黑龙江科技大学学报2024，Vol.34Issue(3)：452-456,468,6.DOI:10.3969/j.issn.2095-7262.2024.03.018
基于剪枝算法改进YOLOv5的煤矿井下安全帽检测方法
Improvement of YOLOv5 detection method for safety helmets in coal mines based on pruning algorithm
摘要
Abstract
This paper aims to address the hard and bad detection performance of the safety helmet caused by the complex underground environments and overly large models.The study works by improving YOLOv5s model by introducing ECA attention mechanism to enhance detection accuracy with no increas-ing computational complexity;and cropping the redundant channels within the network to be more light-weighted by using the model compression strategy based on Batch Normalization layers.The results dem-onstrate that in the self-built underground safety helmet data set,the parameter is 45.5%of that of the o-riginal network,while maintaining equivalent detection accuracy between the improved method and YOLOv5s model,as which effectively balances average detection accuracy with model size.关键词
安全帽检测/注意力机制/模型压缩Key words
helmet detection/attention mechanism/model compression分类
矿山工程引用本文复制引用
汝洪芳,梁一乐,王国新..基于剪枝算法改进YOLOv5的煤矿井下安全帽检测方法[J].黑龙江科技大学学报,2024,34(3):452-456,468,6.基金项目
黑龙江省重点研发计划指导类项目(GZ20220122) （GZ20220122）
黑龙江省省属高等学校基本科研业务费项目(2023-KYYWF-0545) （2023-KYYWF-0545）
