摘要
安全帽在保护施工人员免受事故中起着至关重要的作用。为了加强建筑工地的安全。论文提出了一种基于卷积神经网络的一级系统,用于自动监测施工人员是否戴安全帽并识别相应的颜色。为了便于研究,论文建了一个新安全帽佩戴检测基准数据集,该数据集由2116幅图像组成,涵盖了不同的现场条件。然后,利用所提出的反向渐进注意对不同尺度的不同层次的特征进行区分融合,生成新的特征金字塔,并将其送入单次激发多盒检测器(SSD)中预测最终的检测结果。该系统采用端到端方案进行训练。实验结果表明,该系统在各种现场条件下都是有效的,在输入尺寸为512×512的情况下,平均mAP精度可达82.21%。
Hardhats play an essential role in protecting construction individuals from accidents.To enhance construction sites safety,in this paper,a onestage system based on convolutional neural network is proposed to automatically monitor whether costruc-tion personnel are wearing hardhats and identify the corresponding colors.To facilityate the study,this work constructs a new hard-hat wearing detection benchmark datasett,which consists of 2116 images covering various on-site conditions.Then,features from different layers with different scales are fused discriminately by the proposed reverse progressive attention to generate a new feature pyramid,which will be fed into the single shot multibox detector(SSD)to predict the final detection results.The proposed system is trained by an end-to-end scheme.The experimental results demonstrate that the proposed system is effective under all kinds of on-site conditions,which can achieve 82.21%mAP(mean average precision)with the input size 512×512.
作者
张贝贝
程科
钱倩倩
张亚芹
ZHANG Beibei;CHENG Ke;QIAN Qianqian;ZHANG Yaqin(School of Computer,Iiangsu University of Science and Technology,Zhenjiang 212100)
出处
《计算机与数字工程》
2023年第7期1657-1662,共6页
Computer & Digital Engineering
关键词
深度学习
卷积神经网络
目标检测
K-MEANS聚类算法
图像增广
deep learning
convolutional neural network
object detection
k-means clustering algorithm
image enhance-ment
