基于改进YOLOv5s的电力作业人员安全帽检测算法研究
Research on safety helmet detection algorithm for power operators based on improved YOLOv5s
刘昶成 1邵文权 1李玲陶1
作者信息
- 1. 西安工程大学电子信息学院 西安 710048
- 折叠
摘要
传统的电力施工现场安全帽检测算法的网络计算复杂度高、在复杂场景下对于远处目标和密集群体存在漏检等问题,提出一种改进后的轻量化YOLOv5s-GCAE算法,主干网络首先用GhostNet网络中的深度可分离卷积GhostConv,以此降低网络的计算量和参数量.其次在特征提取阶段中嵌入CA注意力机制,填补了引入轻量化网络时精度的缺失.引入自适应空间特征融合(ASFF)网络以有效融合多尺度特征,提高模型丰富的语义特征表示使网络更好的适应复杂的电力施工现场.最后引入损失函数EIOU,促使网络专注于高质量的锚点以提升在复杂场景下安全帽检测精度.构建了一个包含开源图片和自行收集的图片共9 326张的安全帽佩戴检测数据集.实验结果表明,该算法的安全帽检测准确率为93.4%,比YOLOv5s算法高2.1%,符合电力场景下安全帽检测的精度要求.
Abstract
The traditional network calculation complexity of the safety helmet detection algorithm at the power construction site is high,and there are problems such as missing detection for distant targets and dense groups in complex scenarios.This paper proposes an improved lightweight YOLOv5s-GCAE algorithm,in which the backbone network first uses the deep separable convolutional GhostConv in the GhostNet network to reduce the amount of computation and parameters of the network.Secondly,the CA attention mechanism is embedded in the feature extraction stage,which fills the lack of accuracy when introducing lightweight networks.The ASFF network is introduced to effectively fuse multi-scale features,improve the rich semantic feature representation of the model,and make the network better adapt to complex power construction sites.Finally,the loss function EIOU is introduced to promote the network to focus on high-quality anchor points to improve the accuracy of helmet detection in complex scenarios.In this paper,a safety helmet wearing detection dataset containing 9 326 open-source images and self-collected images is constructed.Experimental results show that the safety helmet detection accuracy of the algorithm is 93.4%,which is 2.1%higher than that of the YOLOv5s algorithm,which meets the accuracy requirements of safety helmet detection in power scenarios.
关键词
安全帽检测/电力场景/YOLOv5s/CA注意力模块/Ghost/NetKey words
helmet detection/power scenarios/YOLOv5s/CA attention mechanism/GhostNet引用本文复制引用
出版年
2024
NETL
NSTL
万方数据