AUTOMATED DETECTION OF HELMET WEARING WITH YOLOV8 AND REAL-TIME MONITORING FOR FACTORY SAFETY.
Saved in:
| Title: | AUTOMATED DETECTION OF HELMET WEARING WITH YOLOV8 AND REAL-TIME MONITORING FOR FACTORY SAFETY. |
|---|---|
| Authors: | Santi, Ratna1 ratna.s.kardi@gmail.com, Suwarningsih, Wiwin2 wiwi005@brin.go.id, Sastrosubroto, Ashwin Sasongko1 ashwin.sasongko@gmail.com |
| Source: | Interdisciplinary Journal of Information, Knowledge & Management. 2025, Vol. 20, p1-26. 26p. |
| Subjects: | Safety hats, Object recognition (Computer vision), Factory safety, Work environment, Safety regulations, Work-related injuries, Industrial safety |
| Abstract: | Aim/Purpose The study aimed to develop an automated, real-time monitoring system using YOLOv8 to detect the use of safety helmets in factories, thereby improving workplace safety and compliance. Background Industrial safety, particularly in factories, is critical for preventing workplace accidents. The detection of safety helmets is an essential component of factory safety protocols; however, manual monitoring can be inefficient and prone to error. This study applies YOLOv8, a state-of-the-art object detection algorithm, to enhance monitoring efficiency by automating the detection process, particularly in challenging conditions such as low-light environments and dynamic settings. Methodology The YOLOv8 model was trained on a comprehensive dataset of helmet images captured in various industrial settings, encompassing different lighting conditions, angles, and helmet types to ensure the model's robustness. The system was designed to detect the presence or absence of helmets in real time using video footage. Performance metrics, including precision, recall, and accuracy, were utilized to evaluate the model's effectiveness, with a focus on addressing the unique challenges of real-world applications. Contribution This research contributes to the field of industrial safety by offering an automated and scalable solution for real-time helmet detection. The system significantly reduces the need for human intervention in monitoring safety compliance and provides an efficient mechanism for alerting supervisors about safety violations. Findings The results indicated that the YOLOv8-based detection system achieved high accuracy in real-time helmet detection, even under challenging environmental conditions. The system successfully identified instances of non-compliance, allowing for timely corrective actions. Additionally, the model demonstrated low false-positive and false-negative rates. Statistical significance testing revealed that the model's performance metrics, including sensitivity and specificity, showed significant improvements compared to previous versions and traditional methods (p < 0.05), underscoring the robustness of YOLOv8 in dynamic factory conditions. Recommendations for Practitioners Factory managers and safety officers are encouraged to implement this system to enhance safety oversight, reduce the risk of accidents, and streamline the monitoring process without requiring extensive human resources. Recommendations for Researchers Further research could focus on integrating additional safety features, such as detecting other protective gear (e.g., gloves, goggles), and expanding the dataset to include more diverse industrial environments. Impact on Society Enhancing safety protocols in industrial settings has the potential to significantly reduce workplace injuries, leading to safer working environments and greater compliance with safety regulations. Future Research Future research may explore the integration of this system with Internet of Things (IoT) devices for broader safety monitoring and the application of YOLOv8 in detecting other safety hazards beyond helmet use. [ABSTRACT FROM AUTHOR] |
| Copyright of Interdisciplinary Journal of Information, Knowledge & Management is the property of Informing Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| Abstract: | Aim/Purpose The study aimed to develop an automated, real-time monitoring system using YOLOv8 to detect the use of safety helmets in factories, thereby improving workplace safety and compliance. Background Industrial safety, particularly in factories, is critical for preventing workplace accidents. The detection of safety helmets is an essential component of factory safety protocols; however, manual monitoring can be inefficient and prone to error. This study applies YOLOv8, a state-of-the-art object detection algorithm, to enhance monitoring efficiency by automating the detection process, particularly in challenging conditions such as low-light environments and dynamic settings. Methodology The YOLOv8 model was trained on a comprehensive dataset of helmet images captured in various industrial settings, encompassing different lighting conditions, angles, and helmet types to ensure the model's robustness. The system was designed to detect the presence or absence of helmets in real time using video footage. Performance metrics, including precision, recall, and accuracy, were utilized to evaluate the model's effectiveness, with a focus on addressing the unique challenges of real-world applications. Contribution This research contributes to the field of industrial safety by offering an automated and scalable solution for real-time helmet detection. The system significantly reduces the need for human intervention in monitoring safety compliance and provides an efficient mechanism for alerting supervisors about safety violations. Findings The results indicated that the YOLOv8-based detection system achieved high accuracy in real-time helmet detection, even under challenging environmental conditions. The system successfully identified instances of non-compliance, allowing for timely corrective actions. Additionally, the model demonstrated low false-positive and false-negative rates. Statistical significance testing revealed that the model's performance metrics, including sensitivity and specificity, showed significant improvements compared to previous versions and traditional methods (p < 0.05), underscoring the robustness of YOLOv8 in dynamic factory conditions. Recommendations for Practitioners Factory managers and safety officers are encouraged to implement this system to enhance safety oversight, reduce the risk of accidents, and streamline the monitoring process without requiring extensive human resources. Recommendations for Researchers Further research could focus on integrating additional safety features, such as detecting other protective gear (e.g., gloves, goggles), and expanding the dataset to include more diverse industrial environments. Impact on Society Enhancing safety protocols in industrial settings has the potential to significantly reduce workplace injuries, leading to safer working environments and greater compliance with safety regulations. Future Research Future research may explore the integration of this system with Internet of Things (IoT) devices for broader safety monitoring and the application of YOLOv8 in detecting other safety hazards beyond helmet use. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 15551229 |
| DOI: | 10.28945/5499 |
