AI-Driven Automated Helmet Detection in Underground Coal Mines using Attention-Enhanced Vision Transformer
Received: 8 March 2025 | Revised: 21 April 2025 | Accepted: 22 April 2025 | Online: 5 May 2025
Corresponding author: Muhammad Yasin
Abstract
Ensuring safety compliance in underground coal mines is essential for preventing accidents and safeguarding miners. Traditional methods for monitoring helmet usage are often ineffective due to poor visibility, dust, and equipment occlusion. This study proposes an attention-enhanced Vision Transformer (ViT) model, specifically adapted for helmet detection in challenging underground environments. The model processes images as sequences of patches, leveraging multi-head self-attention mechanisms to capture global dependencies and improve feature extraction. A custom dataset was developed from underground coal mine footage, and the model was trained using supervised learning with a cross-entropy loss function. The customized ViT achieved an accuracy of 98%, outperforming other State-Of-The-Art (SOTA) models, such as YOLOv8 with attention mechanisms, Mask R-CNN, and Detectron2. The results demonstrate the effectiveness of the attention-enhanced ViT in accurately detecting helmets, even in low-light and cluttered environments. This research contributes to developing real-time, automated safety monitoring systems, which reduce human error and enhance worker safety in hazardous mining operations.
Keywords:
vision transformer, attention mechanism, deep learning, helmet detection, underground coal minesDownloads
References
Y. Liang, Y. Liu, C. Lu, D. Cui, J. Yang, and R. Zhou, "Research on Intelligent Monitoring and Protection Equipment of Vital Signs of Underground Personnel in Coal Mines: Review," Sensors, vol. 25, no. 1, Jan. 2025, Art. no. 63. DOI: https://doi.org/10.3390/s25010063
L. Muduli, D. P. Mishra, and P. K. Jana, "Application of wireless sensor network for environmental monitoring in underground coal mines: A systematic review," Journal of Network and Computer Applications, vol. 106, pp. 48–67, Mar. 2018. DOI: https://doi.org/10.1016/j.jnca.2017.12.022
G. Wang et al., "Research and practice of intelligent coal mine technology systems in China," International Journal of Coal Science & Technology, vol. 9, no. 1, Apr. 2022, Art. no. 24. DOI: https://doi.org/10.1007/s40789-022-00491-3
R. Sehsah, A.-H. El-Gilany, and A. M. Ibrahim, "Personal protective equipment (PPE) use and its relation to accidents among construction workers," La Medicina del Lavoro, vol. 111, no. 4, pp. 285–295, 2020. DOI: https://doi.org/10.23749/mdl.v111i4.9398
P. Lee et al., "Trends in Smart Helmets With Multimodal Sensing for Health and Safety: Scoping Review," JMIR mHealth and uHealth, vol. 10, no. 11, Nov. 2022, Art. no. e40797. DOI: https://doi.org/10.2196/40797
M. Imam et al., "The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines," Sensors, vol. 23, no. 9, Jan. 2023, Art. no. 4294. DOI: https://doi.org/10.3390/s23094294
Z. Wang, Y. Zhu, Y. Zhang, and S. Liu, "An effective deep learning approach enabling miners’ protective equipment detection and tracking using improved YOLOv7 architecture," Computers and Electrical Engineering, vol. 123, Apr. 2025, Art. no. 110173. DOI: https://doi.org/10.1016/j.compeleceng.2025.110173
S. Li, Y. Lv, X. Liu, and M. Li, "Detection of safety helmet and mask wearing using improved YOLOv5s," Scientific Reports, vol. 13, no. 1, Dec. 2023, Art. no. 21417. DOI: https://doi.org/10.1038/s41598-023-48943-3
J. Li, S. Xie, X. Zhou, L. Zhang, and X. Li, "Real-time detection of coal mine safety helmet based on improved YOLOv8," Journal of Real-Time Image Processing, vol. 22, no. 1, Art. no. 26, Dec. 2024. DOI: https://doi.org/10.1007/s11554-024-01604-8
C. Xiang, D. Yin, F. Song, Z. Yu, X. Jian, and H. Gong, "A Fast and Robust Safety Helmet Network Based on a Mutilscale Swin Transformer," Buildings, vol. 14, no. 3, Mar. 2024, Art. no. 688. DOI: https://doi.org/10.3390/buildings14030688
N. D. Nath, A. H. Behzadan, and S. G. Paal, "Deep learning for site safety: Real-time detection of personal protective equipment," Automation in Construction, vol. 112, Apr. 2020, Art. no. 103085. DOI: https://doi.org/10.1016/j.autcon.2020.103085
J.-Y. Lee, W.-S. Choi, and S.-H. Choi, "Verification and performance comparison of CNN-based algorithms for two-step helmet-wearing detection," Expert Systems with Applications, vol. 225, Sep. 2023, Art. no. 120096. DOI: https://doi.org/10.1016/j.eswa.2023.120096
S. R. Kawale, S. Mallikarjun, D. G. V, K. Prasad, S. R, and A. K. N, "Design and Implementation of an AI and IoT-Enabled Smart Safety Helmet for Real-Time Environmental and Health Monitoring," in 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), Jun. 2024, pp. 1–7. DOI: https://doi.org/10.1109/ICITEICS61368.2024.10625126
C. De-qiang et al., "Lightweight network based on residual information for foreign body classification on coal conveyor belt," Journal of China Coal Society, vol. 47, no. 3, pp. 1361–1369, Mar. 2022.
S. P. Uwanteg, “Smart miner helmet and monitoring system in Rwanda. A case of RUTONGO mines, Gasabo district,” M. S. thesis, Deparment of Computer Science, University of Rwanda, Kigali, Rwanda, 2022.
R. Singh, S. Shetty, G. Patil, and P. J. Bide, "Helmet Detection Using Detectron2 and EfficientDet," in 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Jul. 2021, pp. 1–5. DOI: https://doi.org/10.1109/ICCCNT51525.2021.9579953
Helmets: a road safety manual for decision-makers and practitioners, 2nd ed. Geneva, Switzerland: WHO, 2023.
A. Y. Jaffar, "Combining Local and Global Feature Extraction for Brain Tumor Classification: A Vision Transformer and iResNet Hybrid Model," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 17011–17018, Oct. 2024. DOI: https://doi.org/10.48084/etasr.8271
M. Leyva-Vázquez, F. Smarandache, and J. Estupiñan Ricardo, "Artificial intelligence: challenges, perspectives and neutrosophy role," Dilemas Contemporáneos: Educación, Política y Valores, vol. 6, no. Special, 2018.
Downloads
How to Cite
License
Copyright (c) 2025 Muhammad Yasin, Florentin Smarandache, Muhammad Waheed Sabir, Farrukh Arslan, Muhammad Waqas
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
