{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T11:52:42Z","timestamp":1791201162210,"version":"4.2.0"},"reference-count":26,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T00:00:00Z","timestamp":1790985600000},"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>Accurate bidirectional people counting at room entrances is essential for reliable occupancy estimation, yet radar-based methods remain challenged when reflections from multiple individuals temporarily merge or when people move simultaneously in opposite directions. This study presents a hybrid event-based method for bidirectional people counting using a single 77 GHz multiple-input multiple-output frequency-modulated continuous-wave radar. Unlike conventional tracking-based approaches, the proposed method treats a complete doorway passage as one event and does not require continuous individual trajectories or frame-to-frame data association. Each event is represented as a sequence of three-dimensional point clouds with radial velocity information. A PointNet encoder extracts frame-level spatial representations, a bidirectional gated recurrent unit models their temporal evolution, and an attention mechanism emphasizes the most informative event phases. Separate output heads estimate the numbers of entering and exiting individuals, while an auxiliary head identifies the event type. Predictions are accepted using explicit confidence and geometric-consistency criteria. The primary dataset comprised 550 labeled events and an additional 100 events recorded in five continuous sequences. In the held-out test session, entry- and exit-count accuracies were 95.5% and 94.5%, respectively, while joint entry\u2013exit count accuracy reached 92.7%. The mean absolute error in occupancy change was 0.06 person per event, and the mean absolute occupancy error across the continuous sequences was 0.10 person. The proposed method exceeded geometric rules and density-based clustering combined with tracking in joint count accuracy by 37.2 and 24.5 percentage points, respectively. On an independent laboratory dataset comprising 100 events, the model achieved a joint count accuracy of 91.0% without retraining, fine-tuning, or parameter adaptation, providing preliminary evidence of cross-environment generalization.<\/jats:p>","DOI":"10.3390\/s26196270","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T10:57:46Z","timestamp":1791197866000},"page":"6270","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Event-Based Bidirectional People Counting Using a Spatiotemporal Neural Network and a Single 77 GHz MIMO FMCW Radar"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6313-030X","authenticated-orcid":false,"given":"Anna","family":"\u015alesicka","sequence":"first","affiliation":[{"name":"Department of Navigation, Faculty of Navigation and Logistics, Polish Air Force University, 08-521 D\u0119blin, Poland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3930-7504","authenticated-orcid":false,"given":"Adam","family":"Kawalec","sequence":"additional","affiliation":[{"name":"Faculty of Mechatronics, Armament, and Aerospace, Military University of Technology, 00-908 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0857-1081","authenticated-orcid":false,"given":"B\u0142a\u017cej","family":"\u015alesicki","sequence":"additional","affiliation":[{"name":"Department of Avionics and Control Systems, Faculty of Aviation Division, Polish Air Force University, 08-521 D\u0119blin, Poland"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109965","DOI":"10.1016\/j.enbuild.2020.109965","article-title":"A review of building occupancy measurement systems","volume":"216","author":"Sun","year":"2020","journal-title":"Energy Build."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"121594","DOI":"10.1016\/j.apenergy.2023.121594","article-title":"Adopting occupancy-based HVAC controls in commercial building energy codes: Analysis of cost-effectiveness and decarbonization potential","volume":"349","author":"Pang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1109\/TPAMI.2020.3013269","article-title":"NWPU-Crowd: A large-scale benchmark for crowd counting and localization","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MCOM.2019.1800611","article-title":"Toward understanding crowd mobility in smart cities through the Internet of Things","volume":"57","author":"Solmaz","year":"2019","journal-title":"IEEE Commun. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Raykov, Y.P., Ozer, E., Dasika, G., Boukouvalas, A., and Little, M.A. (2016, January 12\u201316). Predicting room occupancy with a single passive infrared (PIR) sensor through behavior extraction. