期刊论文

中文

计算机工程与应用

1002-8331

2023

59

2

194-201

10.3778/j.issn.1002-8331.2206-0468

国家自然科学基金(62101204)。

本校为第一机构

佩戴安全帽是施工过程中人员安全的重要保障之一,但现有的人工检测不仅耗时耗力而且无法做到实时监测,针对这一现象,提出了一种基于深度学习的安全帽佩戴检测算法。该算法以YOLOv5s网络为基础。在网络的主干网中引入CoordA...展开更多 佩戴安全帽是施工过程中人员安全的重要保障之一,但现有的人工检测不仅耗时耗力而且无法做到实时监测,针对这一现象,提出了一种基于深度学习的安全帽佩戴检测算法。该算法以YOLOv5s网络为基础。在网络的主干网中引入CoordAtt坐标注意力机制模块,考虑全局信息,使得网络分配给安全帽更多的注意力,以此提升对小目标的检测能力;针对原主干网对特征融合不充分的问题,将...

Wearing safety helmet is one of the important guarantees for personnel safety in the construction process.However,the existing manual detection is time-consuming and unable to achieve real-time monitoring.Aiming at this phenomenon,a safety helmet detection algorithm bas...MORE Wearing safety helmet is one of the important guarantees for personnel safety in the construction process.However,the existing manual detection is time-consuming and unable to achieve real-time monitoring.Aiming at this phenomenon,a safety helmet detection algorithm based on deep learning is proposed.The algorithm is bas...