增强小目标检测的建筑工地安全装备检测  

Construction Site Safety Equipment Detection with Enhanced Small Target Detection

作　　者：吕明海 王昱博 吕伏 冯永安 LYU Ming-Hai;WANG Yu-Bo;LYU Fu;FENG Yong-An(Software College,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学软件学院,葫芦岛125105

出　　处：《计算机系统应用》2025年第2期122-134,共13页Computer Systems & Applications

基　　金：国家自然科学基金青年基金(51904144);辽宁工程技术大学鄂尔多斯研究院校地科技合作培育项目(YJY-XD-2023-014,YJY-XD-2024-040)。

摘　　要：YOLOv8n算法在面对背景繁杂、目标密集、像素点小的情况下,表现出识别精度欠佳、目标漏检及误识别的问题.针对上述问题,提出一种LNCE-YOLOv8n安全装备佩戴检测算法.包括提出线性多尺度融合注意力LMSFA(linear multi-scale fusion attention)机制,自适应聚焦关键特征,提升对小目标信息提取的能力且减少计算.提出C2f_NewNet(C2f_New network)结构,通过有效的并行化设计,保持高性能且减少深度.结合轻量级通用上采样算子CARAFE(content-aware reassembly of feature),实现跨尺度的高效特征融合与传播,在大的感受野内聚合上下文信息.基于SIoU(symmetric intersection over union)损失函数提出ESIoU(enhanced symmetric intersection over union),提升模型在复杂环境中的适应性和精度.实验采用safety equipment数据集进行训练测试,结果表明LNCEYOLOv8n算法相比YOLOv8n算法,精度提升了5.1%,mAP50提升了2.7%,mAP50-95提升了3.4%,有效提高建筑工地复杂场景的工人安全装备佩戴检测精度.The YOLOv8n algorithm exhibits suboptimal performance when dealing with complex backgrounds,dense targets,and small-sized objects with limited pixel information,leading to reduced precision,missed detection,and misclassification.To address these issues,this study proposes an algorithm,LNCE-YOLOv8n,for safety equipment detection.This algorithm includes a linear multi-scale fusion attention(LMSFA)mechanism,which adaptively focuses on key features to improve the extraction of information from small targets while reducing computational loads.An architecture called C2f_New networks(C2f_NewNet)is also introduced,which maintains high performance and reduces depth through an effective parallelization design.Combined with a lightweight universal up-sampling operator,contentaware reassembly of features(CARAFE),the proposed algorithm realizes efficient cross-scale feature fusion and propagation and aggregates contextual information within a large receptive field.Based on the SIoU(symmetric intersection over union)loss function,this study proposed enhanced SIoU(ESIoU)to improve the adaptability and accuracy of the model in complex environments.Tested on a safety equipment dataset,LNCE-YOLOv8n outperforms YOLOv8n,exhibiting a 5.1%increase in accuracy,a 2.7%rise in mAP50,and a 3.4%boost in mAP50-95,significantly enhancing the detection accuracy of safety equipment for workers in complex construction conditions.

关 键 词：YOLOv8n 注意力机制 并行化设计 上采样 损失函数 

分 类 号：TU714[建筑科学—建筑技术科学] TP391.41[自动化与计算机技术—计算机应用技术]