计算机与现代化 ›› 2022, Vol. 0 ›› Issue (01): 91-97.

• 图像处理 • 上一篇    下一篇

基于深度级联模型工业安全帽检测算法

  

  1. (1.江西科技师范大学通信与电子学院,江西南昌330013;2.防城港市气象局,广西防城港538001)
  • 出版日期:2022-01-24 发布日期:2022-01-24
  • 作者简介:杨贞(1985—),男,山东菏泽人,讲师,博士,研究方向:目标检测,图像分类,E-mail: yangzhenphd@aliyun.com; 朱强强(1995—),男,安徽阜南人,硕士研究生,研究方向:目标检测,E-mail: qiangqiangzhu@aliyun.com; 彭小宝(1995—),男,江西新余人,硕士研究生, 研究方向:图像分割,E-mail: pengxiaobao@aliyun.com; 殷志坚(1968—),男,江西南昌人,教授,硕士,研究方向:目标识别与跟踪,E-mail: zhijianyin@aliyun.com; 温海桥(1990—),男,江西吉安人,讲师,硕士,研究方向:目标缺陷检测,E-mail: 2874116859qq.com; 黄春华(1986—),女,广西防城港人,高级工程师,学士,研究方向:大数据处理,E-mail: 775710447@qq.com。
  • 基金资助:
    国家自然科学基金资助项目(61866016); 江西省自然科学基金面上项目(20202BABL202014); 江西省教育厅一般项目(GJJ190587); 江西省教育厅青年项目(GJJ201142); 江西科技师范大学青年拔尖项目(2018QNBJRC002)

Industrial Safety Helmet Detection Algorithm Based on Depth Cascade Model

  1. (1. College of Communication & Electronics, Jiangxi Science and Technology Normal University, Nanchang 330013, China;
    2. Fangchenggang City Meteorological Bureau, Fangchenggang 538001, China)
  • Online:2022-01-24 Published:2022-01-24

摘要: 在工业生产中,安全帽对人体头部提供了较好的安全保障。在现场环境中,检验施工人员是否佩戴安全帽主要依靠人工检查,因而效率非常低。为了解决施工现场安全帽检测识别难题,提出一种基于深度级联网络模型的安全帽检测方法。首先通过You Only Look Once version 4 (YOLOv4)检测网络对施工人员进行检测;然后运用注意力机制残差分类网络对人员ROI区域进行分类判断,识别其是否佩戴安全帽。该方法在Ubuntu18.04系统和Pytorch深度学习框架的实验环境中进行,在自主制作工业场景安全帽数据集中进行训练和测试实验。实验结果表明,基于深度级联网络的安全帽识别模型与YOLOv4算法相比,准确率提高了2个百分点,有效提升施工人员安全帽检测效果。

关键词: 安全帽, 级联网络, 目标检测, YOLOv4, 残差分类网络, 注意力机制

Abstract: In industrial production, safety helmet provides a better safety guarantee for human head. In the field environment, the inspection of whether the construction personnel wear safety helmet mainly depends on manual inspection, so the efficiency is very low. In order to solve the problem of helmet detection and identification in construction site, this paper proposes a helmet detection method based on the deep cascade network model. Firstly, the construction personnel are detected through the You Only Look Once version 4 (YOLOv4) detection network. Then, the attention mechanism residual classification network is used to classify and judge the ROI region of personnel and identify whether they wear a helmet or not. This method is carried out in the experimental environment of Ubuntu18.04 system and Pytorch deep learning framework, and training and testing experiments are carried out in the self-produced helmet data set. The experimental results show that compared with YOLOv4, the safety helmet recognition model based on the deep cascade network has an accuracy increase of 2 percentage points, which effectively improves the safety helmet detection effect of construction personnel.

Key words: safety helmet, cascade network, target detection, You Only Look Once version 4(YOLOv4), residual classification network, attention mechanism