Jun 2026· Tạp chí Khoa học Lạc Hồng· Vol 1, pp. 9-17· 0 citations
TL;DR
An advanced “SmartSafety” system that employs computer vision technology, utilizing the cutting-edge YOLO (You Only Look Once) version 12 (YOLOv12) for real-time detection of helmets at construction sites, achieves an average mAP@0.5 accuracy exceeding 94%, effectively distinguishing individuals wearing helmets.
Abstract
Ensuring the safety of workers is of utmost importance in construction management, with helmet compliance serving as a crucial preventive measure against head injuries. This paper introduces an advanced “SmartSafety” system that employs computer vision technology, utilizing the cutting-edge YOLO (You Only Look Once) version 12 (YOLOv12) for real-time detection of helmets at construction sites. By analyzing high-resolution video footage from strategically positioned cameras, our deep learning model achieves an average mAP@0.5 accuracy exceeding 94%, effectively distinguishing individuals wearing helmets. The model's effectiveness is underscored by a consistent decrease in loss and enhancements in training metrics. Experimental results under diverse environmental conditions, including varying lighting and dynamic worker movements, further illustrate the system’s robustness. Beyond fostering compliance with safety regulations, this system encourages a proactive safety culture and opens avenues for scalable applications in occupational health management. Our findings underscore the transformative potential of computer vision technologies in enhancing safety and intelligence within construction environments.
This research uses the most recent YOLOv10 object detection architecture to demonstrate a sophisticated computer vision system for real-time safety helmet detection and license plate recognition. The main goal is to improve vehicle monitoring and workplace safety by automatically recognising people who are not wearing safety helmets in industrial zones and recording license plates for regulatory and surveillance purposes. Efficient multi-object identification in difficult situations is made possible by YOLOv10, which is renowned for its exceptional speed and accuracy. To ensure reliable performance, the system is trained using annotated datasets that include a variety of helmet types and car plates under various circumstances. Construction workers' risk of suffering head injuries in highaltitude falls can be significantly decreased by donning safety helmets. This study suggests an enhanced safety helmet detection method based on YOLOv10 to solve the low detection accuracy of current algorithms for small objects and complicated settings in different situations.
Iqra Aziza Khatoon, Dr. Safia Khanam· International Journal of Dat...· 0 citations
Safety helmet compliance monitoring remains challenging because helmets often occupy only a few pixels in wide-area surveillance images. This study tackles these small-object difficulties in vision-based safety-helmet compliance monitoring (helmet vs. no-helmet) using wide-area surveillance imagery. An enhanced You Only Look Once version 10 (YOLOv10) detector is proposed by integrating Omni-Dimensional Dynamic Convolution (ODConv) into the backbone, an Efficient Multi-scale Attention-guided Bidirectional Feature Pyramid Network (EMA-BiFPN) for multi-scale feature fusion, a four-head detection scheme, and the Minimum Points Distance Intersection over Union (MPDIoU) regression loss. Across the experiments, the proposed detector reached an mAP50 of 94.28, with AP50 values of 96.55 for the helmet class and 92.01 for the no-helmet class, exceeding the performance of the YOLOv10 baseline and other benchmark detectors. The most notable gains appeared for extremely small and small targets ([Formula: see text] = 86.10, [Formula: see text] = 91.55), reflecting improved localization of helmets at long distances. Overall, these findings indicate that the method is a strong candidate for deployment-focused helmet-compliance monitoring in large-scale construction settings, although performance limitations remain most evident in far-field views and highly crowded scenes.
Seunghyeon Wang, Enlian Zhang, Rong-Lu Hong et al.· Scientific Reports· 0 citations
The application of computer vision technology in automation systems plays a crucial role in improving the efficiency of occupational safety monitoring in industrial environments. This study developed a YOLOv8-based visual detection application in ONNX format to identify safety helmet violations in real-time. The system was developed using Python with a Tkinter-based user interface and integrated with a Flask web dashboard that displays violation log data. The application can accept video input from various sources, including webcams, USB cameras, and IP cameras, to classify the type of helmet being used. Only orange and white safety helmets are considered valid. Detecting a new helmet, a motorcycle helmet, or a helmet with an inappropriate colour will trigger an alarm and store the image as evidence of the violation. The YOLOv8 model was trained on a six-class dataset and demonstrated good performance, with a precision of 0.921, a recall of 0.859, an mAP50 value of 0.919, and an mAP50-95 value of 0.619. System evaluation demonstrated the application's stability and accuracy in computer vision-based automated surveillance.
