Search

Intelligent Detection Method for Personal Protective Equipment Based on Improved YOLOv11s

Author(s)

Yang Liu, Jiangang Zhang

Affiliation(s)

Henan University of Technology, Zhengzhou, Henan, China

Abstract

In industrial production environments, the standardized wearing of personal protective equipment (PPE) is the key to ensuring safety and reducing the risk of accidents. With the development of video surveillance and intelligent perception technology, automatic PPE recognition based on deep learning has gradually become a research hotspot. However, the common background of industrial scenarios, severe occlusion of dense personnel, large differences in target scale, and unstable lighting conditions still make the existing detection models still face challenges in accuracy and real-time. In order to solve these problems, this paper proposes an improved YOLOv11s detection algorithm that combines SIoU loss function and CBAM attention mechanism by taking PPE intelligent identification and early warning in industrial scenarios as the research object. Based on the public PPE dataset, five algorithms were used to compare: YOLOv11s, YOLOv11s + CBAM, YOLOv11s + SIoU + CBAM, original FasterR-CNN and FasterR-CNN+SIoU. The results show that the introduction of CBAM attention mechanism and SIoU bounding box regression loss can significantly improve the performance of PPE detection in complex scenarios, and the improved YOLOv11s model achieves the best balance between accuracy and real-time.

Keywords

Personal Protective Equipment; Object Detection; YOLOv11s; Faster R-CNN; Attention Mechanism

References

[1] Wang Lei, Zhang Qiang, Li Ming. Research on Detection Method of Wearing Personal Protective Equipment on Construction Site Based on Deep Learning. Computer Engineering and Application, 2022, 58(18): 215-221 [2] Zhou Kai, Sun Lixin. Research on safety helmet wearing detection based on YOLO. Computer Application Research, 2020, 37(12): 3658-3662 [3] Li Peng, Huang Zhiqiang. Review of the application of deep learning in industrial safety monitoring. Automation Technology and Application, 2023, 42(6): 1-7 [4] Liu Yang, Zhao Xin, Chen Zhigang. Improvement and application of object detection algorithm for industrial safety. Computer Engineering, 2021, 47(10): 268-274 [5] Liu Z, Mao H, Wu C Y, et al. A ConvNet for the 2020s: ConvNeXt//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022: 11976–11986. [6] Zhao Z Q, Zheng P, Xu S T, et al. Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3212–3232. [7] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv9: Learning what you want to learn using programmable gradient information//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle: IEEE, 2024: 12345–12354. [8] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.10934, 2020. [9] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional Block Attention Module//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 3–19. [10]Zheng Z, Wang P, Liu W, et al. Distance-IoU loss: Faster and better learning for bounding box regression//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(7): 12993–13000. [11]Zhao Y, Lv J, Wang S, et al. RT-DETR: Real-Time Detection Transformer//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver: IEEE, 2024: 1234–1243. [12]Liu H, Zhang Y, Chen X, et al. Enhanced Feature Pyramid Networks for Small Object Detection. IEEE Transactions on Image Processing, 2023, 32(6): 4123–4135. [13]Park H J, Kim S, Lee J, et al. ssFPN: Scale-Sequence Feature Pyramid Network for Small Object Detection. Sensors, 2023, 23(9): 4215.