An IoT-Based Real-Time Human Fall Detection and Notification System with Instance Segmentation Deep Learning
Article Sidebar
Main Article Content
บทคัดย่อ
This research presents a person fall detection system based on deep learning using the Instance Image Segmentation technique with the YOLOv11-seg model, which achieves high speed and accuracy in object detection. The developed system aims to individually detect a person's posture in an image, enabling accurate analysis of their falling posture characteristics. And there is a notification in the application to the administrator or relevant person within 10 seconds, allowing quick help. Using a dataset of 10,169 images, 8622 for training, 994 for inspection, and 553 for testing (with a ratio of 85:10:5 for training, inspection, and testing). The system performs impressively by using all 3 YOLOv11-seg models: YOLOv11s-seg, YOLOv11n-seg, and YOLOv11m-seg. The training dataset showed excellent performance with a YOLOv11s-seg model, achieving a precision of 0.966, a recall of 0.910, and an F1 Score of 0.88. The results show that the developed system can detect falls and issue real-time alerts via an IoT-based framework. It improves safety and reduces the risk for the elderly or patients at risk of falling.
Article Details
อนุญาตภายใต้เงื่อนไข Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
เอกสารอ้างอิง
World Health Organization. Falls. https://www.who.int/news-room/fact-sheets/detail/falls (accessed 2026-02-23).
He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask R-CNN. Proc. IEEE Int. Conf. Comput. Vis. 2017, 2980–2988. https://doi.org/10.1109/ICCV.2017.322
Zhang, S.-H.; Li, R.; Dong, X.; Rosin, P. L.; Cai, Z.; Han, X.; Yang, D.; Huang, H.-Z.; Hu, S.-M. Pose2Seg: Detection Free Human Instance Segmentation. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 2019, 8811–8819. https://doi.org/10.1109/CVPR.2019.00902
Lu, N.; Wu, Y.; Feng, L.; Song, J. Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data. IEEE J. Biomed. Health Inf. 2019, 23(1), 314–323. https://doi.org/10.1109/JBHI.2018.2808281
Yao, L.; Yang, W.; Huang, W. A Fall Detection Method Based on a Joint Motion Map Using Double Convolutional Neural Networks. Multimed. Tools Appl. 2022, 81, 4551–4568. https://doi.org/10.1007/s11042-020-09181-1
Su, S.; Wu, S.-S.; Chen, S.-Y.; Duh, D.-J. Multi-view Fall Detection Based on Spatio-temporal Interest Points. Multimed. Tools Appl. 2016, 75, 8469–8492. https://doi.org/10.1007/s11042-015-2766-3
Gao, M.; Li, J.; Zhou, D.; Zhi, Y.; Zhang, M.; Li, B. Fall Detection Based on OpenPose and MobileNetV2 Network. IET Image Process. 2023, 17 (3), 722–732. https://doi.org/10.1049/ipr2.12667
Alam, E.; Sufian, A.; Dutta, P.; Leo, M. Vision-Based Human Fall Detection Systems Using Deep Learning: A Review. Comput. Biol. Med. 2022, 146, 105626. https://doi.org/10.1016/j.compbiomed.2022.105626
Li, L.; Fang, M.; Fu, F. Instance Segmentation Based on Improved YOLACT. Proc. Int. Conf. Virtual Real. Vis. (ICVRV) 2020, 165–170. https://doi.org/10.1109/ICVRV51359.2020.00042
Khanam, R.; Hussain, M. YOLOv11: An Overview of the Key Architectural Enhancements. arXiv 2024, arXiv:2410.17725. https://doi.org/10.48550/arXiv.2410.17725
He, L.; Zhou, Y.; Liu, L.; Ma, J. Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites. Buildings 2024, 14(12), 3777. https://doi.org/10.3390/buildings14123777
