.png)
Development of a Spatial-Temporal YOLO-NAS Framework for Real-Time Drowning-Risk Detection in Open-Water Recreational Areas
Abstract
Although effective in swimming pools, automated drowning surveillance in open-water recreational areas remains challenging because of dynamic conditions such as water reflections, lighting variations, wave motion, and crowded scenes. This study proposes the YOLO-NAS-SO (You Only Look Once – Neural Architecture Search – Spatial Optimization) framework to improve the spatial feature representation of YOLO-NAS while maintaining real-time computational efficiency. The framework integrates a Spatial Attention Module after the backbone feature extraction stage to emphasize relevant object features and reduce background interference. For continuous safety monitoring, the proposed framework combines a Modified ByteTrack pipeline with a temporal drowning-duration estimation module. The module monitors the persistence of drowning-risk events across consecutive video frames and generates an early warning when the event duration exceeds a predefined temporal threshold. Unlike conventional ByteTrack, the proposed extension retains the original data association mechanism while adding temporal risk assessment to the tracking process. The main contribution of this study is the integration of spatial attention-based feature enhancement with temporal risk assessment for drowning surveillance in complex open-water environments. Experimental results show that YOLO-NAS-SO achieves a mAP@50–95 of 0.7075, mAP@50 of 0.9166, precision of 0.8844, recall of 0.8817, and F1-score of 0.8830, outperforming the baseline YOLO-NAS and slightly exceeding YOLOv8 while maintaining a real-time inference time of 1.3 ms. These results indicate that combining spatial feature enhancement with temporal drowning-duration monitoring improves detection robustness and supports continuous early-warning surveillance. The proposed framework therefore provides a practical approach for intelligent drowning-risk monitoring in open-water recreational environments.
Keywords
Full Text:
PDFReferences
A. Tsouplaki, C. Fung, and C. Kalloniatis, “Enhancing IoT privacy with artificial intelligence: Recent advances and future directions,” Internet of Things, vol. 34, p. 101752, 2025, doi: https://doi.org/10.1016/j.iot.2025.101752.
T. Pobat et al., “Pool Safety Regulations in Europe: Challenges Towards a Framework for Sustainable Seawater Utilization in Public Swimming Pools,” Water (Basel)., vol. 17, no. 17, 2025, doi: 10.3390/w17172544.
H. Ali, A. Mehmood, N. Ahmed, M. Saeed, and A. Ijaz, “A Lightweight Real-Time CCTV Surveillance Framework for the Education Sector Using Machine Learning,” Journal of Advances in Information Technology, vol. 16, no. 8, pp. 1072–1082, 2025, doi: 10.12720/jait.16.8.1072-1082.
M. Shatnawi, F. Albreiki, A. Alkhoori, M. Alhebshi, and A. Shatnawi, “Advances and Challenges in Automated Drowning Detection and Prevention Systems,” Information, vol. 15, no. 11, 2024, doi: 10.3390/info15110721.
R. Fauzi, Yuhandri, and A. Ramadhanu, “Enhanced Drowning and Swimming Detection in Open Water Recreational Facilities Using YOLO-NAS with Spatial Attention Module,” in 2025 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 2025, pp. 62–67. doi: 10.1109/ICIMCIS68501.2025.11327122.
H. Yu, J. Liu, and M. Lin, “A Comprehensive Literature Review on YOLO-Based Small Object Detection: Methods, Challenges, and Future Trends,” Computers, Materials and Continua, vol. 87, no. 1, 2026, doi: https://doi.org/10.32604/cmc.2025.074191.
M. H. Yuhandri, Yuhandri, and Sumijan, “Modified Convolutional Neural Networks (CNN) with MobileNet-v2-186 Architecture in Crescent Moon Image Detection,” in 2025 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 2025, pp. 32–37. doi: 10.1109/ICIMCIS68501.2025.11326934.
A. Raza, F. Hanif, and H. A. Mohammed, “Analyzing the enhancement of CNN-YOLO and transformer based architectures for real-time animal detection in complex ecological environments,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-26645-2.
D. Nimma et al., “Object detection in real-time video surveillance using attention based transformer-YOLOv8 model,” Alexandria Engineering Journal, vol. 118, pp. 482–495, 2025, doi: https://doi.org/10.1016/j.aej.2025.01.032.
A. Ramadhanu, J. Na’am, G. W. Nurcahyo, and Yuhandri, “Implementation of the Affine Segmentation Point Method and Image Blending Techniques in Creating New Songket Motifs,” in 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 2022, pp. 233–238. doi: 10.23919/EECSI56542.2022.9946616.
X. M. Li, X. H. Pu, W. C. Ling, and X. D. Song, “YOLO-SAM an end-to-end framework for efficient real time object detection and segmentation,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-24576-6.
C. Su et al., “Nav-YOLO: A Lightweight and Efficient Object Detection Model for Real-Time Indoor Navigation on Mobile Platforms,” ISPRS Int. J. Geoinf., vol. 14, no. 9, 2025, doi: 10.3390/ijgi14090364.
T. Pobat, C. Frasca, A. Bruno, and F. Valeriani, “Thermal Water-Supplied Swimming Pools: A Scoping Review of Regulatory Frameworks, Disinfection Challenges, and Emerging Contaminants,” Water (Basel)., vol. 18, no. 9, 2026, doi: 10.3390/w18091050.
