An Efficient Fall Detector Using Improvement of the YOLOv12n Via ONA-Net
Abstract
Meningkatnya permintaan akan sistem deteksi jatuh yang andal dalam pemantauan perawatan pasien sekaligus membantu lingkungan kehidupan mendorong pengembangan model visi komputer yang mampu mengidentifikasi kejadian jatuh secara akurat dalam kondisi dunia nyata. Sistem ini harus mendeteksi perubahan postur tubuh manusia di berbagai posisi sambil mempertahankan ketahanan terhadap latar belakang yang kompleks, yang seringkali mengurangi akurasi deteksi. Selain itu, penerapan di dunia nyata membutuhkan model yang beroperasi secara efisien pada perangkat berbiaya rendah dan memproses aliran video langsung secara real-time. Studi ini menganalisis efektivitas peningkatan versi nano dari arsitektur YOLOv12 untuk deteksi jatuh dengan mengintegrasikan mekanisme ONA-Net. Modul yang diusulkan memungkinkan jaringan untuk fokus pada beberapa respons penting yang terkait dengan postur tubuh manusia, memungkinkan model untuk menangkap isyarat spasial yang terkait dengan kejadian jatuh dengan lebih baik. Desain yang ringan mengurangi beban komputasi sambil mempertahankan ekstraksi fitur yang efektif untuk deteksi yang akurat. Temuan eksperimental menunjukkan YOLOv12-ONA-Net sebagai model yang diperkenalkan memperoleh kinerja deteksi yang kuat, dengan memperoleh 92,3% mAP@50 dan 59,7% mAP@50:95. Meskipun arsitekturnya ringan, model ini tetap mempertahankan efisiensi praktis dengan mencapai kecepatan inferensi 13,13 frame per detik (FPS). Hasil ini menunjukkan bahwa penggabungan ONA-Net ke dalam jaringan YOLOv12n meningkatkan kemampuan deteksi jatuh sekaligus mempertahankan penggunaan komputasi yang sesuai untuk penggunaan pemantauan waktu nyata pada perangkat dengan kapasitas komputasi terbatas.
Keywords
Fall Detection; YOLOv12n; ONA-Net; Real-time object detection; Deep Learning
Full Text:
PDFReferences
N. T. Newaz and E. Hanada, “The methods of fall detection: A literature review,” Sensors, vol. 23, no. 11, p. 5212, 2023. doi: 10.3390/s23115212.
J. Gutiérrez, V. Rodríguez, and S. Martin, “Comprehensive review of vision-based fall detection systems,” Sensors, vol. 21, no. 3, p. 947, 2021. doi: 10.3390/s21030947.
S. Kumar et al, “Falls among older adults: An exploration of trends, clinical outcomes, predisposing risk factors, and intervention strategies,” The American Journal of Surgery, vol. 245, p. 116385, 2025. doi: 10.1016/j.amjsurg.2025.116385
B. Chen et al., “Computer vision and machine learning-based gait pattern recognition for flat fall prediction,” Sensors, vol. 22, no. 20, p. 7960, 2022. doi: 10.3390/s22207960.
S. Juraev, A. Ghimire, J. Alikhanov, V. Kakani and H. Kim, "Exploring Human Pose Estimation and the Usage of Synthetic Data for Elderly Fall Detection in Real-World Surveillance," in IEEE Access, vol. 10, pp. 94249-94261, 2022, doi: 10.1109/ACCESS.2022.3203174.
N. T. Newaz and E. Hanada, “The methods of fall detection: A literature review,” Sensors, vol. 23, no. 11, p. 5212, 2023. doi: 10.3390/s23115212.
P. Yozgatli et al., “Fall detection in passenger elevators using intelligent surveillance camera systems: An application with YOLOv8 Nano model,” arXiv preprint arXiv:2501.01985, 2024. doi: 10.48550/arXiv.2501.01985.
G. A. Pereira, “Fall detection for industrial setups using YOLOv8 variants,” arXiv preprint arXiv:2408.04605, 2024. doi: 10.48550/arXiv.2408.04605.
F. X. Gaya-Morey, C. Manresa-Yee, and J. M. Buades-Rubio, “Deep learning for computer vision-based activity recognition and fall detection of the elderly: A systematic review,” Applied Intelligence, vol. 54, no. 19, pp. 8982–9007, 2024. doi: 10.1007/s10489-024-05434-9.
A. Priadana, D. -L. Nguyen, X. -T. Vo, J. Choi, R. Ashraf and K. Jo, "HFD-YOLO: Improved YOLO Network Using Efficient Attention Modules for Real-Time One-Stage Human Fall Detection," in IEEE Access, vol. 13, pp. 41248-41258, 2025, doi: 10.1109/ACCESS.2025.3547360.
A. Raza, M. H. Yousaf and S. A. Velastin, "Human Fall Detection using YOLO: A Real-Time and AI-on-the-Edge Perspective," 2022 12th International Conference on Pattern Recognition Systems (ICPRS), Saint-Etienne, France, 2022, pp. 1-6, doi: 10.1109/ICPRS54038.2022.9854070.
