Abstract
Safety helmets are important equipment to ensure worker safety on construction site, so it is necessary to detect whether the construction workers are wearing safety helmets. In this paper, we propose an improved YOLO deep model based on YOLOv5 algorithm to detect the head and helmet objects. First, K-means clustering is used to select 12 representative anchor boxes with appropriate size for the head and helmet objects. Then the model's detection scale is improved to better catch the features of small or overlapping objects. Because the goal is to ensure safety, the model performance on head detection is more important. To minimize the false negative rate of head detection, the loss function is modified to separately calculate the loss caused by different classes of objects. Through experiments, the improved model increases the overall mAP by 1.7% compared to basic YOLOv5 and reaches 96.2%. The recall rate of head detection is increased by 3.3% and reaches 96.8%. The overall performance shows that the improved model has practical significance for construction safety.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection[C]. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE, vol. 1, pp. 886–893 (2005)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints[J]. Int. J. Comput. Vision 60(2), 91–110 (2004)
Bay, H., Tuytelaars, T., Van Gool, L.: Surf: speeded up robust features[C]. In: European Conference on Computer Vision, pp. 404–417. Springer, Berlin (2006)
Suykens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers[J]. Neural Process. Lett. 9(3), 293–300 (1999)
Chen, T., He, T., Benesty, M., et al.: Xgboost: extreme gradient boosting[J]. R package version 0.4-2 1(4), 1–4 (2015)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Adv. Neural. Inf. Process. Syst. 28, 91–99 (2015)
He, K., Gkioxari, G., Dollár, P., et al.: Mask r-cnn[C]. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Liu, W., Anguelov, D., Erhan, D., et al.: SSD: single shot multibox detector[C]. In: European Conference on Computer Vision, pp. 21–37. Springer, Cham (2016)
Fu, C.Y., Liu, W., Ranga, A., et al.: DSSD: deconvolutional single shot detector [J]. arXiv:1701.06659 (2017)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift[C]. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement[J]. arXiv:1804.02767 (2018)
Lin, T.Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934 (2020)
Wang, C.Y., Liao, H.Y.M., Wu, Y.H., et al.: CSPNet: a new backbone that can enhance learning capability of CNN[C]. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390–391 (2020)
Huang, Z., Wang, J., Fu, X., et al.: DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection[J]. Inf. Sci. 522, 241–258 (2020)
Liu, S., Qi, L., Qin, H., et al.: Path aggregation network for instance segmentation[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)
Neubeck, A., Van Gool, L:. Efficient non-maximum suppression[C]. In: 18th International Conference on Pattern Recognition (ICPR'06). IEEE, vol. 3, pp. 850–855 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ni, N., Hu, C. (2022). Automatic Detection of Safety Helmet Based on Improved YOLO Deep Model. In: Nakamatsu, K., Kountchev, R., Patnaik, S., Abe, J.M., Tyugashev, A. (eds) Advanced Intelligent Technologies for Industry. Smart Innovation, Systems and Technologies, vol 285. Springer, Singapore. https://doi.org/10.1007/978-981-16-9735-7_20
Download citation
DOI: https://doi.org/10.1007/978-981-16-9735-7_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9734-0
Online ISBN: 978-981-16-9735-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)