计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (12): 111-117.DOI: 10.3778/j.issn.1002-8331.2309-0440

• 模式识别与人工智能 • 上一篇    下一篇

化工园区场景下安全帽佩戴状态检测算法研究

李永辉,袁亮,何丽,冉腾,吕凯   

  1. 1.新疆大学 智能制造现代产业学院,乌鲁木齐 830047
    2.北京化工大学 信息科学与技术学院,北京 100029
  • 出版日期:2024-06-15 发布日期:2024-06-14

Research on Safety Helmet Wearing Detection Algorithm in Chemical Industry Park Scenarios

LI Yonghui, YUAN Liang, HE Li, RAN Teng, LYU Kai   

  1. 1.School of Intelligent Manufacturing Modern Industry, Xinjiang University, Urumqi 830047, China
    2.School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
  • Online:2024-06-15 Published:2024-06-14

摘要: 针对现有基于深度学习的安全帽佩戴状态检测算法在化工园区复杂场景下小目标检测效果差等问题,提出了一种基于YOLOv5s改进的安全帽佩戴状态检测算法SEE-YOLOv5s。通过增加小目标检测头,以更好地捕捉和定位小目标,从而提高模型对复杂场景小目标的识别和检测能力;将YOLOv5s所有的C3模块融合轻量ECA(efficient channel attention)注意力机制,有效整合全局特征信息,提升小目标检测能力,并降低模型复杂度;引入EIoU(efficient intersection over union)损失函数,提升模型训练效果。在自建的SHWD-HG数据集上进行实验,实验结果表明,改进后YOLOv5s比原始模型的P(precision)、R(recall)、mAP0.5(mean average precision 0.5)和mAP0.5:0.95分别提高了0.5、6.5、5.9和3.2个百分点,且模型大小降低了0.7 MB。

关键词: 小目标检测头, 注意力机制, 安全帽检测, YOLOv5s

Abstract: The deep learning-based methods for safety helmet wearing status detection are not robust enough, resulting in poor detection in chemical industrial parks. In this study, a safety helmet wearing status detection algorithm SEE-YOLOv5s based on YOLOv5s is proposed to improve the accuracy. Firstly, by adding a small target detection layer to better capture and locate small targets, the ability of model to recognize and detect small targets in complex scenes is improved. Secondly, all C3 modules of YOLOv5s are integrated with the lightweight ECA (efficient channel attention) attention mechanism, effectively integrating global feature information, improving small object detection ability, and reducing model complexity. Finally, the EIoU (effective intersection over union) loss function is introduced to improve the training effect of the model. Experiments are conducted on the self built SHWD-HG dataset, and the experimental results show that the improved YOLOv5s increased P(precision), R(recall), mAP 0.5(mean average precision 0.5), and mAP0.5:0.95 compared to the original model by 0.5, 6.5, 5.9, and 3.2 percentage points, respectively, and the model size is reduced by 0.7 MB.

Key words: small target detection head, attention mechanism, safety helmet detection, YOLOv5s