Optimization Research Method for Personal Protective Equipment Wearing Detection on Offshore Platforms Based on YOLOv7
DOI:
https://doi.org/10.54097/411ww112Keywords:
Process Monitoring, Yolov7, Target Recognition, CBAM Mechanism, Labor Insurance Supplies TestingAbstract
In response to the monitoring requirements of offshore operations, this paper addresses the issue of subjective oversight in the wearing of personal protective equipment (PPE) by inspection personnel on offshore platforms during their work process. By integrating object detection algorithms from the field of computer vision, a monitoring method for PPE usage by workers on offshore platforms is proposed. This method builds upon the YOLOv7 neural network and introduces the CBAM attention mechanism and the Focaler-IOU bounding box loss function to optimize the recognition accuracy of detection targets, resulting in an increase in the mean average precision (mAP) by 5.9% compared to the original model. The feasibility and effectiveness of the integrated detection method were validated through testing on a field dataset.
Downloads
References
[1] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.
[2] He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9): 1904-1916.
[3] Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.
[4] Jiang P, Ergu D, Liu F, et al. A Review of Yolo algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073.
[5] Li H, Wu D, Zhang W, et al. YOLO-PL: Helmet wearing detection algorithm based on improved YOLOv4[J]. Digital Signal Processing, 2023: 104283.
[6] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023: 7464-7475.
[7] Jakubec M, Lieskovska E, Brezani A, et al. Deep learning-based automatic helmet recognition for two-wheeled road safety [J]. Transportation research procedia, 2023, 74: 1171-1178.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
