{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T19:24:29Z","timestamp":1764962669815,"version":"3.46.0"},"reference-count":37,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hubei emergency management department","award":["SJZX20230907"],"award-info":[{"award-number":["SJZX20230907"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Campus stairwells, characterized by their crowded nature during certain short periods of time, present a high risk for falls that can lead to dangerous stampedes. Accurate fall detection is crucial for preventing such accidents. However, existing research lacks a detection model that balances high precision with lightweight design and lacks on-site experimental validation to assess practical feasibility. This study addresses these gaps by proposing an enhanced fall recognition model based on YOLOv7, validated through on-site experiments. A dataset on campus stairwell falls was established, capturing diverse stairwell personnel behaviors. Four YOLOv7 improvement schemes were proposed, and numerical comparison experiments identified the best-performing model, combining DO-DConv and Slim-Neck modules. This model achieved an average precision (mAP) of 88.1%, 2.41% higher than the traditional YOLOv7, while reducing GFLOPs from 105.2 to 38.2 and cutting training time by 4 h. A field experiment conducted with 22 groups of participants under small-scale populations and varying lighting conditions preliminarily confirmed that the model\u2019s accuracy is within an acceptable range. The experimental results also analyzed the changes in detection confidence across different population sizes and lighting conditions, offering valuable insights for further model improvement and its practical applications.<\/jats:p>","DOI":"10.3390\/s25237394","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:42:02Z","timestamp":1764960122000},"page":"7394","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancements and On-Site Experimental Study on Fall Detection Algorithm for Students in Campus Staircase"],"prefix":"10.3390","volume":"25","author":[{"given":"Ying","family":"Lu","sequence":"first","affiliation":[{"name":"College of Resources and Environmental Engineering, Wuhan University of Science and Technology, Wuhan 430081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuze","family":"Cui","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Engineering, Wuhan University of Science and Technology, Wuhan 430081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yan","sequence":"additional","affiliation":[{"name":"Hubei Chemical Safety Association, Wuhan 430060, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4476","DOI":"10.1109\/TITS.2018.2886415","article-title":"Optimization of crowd evacuation with leaders in urban rail transit stations","volume":"20","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1016\/j.physa.2015.10.091","article-title":"Modeling, simulation and analysis of group trampling risks during escalator transfers","volume":"444","author":"Li","year":"2016","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"129002","DOI":"10.1016\/j.physa.2023.129002","article-title":"An extended model for crowd evacuation considering crowding and stampede effects under the internal crushing","volume":"625","author":"Chen","year":"2023","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/s11069-017-2785-7","article-title":"The occurrence laws of campus stampede accidents in China and its prevention and control measures","volume":"87","author":"Zhang","year":"2017","journal-title":"Nat. Hazards"},{"key":"ref_5","first-page":"22","article-title":"Study on campus stampede causes and prevention based on 24Model-AHP","volume":"43","author":"Ma","year":"2022","journal-title":"Safety"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Xie, K., Song, Y., Liu, J., Liang, B., and Liu, X. (2018). Stampede Prevention Design of Primary School Buildings in China: A Sustainable Built Environment Perspective. Int. J. Environ. Res. Public Health, 15.","DOI":"10.3390\/ijerph15071517"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Alam, E., Sufian, A., Dutta, P., and Leo, M. (2022). Vision-based human fall detection systems using deep learning: A review. Comput. Biol. Med., 146.","DOI":"10.1016\/j.compbiomed.2022.105626"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lin, H.-C., Chen, M.-J., Lee, C.-H., Kung, L.-C., and Huang, J.-T. (2023). Fall recognition based on an IMU wearable device and fall verification through a smart speaker and the IoT. Sensors, 23.","DOI":"10.3390\/s23125472"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yan, J., Wang, X., Shi, J., and Hu, S. (2023). Skeleton-based fall detection with multiple inertial sensors using spatial-temporal graph convolutional networks. Sensors, 23.","DOI":"10.3390\/s23042153"},{"key":"ref_10","first-page":"8826088","article-title":"Human falling detection algorithm based on multisensor data fusion with SVM. Mob","volume":"2020","author":"Pan","year":"2020","journal-title":"Inf. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, B., Ni, X., Zhao, G., Ma, Y., Gao, X., Li, H., Xiong, C., Wang, L., and Liang, S. (2017, January 11\u201315). A wearable action recognition system based on acceleration and attitude angles using real-time detection algorithm. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju Island, Republic of Korea.","DOI":"10.1109\/EMBC.2017.8037336"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.1049\/ipr2.12208","article-title":"Falling motion detection algorithm based on deep learning","volume":"16","author":"Zhu","year":"2022","journal-title":"IET Image Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/JBHI.2014.2304357","article-title":"Depth-Based Human Fall Detection via Shape Features and Improved Extreme Learning Machine","volume":"18","author":"Ma","year":"2014","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_14","unstructured":"Medel, J.R., and Savakis, A. (2016). Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., and Shah, M. (2018, January 18\u201323). Real-World Anomaly Detection in Surveillance Videos. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref_16","first-page":"4","article-title":"Sistema de detecci\u00f3n de ca\u00eddas en personas utilizando v\u00eddeo vigilancia","volume":"28","year":"2024","journal-title":"Ingeniare. Rev. Chil. De Ing."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yu, F., Gao, S., Chang, C., and Zhang, X. (2022). Experimental and Numerical Study on Rapid Evacuation Characteristics of Staircases in Campus Buildings. Buildings, 12.","DOI":"10.3390\/buildings12060848"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bertram, J., Kr\u00fcger, T., R\u00f6hling, H.M., Jelusic, A., Mansow-Model, S., Schniepp, R., Wuehr, M., and Otte, K. (2023). Accuracy and repeatability of the Microsoft Azure Kinect for clinical measurement of motor function. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0279697"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kan, X., Zhu, S., Zhang, Y., and Qian, C. (2023). A Lightweight Human Fall Detection Network. Sensors, 23.","DOI":"10.3390\/s23229069"},{"key":"ref_20","first-page":"65","article-title":"Research on artificial intelligence early warning and diversion system for campus crowding and stampede accidents","volume":"47","author":"Xu","year":"2021","journal-title":"Informatiz. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s11554-022-01201-7","article-title":"SlimYOLOv4: Lightweight object detector based on YOLOv4","volume":"19","author":"Ding","year":"2022","journal-title":"J. Real-Time Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"177111","DOI":"10.1109\/ACCESS.2025.3620430","article-title":"HyperFallNet: Human Fall Detection in Real-Time Using YOLOv13 with Hypergraph-Enhanced Correlation Learning","volume":"13","author":"Sanjalawe","year":"2025","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"41336","DOI":"10.1109\/ACCESS.2025.3547914","article-title":"Hybrid Deep Learning for Human Fall Detection: A Synergistic Approach Using YOLOv8 and Time-Space Transformers","volume":"13","author":"Sanjalawe","year":"2025","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4135","DOI":"10.1109\/ACCESS.2018.2887144","article-title":"Fall Detection in Videos with Trajectory-Weighted Deep-Convolutional Rank-Pooling Descriptor","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3058","DOI":"10.1109\/JSEN.2023.3334555","article-title":"A novel fall detection framework with age estimation based on cloud-fog computing architecture","volume":"24","author":"Lin","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, C., Wang, Y., and Liu, X. (2023). An Improved YOLOv7 Lightweight Detection Algorithm for Obscured Pedestrians. Sensors, 23.","DOI":"10.3390\/s23135912"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5155970","DOI":"10.1155\/2022\/5155970","article-title":"Little-YOLOv4: A Lightweight Pedestrian Detection Network Based on YOLOv4 and GhostNet","volume":"2022","author":"Zheng","year":"2022","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Chen, Y., Wang, Z., Shan, H., Chen, Y., and Zhang, Y. (2025, January 11\u201315). Patient-level anatomy meets scanning-level physics: Personalized federated low-dose ct denoising empowered by large language model. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00486"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.patcog.2011.04.017","article-title":"Slip and fall event detection using Bayesian Belief Network","volume":"45","author":"Liao","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1007\/s11760-025-04179-4","article-title":"DBF-YOLO: A fall detection algorithm for complex scenes","volume":"19","author":"Wang","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_31","unstructured":"Schneider, D., Marinov, Z., Baur, R., Zhong, Z., D\u00fcger, R., and Stiefelhagen, R. (2025). OmniFall: A Unified Staged-to-Wild Benchmark for Human Fall Detection. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 20\u201325). Coordinate attention for efficient mobile network design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., and Hu, Z. (2023). Improved YOLOv7 for small object detection algorithm based on attention and dynamic convolution. Appl. Sci., 13.","DOI":"10.3390\/app13169316"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zheng, J., Wu, H., Zhang, H., Wang, Z., and Xu, W. (2022). Insulator-defect detection algorithm based on improved YOLOv7. Sensors, 22.","DOI":"10.3390\/s22228801"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3726","DOI":"10.1109\/TIP.2022.3175432","article-title":"DO-Conv: Depthwise Over-Parameterized Convolutional Layer","volume":"31","author":"Cao","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","unstructured":"Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., and Ren, Q. (2022). Slim-neck by GSConv: A better design paradigm of detector ar-chitectures for autonomous vehicles. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yu, M., Wan, Q., Tian, S., Hou, Y., Wang, Y., and Zhao, J. (2022). Equipment Identification and Localization Method Based on Improved YOLOv5s Model for Production Line. Sensors, 22.","DOI":"10.3390\/s222410011"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/23\/7394\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:54:19Z","timestamp":1764960859000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/23\/7394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":37,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["s25237394"],"URL":"https:\/\/doi.org\/10.3390\/s25237394","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}