Z. Cai, K. Zhou, and Z. Liao, “A Systematic Review of YOLO-Based Object Detection in Medical Imaging: Advances, Challenges, and Future Directions,” Computers, Materials and Continua, vol. 85, no. 2, pp. 2255–2303, 2025, doi: https://doi.org/10.32604/cmc.2025.067994.
D. Ngo, H.-C. Park, and B. Kang, “Edge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments,” Electronics (Basel)., vol. 14, no. 12, 2025, doi: 10.3390/electronics14122495.
S. Abba, A. M. Bizi, J.-A. Lee, S. Bakouri, and M. L. Crespo, “Real-time object detection, tracking, and monitoring framework for security surveillance systems,” Heliyon, vol. 10, no. 15, Aug. 2024, doi: 10.1016/j.heliyon.2024.e34922.
E. Bayraktar, “ReTrackVLM: Transformer-Enhanced Multi-Object Tracking with Cross-Modal Embeddings and Zero-Shot Re-Identification Integration,” Applied Sciences, vol. 15, no. 4, 2025, doi: 10.3390/app15041907.
W. H. E. Mg et al., “Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments,” Sensors, vol. 24, no. 4, 2024, doi: 10.3390/s24041181.
Z. Zhang, C. Shuai, C. Yuan, B. Li, J. Ma, and X. Shang, “ESL-YOLO: Edge-Aware Side-Scan Sonar Object Detection with Adaptive Quality Assessment,” J. Mar. Sci. Eng., vol. 13, no. 8, 2025, doi: 10.3390/jmse13081477.
R. Alfred, J. Leo, and S. F. Kaijage, “Optimizing dataset diversity for a robust deep-learning model in rice blast disease identification to enhance crop health assessment across diverse conditions,” Smart Agricultural Technology, vol. 10, p. 100726, 2025 doi: https://doi.org/10.1016/j.atech.2024.100726.
H. Soudbakhsh, S. R. Das, B. Hassan, and M. F. Wasiq, “Transfer Learning-Based Ethnicity Recognition Using Arbitrary Images Captured Through Diverse Imaging Sensors,” Sensors, vol. 26, no. 3, 2026, doi: 10.3390/s26030886.
G. D.P., A. Pathania, A. -, and S. -, “AUTHENTICATION OF DIGITAL MP4 VIDEO RECORDINGS USING FILE CONTAINERS AND METADATA PROPERTIES,” International Journal of Computer Science Engineering, vol. 10, no. 2, pp. 28–38, Apr. 2021, doi: 10.21817/ijcsenet/2021/v10i2/211002004.
P. Gong and X. Luo, “A Survey of Video Action Recognition Based on Deep Learning,” Knowl. Based. Syst., vol. 320, p. 113594, 2025, doi: https://doi.org/10.1016/j.knosys.2025.113594.
D. A. Amer, N. Y. Ibrahim, I. K. Ibrahim, A. M. Mohamed, and S. A. Soliman, “Intelligent eyes on water: YOLOv11-based real-time drowning detection system,” J. Supercomput., vol. 81, no. 12, p. 1242, 2025, doi: 10.1007/s11227-025-07732-7.
R. Sapkota et al., “YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series,” Artif. Intell. Rev., vol. 58, no. 9, p. 274, 2025, doi: 10.1007/s10462-025-11253-3.
Md. M. Rahman, U. F. Rahim, and E. A. Taufik, “Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10,” Mar. 2026, [Online]. Available: http://arxiv.org/abs/2603.03807
X.-B. Fu, S.-L. Yue, and D.-Y. Pan, “Camera-based Basketball Scoring Detection Using Convolutional Neural Network,” International Journal of Automation and Computing, vol. 18, no. 2, pp. 266–276, 2021, doi: 10.1007/s11633-020-1259-7.
M. Hou, Y. Wu, H. Shi, and X. Mu, “A two stage multi object tracking algorithm with transformer and attention mechanism,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-16389-4.
X. Xu, Y. Jiang, W. Chen, Y. Huang, Y. Zhang, and X. Sun, “DAMO-YOLO : A Report on Real-Time Object Detection Design,” Apr. 2023, [Online]. Available: http://arxiv.org/abs/2211.15444
H. Ahn et al., “SAFP-YOLO: Enhanced Object Detection Speed Using Spatial Attention-Based Filter Pruning,” Applied Sciences (Switzerland), vol. 13, no. 20, Oct. 2023, doi: 10.3390/app132011237.
H. Zhou et al., “Real-time underwater object detection technology for complex underwater environments based on deep learning,” Ecol. Inform., vol. 82, Sep. 2024, doi: 10.1016/j.ecoinf.2024.102680.
G. B. N. I. Saluky and S. Harso Supangkat, “Enhancing Abandoned Object Detection with Dual Background Models and Yolo-NAS,” Nov. 2023. [Online]. Available: www.ijisae.org
W. Yulita et al., “Improved human image density detection with comparison of YOLOv8 depth level architecture and drop-out implementation,” Journal of Soft Computing Exploration, vol. 6, no. 1, pp. 33–39, Mar. 2025, doi: 10.52465/joscex.v6i1.556.
DOI: https://doi.org/10.47738/jads.v7i4.1515
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0