AI-DRIVEN REAL-TIME PPE COMPLIANCE MONITORING IN THE PALM OIL INDUSTRY USING YOLOv8
DOI:
https://doi.org/10.11113/jurnalteknologi.v88.24334Keywords:
PPE compliance, YOLOv8, palm oil industry, AI-based monitoring, real-time detectionAbstract
Ensuring personal protective equipment (PPE) compliance in hazardous work environments, such as the palm oil industry, remains a significant challenge due to the limitations of manual inspections. Current monitoring methods are mostly labor-intensive, prone to human error, and lack real-time capabilities. This study proposes an AI-driven PPE detection system utilizing YOLOv8, an object detection model, to enhance safety compliance through real-time monitoring. A comprehensive dataset of PPE usage scenarios was developed, and the YOLOv8 model was trained to recognize essential safety gear, including hard hats, safety vests, masks, and safety shoes. Based on experimental results it was found that the proposed system achieves a mean average precision (mAP) of 67.3% for 200 epochs of training, with a precision of 96.5% and a recall of 85.4%, significantly improving PPE detection accuracy compared to previous models. Furthermore, the system integrates Streamlit for an interactive interface and a Telegram application-based notifications for real-time compliance alerts. These findings suggested that AI-based monitoring can provide an effective, scalable, and automated solution for enforcing PPE regulations, reducing workplace hazards, and enhancing operational efficiency in the palm oil industry.
References
Li, Z., W. Xie, L. Zhang, S. Lu, L. Xie, H. Su, W. Du, and W. Hou. 2022. Toward Efficient Safety Helmet Detection Based on YOLOv5 with Hierarchical Positive Sample Selection and Box Density Filtering. IEEE Transactions on Instrumentation and Measurement. 71: 1–14. https://doi.org/10.1109/TIM.2022.3169564.
Yipeng, and J. Wu. 2024. Personal Protective Equipment Detection for Construction Workers: A Novel Dataset and Enhanced YOLOv5 Approach. IEEE Access. 12: 47338–47358. https://doi.org/10.1109/ACCESS.2024.3382817.
Lin, B. 2024. Safety Helmet Detection Based on Improved YOLOv8. IEEE Access. 12: 28260–28272. https://doi.org/10.1109/ACCESS.2024.3368161.
Wang, Z., Y. Wu, L. Yang, A. Thirunavukarasu, C. Evison, and Y. Zhao. 2021. Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches. Sensors. 21(10): 3478. https://doi.org/10.3390/s21103478.
Zou, J., T. Song, S. Cao, B. Zhou, and Q. Jiang. 2024. Dress Code Monitoring Method in Industrial Scene Based on Improved YOLOv8n and DeepSORT. Sensors. 24(18): 6063. https://doi.org/10.3390/s24186063.
Liu, G., Y. Zhang, J. Liu, D. Liu, C. Chen, Y. Li, X. Zhang, and P. L. Touko Mbouembe. 2024. An Improved YOLOv7 Model Based on Swin Transformer and Trident Pyramid Networks for Accurate Tomato Detection. Frontiers in Plant Science. 15: 1452821. https://doi.org/10.3389/fpls.2024.1452821.
Redmon, J., S. Divvala, R. Girshick, and A. Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779–788. https://doi.org/10.1109/CVPR.2016.91.
Chen, H., J. Qi, M. Wang, and C. Wu. 2023. Helmet-Wearing Detection Algorithm Based on Improved YOLOv5s. In Proceedings of the IEEE International Conference on Computer Science and Applications (ICCSA), 8564–8569. https://doi.org/10.1109/ICCSA.2023.8564896.
Medioni, M., and M. Cahyandito. 2015. Is Converting Shrub Land to Palm Oil Plantation Worth It? An Ecosystem Services Analysis. Journal of Academic Business and Retail Management. 10(1). https://doi.org/10.2139/ssrn.2676275.
Mamun, K. A., et al. 2024. Smart Reception: An Artificial Intelligence-Driven Bangla Language-Based Receptionist System Employing Speech, Speaker, and Face Recognition for Automating Reception Services. Engineering Applications of Artificial Intelligence. 136: 108923. https://doi.org/10.1016/j.engappai.2024.108923.
Khatun, R., M. I. H. Reza, M. Moniruzzaman, and Z. Yaakob. 2017. Sustainable Oil Palm Industry: The Possibilities. Renewable and Sustainable Energy Reviews. 76: 608–619. https://doi.org/10.1016/j.rser.2017.03.077.
Waqar, A., N. Bheel, and B. A. Tayeh. 2024. Modeling the Effect of Implementation of Artificial Intelligence Powered Image Analysis and Pattern Recognition Algorithms in Concrete Industry. Developments in the Built Environment. 17: 100349. https://doi.org/10.1016/j.dibe.2024.100349.
Verma, A., G. Ghajari, K. M. T. Jawad, H. P. Salehi, and F. Amsaad. 2024. Real-Time Automated Donning and Doffing Detection of PPE Based on YOLOv4-Tiny. In Proceedings of the IEEE National Aerospace Electronics Conference (NAECON). 398–402. https://doi.org/10.1109/NAECON.2024.10670616.
Luwes, N., and W. Pretorius. 2024. Development of a Cost-Effective Artificial Intelligence-Based Image Processing Sorting Mechanism for Conveyor Belt System. In Proceedings of the IEEE International Conference on Human System Interaction (HSI). 1–6. https://doi.org/10.1109/HSI.2024.10613600.
Waqar, A., N. Bheel, and B. A. Tayeh. 2024. Modeling the Effect of Implementation of Artificial Intelligence Powered Image Analysis and Pattern Recognition Algorithms in Concrete Industry. Developments in the Built Environment. 17: 100349. https://doi.org/10.1016/j.dibe.2024.100349.
Luwes, N., and W. Pretorius. 2024. “Development of a Cost-Effective Artificial Intelligence-Based Image Processing Sorting Mechanism for Conveyor Belt System. In International Conference on Human System Interaction (HSI) IEEE Computer Society. 1–6. https://doi.org/10.1109/HSI61632.2024.10613600.
Al-Azani, S., H. Luqman, M. Alfarraj, A. A. I. Sidig, A. H. Khan, and D. Al-Hammed. 2024. Real-Time Monitoring of Personal Protective Equipment Compliance in Surveillance Cameras. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3451117.
Li, H., H. Xu, Y. Li, and X. Li. 2024. Application of Artificial Intelligence (AI)-Enhanced Biochemical Sensing in Molecular Diagnosis and Imaging Analysis: Advancing and Challenges. TrAC - Trends in Analytical Chemistry. 174: 117700. https://doi.org/10.1016/j.trac.2024.117700.
Arfan, M., S. Sumardi, and H. Huboyo. 2023. Advancing Workplace Safety: A Deep Learning Approach for Personal Protective Equipment Detection Using Single Shot Detector. In International Workshop on Artificial Intelligence and Image Processing (IWAIIP 2023), Institute of Electrical and Electronics Engineers Inc. 127–132. https://doi.org/10.1109/IWAIIP58158.2023.10462804.
Wu, D., et al. 2022. Detection of Camellia Oleifera Fruit in Complex Scenes by Using YOLOv7 and Data Augmentation. Applied Sciences (Switzerland) 12 (22): 11318. https://doi.org/10.3390/app122211318.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
