of external forces in alpine skiing using a differential global navigation satellite system","volume":"13","author":"Gilgien","year":"2013","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1080\/02640414.2014.977934","article-title":"Determination of the centre of mass kinematics in alpine skiing using differential global navigation satellite systems","volume":"33","author":"Gilgien","year":"2015","journal-title":"J. Sports Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sp\u00f6rri, J., Schieferm\u00fcller, C., and M\u00fcller, E. (2016). Collecting Kinematic Data on a Ski Track with Optoelectronic Stereophotogrammetry: A Methodological Study Assessing the Feasibility of Bringing the Biomechanics Lab to the Field. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0161757"},{"key":"ref_7","unstructured":"Qualisys AB (2025, June 15). Qualisys Track Manager (QTM). Available online: https:\/\/www.qualisys.com\/software\/qualisys-track-manager\/."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Adlou, B., Wilburn, C., and Weimar, W. (2025). Motion Capture Technologies for Athletic Performance Enhancement and Injury Risk Assessment: A Review for Multi-Sport Organizations. Sensors, 25.","DOI":"10.3390\/s25144384"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9026","DOI":"10.1038\/s41598-023-35775-4","article-title":"Model-based estimation of muscle and ACL forces during turning maneuvers in alpine skiing","volume":"13","author":"Heinrich","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, B., Liu, Y., and Xiong, C. (2021). Automatic Checkerboard Detection for Robust Camera Calibration. Proceedings of the 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, IEEE.","DOI":"10.1109\/ICME51207.2021.9428389"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., and Lu, C. (2017). RMPE: Regional Multi-person Pose Estimation. Proceedings of the ICCV, 2017, IEEE.","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref_12","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., and Sheikh, Y. (2019). OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chen, H., Feng, R., Wu, S., Ji, S., Yang, B., and Wang, X. (2021). Deep Dual Consecutive Network for Human Pose Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, IEEE.","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., and Malik, J. (2023). Humans in 4D: Reconstructing and Tracking Humans with Transformers. Proceedings of the ICCV, 2023, IEEE.","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, M., Liu, H., Wang, P., Cai, J., and Sebe, N. (2024). Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation. arXiv.","DOI":"10.1109\/CVPR52733.2024.00064"},{"key":"ref_16","unstructured":"Li, J., Bian, S., Xu, C., Chen, Z., Yang, L., and Lu, C. (2023). HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bachmann, R., Sp\u00f6rri, J., Fua, P., and Rhodin, H. (2019). Motion Capture from Pan-Tilt Cameras with Unknown Orientation. Proceedings of the IEEE International Conference on 3D Vision (3DV), 2019, IEEE.","DOI":"10.1109\/3DV.2019.00042"},{"key":"ref_18","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., and Girshick, R. (2025, March 13). Detectron2. Available online: https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., and Auli, M. (2019). 3D human pose estimation in video with temporal convolutions and semi-supervised training. arXiv.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Sp\u00f6rri, J., Katircioglu, I., Constantin, V., Meyer, F., M\u00fcller, E., Salzmann, M., and Fua, P. (2018). Learning monocular 3d human pose estimation from multi-view images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18\u201322 June 2018, IEEE.","DOI":"10.1109\/CVPR.2018.00880"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ostrek, M., Rhodin, H., Fua, P., M\u00fcller, E., and Sp\u00f6rri, J. (2019). Are existing monocular computer vision-based 3D Motion capture approaches ready for deployment? A methodological study on the example of alpine skiing. Sensors, 19.","DOI":"10.3390\/s19194323"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100034","DOI":"10.1016\/j.jsampl.2023.100034","article-title":"Deep learning-based 2D keypoint detection in alpine ski racing\u2014A performance analysis of state-of-the-art algorithms applied to regular skiing and injury situations","volume":"2","author":"Heinrich","year":"2023","journal-title":"JSAMS Plus"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"21465","DOI":"10.1038\/s41598-023-47875-2","article-title":"A graph-based approach can improve keypoint detection of complex poses: A proof-of-concept on injury occurrences in alpine ski racing","volume":"13","author":"Heinrich","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_24","first-page":"120","article-title":"The OpenCV Library","volume":"25","author":"Bradski","year":"2000","journal-title":"DDJ Softw. Tools"},{"key":"ref_25","unstructured":"Skischulverband, \u00d6. (2018). Snowsport Austria: Die \u00d6sterreichische Skischule, \u00d6sterreichischer Skischulverband."},{"key":"ref_26","unstructured":"Ultralytics (2025, March 13). YOLOv8: Advanced Real-Time Object Detection System. Ultralytics YOLO Documentation. Available online: https:\/\/docs.ultralytics.com."},{"key":"ref_27","unstructured":"Abdel-Aziz, Y.I., and Karara, H.M. (1971). Direct Linear Transformation from Comparator Coordinates into Object Space Coordinates in Close-Range Photogrammetry. Proceedings of the Symposium on Close-Range Photogrammetry, American Society of Photogrammetry."},{"key":"ref_28","first-page":"155","article-title":"A method for obtaining 3-D data in alpine skiing using pan and tilt cameras with zoom lenses","volume":"Volume 1266","author":"Mote","year":"1996","journal-title":"Skiing Trauma and Safety"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Winter, D.A. (2009). Biomechanics and Motor Control of Human Movement, John Wiley & Sons. [4th ed.].","DOI":"10.1002\/9780470549148"},{"key":"ref_30","unstructured":"Wandt, B., Ackermann, H., and Rosenhahn, B. (2017). A Kinematic Chain Space for Monocular Motion Capture. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s40798-018-0139-y","article-title":"A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System","volume":"4","author":"Colyer","year":"2018","journal-title":"Sports Med.-Open"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/6\/1951\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:48:54Z","timestamp":1774000134000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/6\/1951"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["s26061951"],"URL":"https:\/\/doi.org\/10.3390\/s26061951","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]}}}