Deepa, D.; Sivasangari, A.; Roonwal, R.; Nayan, R. Pothole Detection using Roboflow Convolutional Neural Networks. Proc. 7th Int. Conf. Intell. Comput. Control Syst. (ICICCS) 2023, 560–564. https://doi.org/10.1109/ICICCS56967.2023.10142700
Su-Hren, W.; Chuchit, T.; Kaewpoung, S. Development of an Autonomous EV Navigation System Using Instance Segmentation for Medical Supply Delivery. Proc. 13th Int. Electr. Eng. Congr. (iEECON) 2025, 1–6. https://doi.org/10.1109/iEECON64081.2025.10987580
Babila, I. F. E.; Villasor, S. A. E.; Dela Cruz, J. C. Object Detection for Inventory Stock Counting Using YOLOv5. Proc. IEEE 18th Int. Colloq. Signal Process. Appl. (CSPA) 2022, 304–309. https://doi.org/10.1109/CSPA55076.2022.9782028
Mostafa, M.; Sadi, S.; Anamika, S. A.; Hussain, M. S.; Khan, R. Automatic Vehicle Classification and Speed Tracking. Proc. 2nd Int. Conf. Appl. Artif. Intell. Comput. (ICAAIC) 2023, 972–977. https://doi.org/10.1109/ICAAIC56838.2023.10140935
Pornpanomchai, C. Image Based Papaya (Carica papaya Linn.) Seed Germination Evaluation by ResNet50. ASEAN J. Sci. Technol. Rep. 2025, 28 (1), e254804. https://doi.org/10.55164/ajstr.v25i1.245292
Elaanba, A.; Ridouani, M.; Hassouni, L. Automatic Detection Using Deep Convolutional Neural Networks for Abnormal Positioning of Tubes and Catheters in Chest X-ray Images. Proc. IEEE World AI IoT Congr. (AIIoT) 2021, 7–12. https://doi.org/10.1109/AIIoT52608.2021.9454205
Ahmed, S.; Rahman, M. J.; Razzak, M. A. Design and Development of an IoT-Based LPG Gas Leakage Detector for Households and Industries. Proc. IEEE World AI IoT Congr. (AIIoT) 2023, 762–767. https://doi.org/10.1109/AIIoT58121.2023.10174377
Karar, M. E.; Shehata, H. I.; Reyad, O. A Survey of IoT-Based Fall Detection for Aiding Elderly Care: Sensors, Methods, Challenges and Future Trends. Appl. Sci. 2022, 12(7), 3276. https://doi.org/10.3390/app12073276
Mrozek, D.; Koczur, A.; Małysiak-Mrozek, B. Fall Detection in Older Adults with Mobile IoT Devices and Machine Learning in the Cloud and on the Edge. Inf. Sci. 2020, 537, 132–147. https://doi.org/10.1016/j.ins.2020.05.070
Yacchirema, D.; de Puga, J. S.; Palau, C.; Esteve, M. Fall Detection System for Elderly People Using IoT and Ensemble Machine Learning Algorithm. Pers. Ubiquitous Comput. 2019, 23, 801–817. https://doi.org/10.1007/s00779-018-01196-8
Stanivuk, I.; Bjelić, V.; Samardžić, T.; Simić, Đ. Expanding Lua Interface to Support HTTP/HTTPS Protocol. Proc. 13th Int. Conf. Adv. Technol., Syst. Serv. Telecommun. (TELSIKS) 2017, 407–410. https://doi.org/10.1109/TELSKS.2017.8246311
Rougier, C.; Meunier, J.; St-Arnaud, A.; Rousseau, J. Fall Detection from Human Shape and Motion History Using Video Surveillance. Proc. 21st Int. Conf. Adv. Inf. Netw. Appl. Workshops (AINAW) 2007, 875–880. https://doi.org/10.1109/AINAW.2007.181
Mubashir, M.; Shao, L.; Seed, L. A Survey on Fall Detection: Principles and Approaches. Neurocomputing 2013, 100, 144–152. https://doi.org/10.1016/j.neucom.2011.09.037
Noury, N.; Fleury, A.; Rumeau, P.; Bourke, A. K.; Laighin, G. O.; Rialle, V.; Lundy, J. E. Fall Detection – Principles and Methods. Proc. 29th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBS) 2007, 1663–1666. https://doi.org/10.1109/IEMBS.2007.4352627
Cao, Z.; Simon, T.; Wei, S.-E.; Sheikh, Y. Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) 2017, 1302–1310. https://doi.org/10.1109/CVPR.2017.143
Yang, G.; Zhao, J.; Guo, J. Research on Fall Detection Algorithm Based on CNN and LSTM. Proc. 3rd Int. Conf. Nat. Lang. Process. (ICNLP) 2021, 190–195.