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany.","DOI":"10.1145\/2971648.2971746"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Matuska, S., Machaj, J., Hudec, R., and Kamencay, P. (2022). An improved IoT-based system for detecting the number of people and their distribution in a classroom. Sensors, 22.","DOI":"10.3390\/s22207912"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1109\/JIOT.2022.3201877","article-title":"Building occupancy detection and localization using CCTV camera and deep learning","volume":"10","author":"Hu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kraft, M., Aszkowski, P., Pieczy\u0144ski, D., and Fularz, M. (2021). Low-cost thermal camera-based counting occupancy meter facilitating energy saving in smart buildings. Energies, 14.","DOI":"10.3390\/en14154542"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1016\/j.buildenv.2017.07.027","article-title":"Predicting occupancy counts using physical and statistical CO2-based modeling methodologies","volume":"123","author":"Zuraimi","year":"2017","journal-title":"Build. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.buildenv.2019.05.015","article-title":"Inferring occupant counts from Wi-Fi data in buildings through machine learning","volume":"158","author":"Wang","year":"2019","journal-title":"Build. Environ."},{"key":"ref_11","unstructured":"Jankiraman, M. (2018). FMCW Radar Design, Artech House."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Knudde, N., Vandersmissen, B., Parashar, K., Couckuyt, I., Jalalvand, A., Bourdoux, A., De Neve, W., and Dhaene, T. (2017, January 11\u201313). Indoor tracking of multiple persons with a 77 GHz MIMO FMCW radar. Proceedings of the 2017 European Radar Conference (EURAD), Nuremberg, Germany.","DOI":"10.23919\/EURAD.2017.8249147"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7283","DOI":"10.1109\/JSEN.2019.2914365","article-title":"Human target detection, tracking, and classification using 24-GHz FMCW radar","volume":"19","author":"Will","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3726","DOI":"10.1109\/JSEN.2022.3141202","article-title":"Radar-based robust people tracking and consumer applications","volume":"22","author":"Ninos","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"27559","DOI":"10.1109\/JSEN.2023.3319030","article-title":"A bi-direction people counting method based on multiscale clustering and multiple extended target tracking using MIMO radar","volume":"23","author":"Yang","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"14745","DOI":"10.1109\/JSEN.2025.3609465","article-title":"Bi-directional people counting exploiting door open\u2013close discrimination using 4-D millimeter-wave radar","volume":"26","author":"Yang","year":"2026","journal-title":"IEEE Sens. J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"20107","DOI":"10.1109\/JIOT.2023.3282797","article-title":"Grouped people counting using mm-wave FMCW MIMO radar","volume":"10","author":"Ren","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1298","DOI":"10.1109\/TRS.2025.3609436","article-title":"Grouped target tracking and seamless people counting with a 24-GHz MIMO FMCW","volume":"3","author":"Wang","year":"2025","journal-title":"IEEE Trans. Radar Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7715","DOI":"10.1109\/JIOT.2021.3113671","article-title":"Deep learning approach for radar-based people counting","volume":"9","author":"Choi","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aydogdu, C.Y., Hazra, S., Santra, A., and Weigel, R. (May, January 27). Multi-modal cross learning for improved people counting using short-range FMCW radar. Proceedings of the 2020 IEEE International Radar Conference (RADAR), Washington, DC, USA.","DOI":"10.1109\/RADAR42522.2020.9114871"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5108418","DOI":"10.1109\/TGRS.2023.3305551","article-title":"People flow detection algorithm based on a multiencoder-classifier cotraining architecture for FMCW radar","volume":"61","author":"Cao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cakoni, D., Storrer, L., De Doncker, P., and Horlin, F. (2023, January 6\u201310). Group counting using micro-Doppler signatures from a 77 GHz FMCW radar. Proceedings of the 2023 IEEE International Radar Conference (RADAR), Sydney, Australia.","DOI":"10.1109\/RADAR54928.2023.10371139"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"60846","DOI":"10.1109\/ACCESS.2025.3557317","article-title":"Spiking neural networks for people counting based on FMCW radar","volume":"13","author":"Saez","year":"2025","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, D., Yarovoy, A., and Fioranelli, F. (2025, January 4\u20139). Transformer network for grouped target counting tracking with a 24 GHz MIMO FMCW radar. Proceedings of the 2025 IEEE Radar Conference (RadarConf\u201925), Krak\u00f3w, Poland.","DOI":"10.1109\/RadarConf2559087.2025.11204984"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, N., Li, H., Zahid, A., Tian, Y., and Li, W. (2026). A robust mmWave radar framework for accurate people counting and motion classification. Sensors, 26.","DOI":"10.3390\/s26041289"},{"key":"ref_26","unstructured":"Anteral S.L. (2022). uRAD Automotive HPA v2.0: 77 GHz Radar, Velocity and 3D Positioning, Anteral S.L.. Product Datasheet."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6270\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T10:58:23Z","timestamp":1791197903000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,3]]},"references-count":26,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196270"],"URL":"https:\/\/doi.org\/10.3390\/s26196270","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,3]]}}}