Can Generative AI-Generated Images Effectively Support and Enhance Real-World Construction Helmet Detection?
Open Access
- 13 November 2025
- Vol. 15 (22) , 4080
Abstract
Although computer vision methods have advanced in construction helmet detection in recent years, their performance heavily depends on large-scale, class-balanced, and diverse annotated datasets. To address the high cost and labor-intensive nature of traditional data collection and annotation, this study introduces a novel helmet detection dataset named AIGC-HWD (Artificial Intelligence-Generated Content–Helmet Wearing Detection), automatically generated using generative AI tools. The dataset contains five categories of labels, supporting both helmet-wearing detection and color classification tasks. We evaluate the standalone performance of AIGC-HWD, as well as its augmentation effect when combined with the real-world dataset GDUT-HWD, using multiple algorithms, including YOLO v8, YOLO v10, YOLO 11, YOLO v11-MobileNet v4, YOLO v13, Faster R-CNN, and RT-DETR. Experimental results show that models trained solely on AIGC-generated images can achieve mAP@50 scores exceeding 0.7 and 0.8 on real-world images in two separate tests, demonstrating a certain level of generalization. When used for data augmentation alongside real-world images, the performance improves to varying degrees—by approximately 1% on the YOLO series, and by over 10% on the two-stage algorithm Faster R-CNN. These findings validate the potential of generative AI images for safety monitoring in construction scenarios and provide new insights into the integration of synthetic and real-world data.Keywords
Funding Information
- Liaoning Provincial Joint Science and Technology Program (2025-BSLH-185)
- Basic Research Program for Universities of the Educational Department of Liaoning Province (JYTQN2023241)
This publication has 42 references indexed in Scilit:
- Detection of helmet use among construction workers via helmet-head region matching and state trackingAutomation in Construction, 2025
- Generating realistic training images from synthetic data for excavator pose estimationAutomation in Construction, 2024
- CA-CentripetalNet: a novel anchor-free deep learning framework for hardhat wearing detectionSignal, Image and Video Processing, 2023
- SODA: A large-scale open site object detection dataset for deep learning in constructionAutomation in Construction, 2022
- Towards on-site hazards identification of improper use of personal protective equipment using deep learning-based geometric relationships and hierarchical scene graphAutomation in Construction, 2021
- Deep learning for site safety: Real-time detection of personal protective equipmentAutomation in Construction, 2020
- Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark datasetAutomation in Construction, 2019
- Detecting non-hardhat-use by a deep learning method from far-field surveillance videosAutomation in Construction, 2018
- Fatal traumatic brain injuries in the construction industry, 2003−2010American Journal of Industrial Medicine, 2016
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009