S. Syufrijal, Heri Firmansyah, Christophorus Mrc Yuda et al.· EPJ Web of Conferences· 0 citations
Safety helmet wearing detection is a crucial component of safety management in construction sites. Traditional detection methods based on manual monitoring are inefficient, while existing deep learning models often suffer from high computational costs and poor detection performance for small or occluded targets. To address these issues, this paper proposes a lightweight detection algorithm named GCW-YOLOv8. Firstly, the Ghost Module is introduced into the backbone network to replace the conventional convolution layers, significantly reducing the number of parameters and floating-point operations (FLOPs) while maintaining feature extraction capability. Secondly, the Coordinate Attention (CA) mechanism is embedded into the neck network to enhance the model's sensitivity to spatial location and channel information, thereby improving the detection accuracy of small targets. Finally, the Wise-IoU (WIoU) loss function is adopted to replace the original CIoU loss, utilizing a dynamic non-monotonic focusing mechanism to optimize the gradient assignment for low-quality samples. Experimental results on the safety helmet dataset show that the proposed algorithm achieves a mean Average Precision (mAP@0.5) of 94.5%, while the inference speed reaches 108 FPS. Compared with the baseline YOLOv8n, our method improves detection accuracy by 1.4% while reducing parameter count by 34.4%, achieving a superior balance between accuracy and efficiency for smart construction site applications.
Zheng Re, Zhisen Ren, Qianru Liu et al.· International Conference on...· 0 citations
Workplaces in construction and industry suffer from a significant number of workplace accidents because of a lack of safety mechanisms like helmets and high-visibility vests. In order to solve this issue, an automatic detection system for detecting the presence of the worker's helmet & safety vest using a deep learning model is developed. You Only Look Once – Neural Architecture Search (YOLO-NAS) algorithm was chosen to be used in the model because of its fast and high-quality detection process. A dataset with images containing healthy workers wearing helmets & safety vests (with some workers appearing in different safety vests) is collected and used as the training set. The resulting model is then saved for future usage in making predictions with new images. Then, this model is connected to Streamlit, which provides a convenient Web-based user interface through which a user can provide an image as an input to the model. The trained neural network is applied to the input image, and all detected objects that correspond to helmet & safety vest are put in bounding boxes on the input image. Moreover, each of the bounding boxes is labeled with the name of the object and confidence score of the detection. Thus, a clear visualization of the safety equipment worn by the worker is provided. Overall, the developed detection system significantly decreases the human intervention needed for visual verification of the safety helmet or vest. The described system is a user-friendly and cost-effective way of evaluating workplace safety compliance.
S. Vijayakumar, Loganathan Nachimuthu, Balasubramaniam C et al.· 2026 International Conferenc...· 0 citations
The construction safety of workers in hydraulic construction sites that are crowded and difficult to manage is very serious. When personnel movement is frequent, the status of workers wearing safety helmets is difficult to monitor in real time. The focus of this study is the design of HDS-DETR model which is aimed to improve the safety recognition in hydraulic construction projects. Improvements were achieved by integrating the C2f-HDRAB Module to the RT-DETR model to strengthen the model's ability to detect features, the D-Attention mechanism to improve the model's ability to recognize important features, and SlimNeck architecture was implemented to improve the model's ability to efficiently fuse features. The results of the experiments reflect that the accuracy achieved was 94.1% and 89.6% of the improved model offered by the dedicated dataset in recall, and 94.9% of the mean Average Precision at IoU threshold 0.5, which is a 3.7% increase in the original model. The ablation tests demonstrate the effectiveness of the correction of modules and the proposed design is aimed at the complex nature of hydraulic construction, and provides real-time hard hat wearing monitoring. Safety management of the hydraulic engineering construction project provides support and improves the safety condition recognition in smart water conservancy construction projects.
Shousong Liu, Qiulei Zhang, J. Mi et al.· International Conference on...· 0 citations