Industrial Safety Helmet Detection: Innovative CNN-Based Classification Approach
DOI:
https://doi.org/10.59890/ijist.v2i5.1925Keywords:
Safety Helmet Detection, Convolutional Neural Networks (CNN), Industrial Safety, Image Classification, Deep LearningAbstract
This study presents the development and evaluation of a CNN-based model for detecting safety helmets in industrial settings. Utilizing a dataset from GitHub, which includes images of individuals wearing safety helmets in various industrial environments, the model was trained using the YOLOv8 architecture over 100 epochs. The comprehensive training process involved data augmentation techniques to enhance generalization capabilities. The evaluation results demonstrated high precision (0.92) and recall (0.856) for helmet detection, with an overall mAP50 of 0.766. Visual analysis through precision-confidence curves confirmed the model's high reliability in detecting helmets at higher confidence thresholds. These findings suggest that the implementation of this model in real-time monitoring systems could significantly enhance industrial safety by reducing manual inspection efforts and ensuring compliance with safety regulations
References
An, Q., Xu, Y., Yu, J., Tang, M., Liu, T., & Xu, F. (2023). Research on Safety Helmet Detection Algorithm Based on Improved YOLOv5s. Sensors 2023, Vol. 23, Page 5824, 23(13), 5824. https://doi.org/10.3390/S23135824
Bhattarai, B., Subedi, R., Gaire, R. R., Vazquez, E., & Stoyanov, D. (2023). Histogram of Oriented Gradients meet deep learning: A novel multi-task deep network for 2D surgical image semantic segmentation. Medical Image Analysis, 85, 102747. https://doi.org/10.1016/J.MEDIA.2023.102747
GitHub - njvisionpower/Safety-Helmet-Wearing-Dataset: Safety helmet wearing detect dataset, with pretrained model. (n.d.). Retrieved May 28, 2024, from https://github.com/njvisionpower/Safety-Helmet-Wearing-Dataset
Liu, Y., Lv, Z., Hu, Y., Dai, F., & Zhang, H. (2022). Improved Cotton Seed Breakage Detection Based on YOLOv5s. Agriculture 2022, Vol. 12, Page 1630, 12(10), 1630. https://doi.org/10.3390/AGRICULTURE12101630
Man, Y., Tran, K. P., Hayat, A., & Morgado-Dias, F. (2022). Deep Learning-Based Automatic Safety Helmet Detection System for Construction Safety. Applied Sciences 2022, Vol. 12, Page 8268, 12(16), 8268. https://doi.org/10.3390/APP12168268
Nandhini, C., & Brindha, M. (2023). Transfer learning based SSD model for helmet and multiple rider detection. International Journal of Information Technology (Singapore), 15(2), 565–576. https://doi.org/10.1007/S41870-022-01058-W/METRICS
Rashed, B. M., & Popescu, N. (2022). Critical Analysis of the Current Medical Image-Based Processing Techniques for Automatic Disease Evaluation: Systematic Literature Review. Sensors 2022, Vol. 22, Page 7065, 22(18), 7065. https://doi.org/10.3390/S22187065
Sadeghi, H., & Raie, A. A. (2022). HistNet: Histogram-based convolutional neural network with Chi-squared deep metric learning for facial expression recognition. Information Sciences, 608, 472–488. https://doi.org/10.1016/J.INS.2022.06.092
Saumya, A., Gayathri, V., Venkateswaran, K., Kale, S., & Sridhar, N. (2020). Machine Learning based Surveillance System for Detection of Bike Riders without Helmet and Triple Rides. Proceedings - International Conference on Smart Electronics and Communication, ICOSEC 2020, 347–352. https://doi.org/10.1109/ICOSEC49089.2020.9215266
Shah, I. A., & Mishra, S. (n.d.). Artificial intelligence in advancing occupational health and safety: an encapsulation of developments. Journal of Occupational Health, 2024(1), 17. https://doi.org/10.1093/JOCCUH/uiad017
Wang, X., Wang, P., Song, J., Hao, T., & Duan, X. (2023). A TEDE Algorithm Studies the Effect of Dataset Grouping on Supervised Learning Accuracy. Electronics 2023, Vol. 12, Page 2546, 12(11), 2546. https://doi.org/10.3390/ELECTRONICS12112546
Zhang, H., Liu, K., Zhang, Y., & Lin, J. (2024). TRANS-CNN-Based Gesture Recognition for mmWave Radar. Sensors 2024, Vol. 24, Page 1800, 24(6), 1800. https://doi.org/10.3390/S24061800