M. L. Ali and Z. Zhang, “The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection,” Computers, vol. 13, no. 12, p. 336, 2024. doi: 10.3390/computers13120336.
Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-centric real-time object detectors,” arXiv preprint, arXiv:2502.12524, 2025, doi: 10.48550/arXiv.2502.12524.
P. D. K. Manembu, J. I. Litouw, F. D. Kambey, A. H. J. Ontowirjo, V. C. Poekoel, and M. D. Putro, “Efficient fall detection using lightweight network to enhance smart internet of things,” International Journal of Electrical and Computer Engineering (IJECE), vol. 15, no. 5, pp. 5031–5044, 2025. doi. 10.11591/ijece.v15i5.pp5031-5044
H. Ren and P. Lan, “BMR-YOLO: A deep learning approach for fall detection in complex environments,” PLoS One, vol. 20, no. 11, p. e0335992, 2025, doi: 10.1371/journal.pone.0335992.
J. Song, J. Xie, Q. Wang, and T. Shen, “An improved YOLO-based method with lightweight C3 modules for object detection in resource-constrained environments,” J. Supercomput., vol. 81, p. 702, 2025, doi: 10.1007/s11227-025-07187-w.
X. Wu and S. Yu, “CSP-YOLO: An efficient and lightweight real-time algorithm for internal rail defect detection,” The Journal of Supercomputing, vol. 81, no. 15, p. 1450, 2025. doi: 10.1007/s11227-025-07949-6.
S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8759–8768. doi: 10.1109/CVPR.2018.00913.
X. Wang and J. Song, "ICIoU: Improved Loss Based on Complete Intersection Over Union for Bounding Box Regression," in IEEE Access, vol. 9, pp. 105686-105695, 2021, doi: 10.1109/ACCESS.2021.3100414
U. R. Dr. A., “Binary cross entropy with deep learning technique for image classification,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 4, pp. 5393–5397, Aug. 2020, doi: 10.30534/ijatcse/2020/175942020.
X. Li et al., “Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection,” Jun. 2020. [Online]. Available: http://arxiv.org/abs/2006.04388.
M. Dwisnanto Putro, A. Priadana, D. -L. Nguyen and K. -H. Jo, "EMOTIZER: A Multipose Facial Emotion Recognizer Using RGB Camera Sensor on Low-Cost Devices," in IEEE Sensors Journal, vol. 25, no. 2, pp. 3708-3718, 15 Jan.15, 2025, doi: 10.1109/JSEN.2024.3493947.
A. Mujhid, S. Surono, N. Irsalinda, and A. Thobirin, “Comparison and combination of Leaky ReLU and ReLU activation function and three optimizers on deep CNN for COVID-19 detection,” in Fuzzy Systems and Data Mining VIII: Proc. FSDM 2022, pp. 50–57, 2022. doi:10.3233/FAIA220369.
X. Kan, S. Zhu, Y. Zhang, and C. Qian, “A lightweight human fall detection network,” Sensors, vol. 23, no. 22, p. 9069, 2023. doi: 10.3390/s23229069.
D. Schneider, Z. Marinov, R. Baur, Z. Zhong, R. Düger, and R. Stiefelhagen, “OmniFall: A unified staged-to-wild benchmark for human fall detection,” arXiv preprint, arXiv:2505.19889, 2025. doi: 10.48550/arXiv.2505.19889.
B. ByoungWook, “fallen_new_version Dataset,” Roboflow Universe, Roboflow, Jan. 2023. [Online]. Available: https://universe.roboflow.com.
I. Dagal, K. Tanrıöven, A. Nayir, and B. Akın, “Adaptive stochastic gradient descent (SGD) for erratic datasets,” Future Generation Computer Systems, vol. 166, p. 107682, 2025. doi: 10.1016/j.future.2024.107682.
B. Wang, “A Parallel Implementation of Computing Mean Average Precision,” arXiv preprint arXiv:2206.09504, Jun. 2022, doi: 10.48550/arXiv.2206.09504.
R. Kishor, "Performance benchmarking of YOLOv11 variants for real-time delivery vehicle detection: a study on accuracy, speed, and computational trade-offs," Asian Journal of Research in Computer Science, vol. 17, no. 12, pp. 108–122, 2024. doi. 10.9734/ajrcos/2024/v17i12532.
A. Kuzmin, M. Nagel, M. Van Baalen, A. Behboodi, and T. Blankevoort, “Pruning vs quantization: Which is better?” Advances in Neural Information Processing Systems, vol. 36, pp. 62414–62427, 2023, doi: 10.5555/12345678.
DOI: https://doi.org/10.33387/protk.v13i2.11653
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
| Journal Policies | Submissions | People | Information |
Editorial Office :
Protek : Jurnal Ilmiah Teknik Elektro
Department of Electrical Engineering. Faculty of Engineering. Universitas Khairun.
Address: Jusuf Abdulrahman 53 Gambesi, Ternate City, Indonesia.
Email: protek@unkhair.ac.id, WhatsApp: +6282292852552
Address: Jusuf Abdulrahman 53 Gambesi, Ternate City, Indonesia.
Email: protek@unkhair.ac.id, WhatsApp: +6282292852552
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.