{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:54:50Z","timestamp":1785430490459,"version":"3.56.0"},"reference-count":38,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"MultiChoice Chair in Machine Learning at the University of Pretoria, South Africa"},{"id":[{"id":"https:\/\/ror.org\/00g0p6g84","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents a multimodal sensing approach for fine-grained soccer action recognition using synchronized mm-wave FMCW radar and multiview RGB cameras. A TI IWR1443BOOST FMCW radar and three Sony IMX296 global-shutter cameras were used to record seven soccer-related actions in different movement directions in an outdoor environment. Range\u2013Doppler radar processing is applied to extract global mel features and CFAR-localized block representations of mel and radar spectrogram features to capture both coarse and fine micro-Doppler characteristics. Camera features are derived from bounding box, HOG, optical flow, and pose estimations. Classification is performed using logistic regression as the classical model and various deep models. Performance is evaluated using cross-validation. Radar alone achieved moderate performance (0.897 F1macro using TCN), successfully identifying coarse motion but showing limited separability for dribbling-based actions. Camera-only models achieve near-perfect accuracy (\u22650.997 F1macro using 1D-CNN), with the confusion matrices being nearly perfectly diagonal already. The best performance is obtained from a cross-modal transformer with multiple cameras (0.998 F1macro). These results demonstrate that a camera by itself performs strongly for the action recognition task but also that radar\u2013camera fusion can improve robustness and enhance the discrimination of finer soccer player movements for outdoor analytics and player monitoring applications.<\/jats:p>","DOI":"10.3390\/s26082532","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:01:22Z","timestamp":1776686482000},"page":"2532","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Recognition of Soccer Player Actions Using a Synchronized Multi-Camera and mm-Wave Radar Platform"],"prefix":"10.3390","volume":"26","author":[{"given":"Dani\u00ebl Benjamin","family":"Keyter","sequence":"first","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Pretoria, Hatfield 0028, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2506-6594","authenticated-orcid":false,"given":"Johan Pieter","family":"de Villiers","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Pretoria, Hatfield 0028, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1831","DOI":"10.1109\/LGRS.2014.2311819","article-title":"Application of Linear Predictive Coding for Human Activity Classification Based on Micro-Doppler Signatures","volume":"11","author":"Javier","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1109\/LGRS.2015.2452946","article-title":"Micro-Doppler-Based Human Activity Classification Using the Mote-Scale BumbleBee Radar","volume":"12","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Peng, Y., Wang, J., and Lei, P. (2019, January 11\u201313). Human Motion Recognition Based on Radar Micro-Doppler Features Using Bayesian Network. Proceedings of the 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Chongqing, China.","DOI":"10.1109\/ICSIDP47821.2019.9173502"},{"key":"ref_4","unstructured":"Carnegie Mellon Graphics Lab (2025, November 16). Carnegie Mellon University Motion Capture Database. Available online: http:\/\/mocap.cs.cmu.edu\/."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chae, R., Wang, A., and Li, C. (2019, January 20\u201323). FMCW Radar Driver Head Motion Monitoring Based on Doppler Spectrogram and Range-Doppler Evolution. Proceedings of the 2019 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet), Orlando, FL, USA.","DOI":"10.1109\/WISNET.2019.8711807"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lin, Y., Li, H., and Faccio, D. (2024). Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet. Sensors, 24.","DOI":"10.3390\/s24165450"},{"key":"ref_7","first-page":"1","article-title":"Micro-Doppler radar classification of humans and animals in an operational environment","volume":"102","author":"Berndt","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sch\u00fcldt, C., Laptev, I., and Caputo, B. (2004, January 23\u201326). Recognizing Human Actions: A Local SVM Approach. Proceedings of the 17th International Conference on Pattern Recognition (ICPR), Cambridge, UK.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1109\/TIFS.2013.2258152","article-title":"Attribute Regularization Based Human Action Recognition","volume":"8","author":"Zhang","year":"2013","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Niebles, J.C., Chen, C.W., and Li, F.-F. (2010, January 5\u201311). Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification. Proceedings of the European Conference on Computer Vision (ECCV), Crete, Greece.","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Benitez-Garcia, G., Olivares-Mercado, J., Sanchez-Perez, G., and Yanai, K. (2021, January 10\u201315). IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition. Proceedings of the 25th International Conference on Pattern Recognition, (ICPR 2020), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412317"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Le, V.D., Nghiem, T.L., and Le, T.L. (November, January 31). Accurate continuous action and gesture recognition method based on skeleton and sliding windows techniques. Proceedings of the 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Taipei, Taiwan.","DOI":"10.1109\/APSIPAASC58517.2023.10317368"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Jeon, M., and Woo, S. (2026). A Lightweight Radar\u2013Camera Fusion Deep Learning Model for Human Activity Recognition. Sensors, 26.","DOI":"10.3390\/s26030894"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"45610","DOI":"10.1109\/JIOT.2025.3600817","article-title":"M2FM: A Multimodal Fusion Model for Human Action Recognition With Camera and Millimeter-Wave Radar","volume":"12","author":"Yi","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Keyter, D., and de Villiers, P. (2025, January 7\u201311). Feature Analysis in Camera and Mm-Wave Radar Fusion for Soccer Player Action Recognition. Proceedings of the 2025 28th International Conference on Information Fusion (FUSION), Rio de Janeiro, Brazil.","DOI":"10.23919\/FUSION65864.2025.11124142"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6469","DOI":"10.1109\/JSEN.2023.3348199","article-title":"mmPose-FK: A Forward Kinematics Approach to Dynamic Skeletal Pose Estimation Using mmWave Radars","volume":"24","author":"Hu","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rivas-Caicedo, J.L., Salda\u00f1a-Aristizabal, L., Ni\u00f1o-Tejada, K., and Patarroyo-Montenegro, J.F. (2025). A Multi-Sensor Dataset for Human Activity Recognition Using Inertial and Orientation Data. Data, 10.","DOI":"10.3390\/data10080129"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1109\/TMTT.2025.3630829","article-title":"Setup-Independent Quadrature Imbalance Calibration for Microwave and Millimeter-Wave Doppler Radars","volume":"74","author":"Cardillo","year":"2026","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Richards, M.A., Holm, W.A., and Scheer, J. (2010). Principles of Modern Radar: Basic Principles, SciTech Publishing. [1st ed.].","DOI":"10.1049\/SBRA021E"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1121\/1.1915893","article-title":"A Scale for the Measurement of the Psychological Magnitude Pitch","volume":"8","author":"Stevens","year":"1937","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_22","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLOv8, Ultralytics."},{"key":"ref_23","first-page":"122","article-title":"The OpenCV Library","volume":"120","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s J. Softw. Tools"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M., and Kautz, J. (2017). PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume. arXiv.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"130210","DOI":"10.1016\/j.neucom.2025.130210","article-title":"A review of transformer-based human pose estimation: Delving into the relation modeling","volume":"639","author":"Wei","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_26","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201325). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_27","unstructured":"Bigun, J., and Gustavsson, T. (2003). Two-Frame Motion Estimation Based on Polynomial Expansion. Proceedings of the Image Analysis, Springer."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","article-title":"Principal components analysis (PCA)","volume":"19","author":"Ratajczak","year":"1993","journal-title":"Comput. Geosci."},{"key":"ref_29","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","first-page":"191","article-title":"Ridge Estimators in Logistic Regression","volume":"41","author":"Cessie","year":"1992","journal-title":"J. R. Stat. Soc. Ser. C (Appl. Stat.)"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks","volume":"63","author":"Kiranyaz","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_34","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv."},{"key":"ref_35","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2023). Attention Is All You Need. arXiv."},{"key":"ref_36","unstructured":"Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv."},{"key":"ref_37","unstructured":"Loshchilov, I., and Hutter, F. (2017). SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv."},{"key":"ref_38","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2532\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:03:48Z","timestamp":1776686628000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":38,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26082532"],"URL":"https:\/\/doi.org\/10.3390\/s26082532","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}