基于SSD-MobileNet的矿工安保穿戴设备检测系统

张春堂, 管利聪

张春堂,管利聪.基于SSD-MobileNet的矿工安保穿戴设备检测系统[J].工矿自动化,2019,45(6):96-100.. DOI: 10.13272/j.issn.1671-251x.2019010071
引用本文: 张春堂,管利聪.基于SSD-MobileNet的矿工安保穿戴设备检测系统[J].工矿自动化,2019,45(6):96-100.. DOI: 10.13272/j.issn.1671-251x.2019010071
ZHANG Chuntang, GUAN Licong. Detection system of miners' wearable security equipments based on SSD-MobileNet[J]. Journal of Mine Automation, 2019, 45(6): 96-100. DOI: 10.13272/j.issn.1671-251x.2019010071
Citation: ZHANG Chuntang, GUAN Licong. Detection system of miners' wearable security equipments based on SSD-MobileNet[J]. Journal of Mine Automation, 2019, 45(6): 96-100. DOI: 10.13272/j.issn.1671-251x.2019010071

基于SSD-MobileNet的矿工安保穿戴设备检测系统

详细信息
  • 中图分类号: TD67

Detection system of miners' wearable security equipments based on SSD-MobileNet

  • 摘要: 针对因矿山人员流动复杂性导致监管困难及因下井人员安全意识不强导致不能有效穿戴安保设备等问题,设计了基于SSD-MobileNet的矿工安保穿戴设备检测系统。将SSD算法的特征提取网络VGG16替换成MobileNet网络,构建了SSD-MobileNet算法模型;按照VOC2007数据集标准制作矿工安保穿戴设备的照片数据集,对SSD-MobileNet算法模型进行训练;采用SSD-MobileNet算法识别矿工8件安保穿戴设备(安全帽、防尘面具、工作服、工作靴、手电筒、自救器、定位卡、防砸背夹),根据矿工多张不同角度的照片的最高置信度结果综合判定是否穿戴了某件安保设备,并将最高置信度阈值设置为75%。测试结果表明,该系统能够实时、准确地检测出矿工安保设备的穿戴情况,且具有良好的稳定性和抗干扰性。
    Abstract: In view of problems of supervision difficulties caused by complexity of mine personnel flow, and that security equipments cannot be effectively worn due to weak safety awareness of underground personnel, a detection system of miners' wearable security equipments based on SSD-MobileNet was designed. Feature extraction network VGG16 of SSD algorithm is replaced by MobileNet network to construct SSD-MobileNet algorithm model. Photo data set of miners' wearable security equipments is made according to VOC2007 data set standard and used to train the SSD-MobileNet algorithm model. The SSD-MobileNet algorithm is used to identify eight wearable security equipments for miners (hardhats, dust masks, overalls, work boots, flashlights, self-rescuing devices, positioning cards, anti-back clamps). The highest confidence of photos of miner with multiple angles is used for comprehensive determination of whether a security equipment is worn and the highest confidence threshold is set at 75%. The test results show that the system can detect wearing condition of miners' security equipments in real time and accurately, and has good stability and anti-interference.
  • 期刊类型引用(13)

    1. 赵淑枫. 煤矿“智慧安监”系统架构设计与实现. 现代计算机. 2024(03): 117-120 . 百度学术
    2. 韩忠利. 基于卷积神经网络的矿用安全帽佩戴检测. 工矿自动化. 2024(S1): 82-87 . 本站查看
    3. 郭曦浩. 矿井“智慧安监”系统架构设计及实现探究. 当代化工研究. 2024(23): 194-196 . 百度学术
    4. 苏海涛,张守棋. 注意力机制优化SSD的戴口罩人脸快速检测研究. 电脑知识与技术. 2023(19): 30-34+38 . 百度学术
    5. 常政威,蒲维,吴杰,黄坤超,熊兴中,陈明举. 一种基于姿态感知的电力人员穿戴识别残差网络. 电讯技术. 2022(01): 31-38 . 百度学术
    6. 谢晓晓,刘艳艳,陈文涛. 职业性尘肺病与粉尘防治技术研究现状. 武汉理工大学学报(信息与管理工程版). 2022(01): 39-44 . 百度学术
    7. 林其雄,陈畅,闫云凤,齐冬莲. 一种基于特征引导的电力施工场景工装合规穿戴二阶段检测算法. 浙江电力. 2022(04): 44-50 . 百度学术
    8. 魏智锋,肖书浩,蒋国璋,伍世虔,程国飞. 基于深度学习的人造板表面缺陷检测研究. 林产工业. 2021(02): 21-26 . 百度学术
    9. 陈新,伍萍辉,祖绍颖,徐丹,张云鹤,董静. 基于改进SSD轻量化神经网络的番茄疏花疏果农事识别方法. 中国瓜菜. 2021(09): 38-44 . 百度学术
    10. 薄景文,张春堂,樊春玲,李海菊. 改进YOLOv3的矿石输送带杂物检测方法. 计算机工程与应用. 2021(21): 248-255 . 百度学术
    11. 吴蓬勃,姚美菱,王拓,孙青华. 基于TensorFlow的垃圾分拣机器人设计. 实验室研究与探索. 2020(06): 117-122 . 百度学术
    12. 金鹏,薛哲彬,戈垚. 具有实时瓦斯监测功能的新型智能矿工服设计. 纺织学报. 2020(11): 143-149 . 百度学术
    13. 徐贺,杨春梅,李博. 基于改进目标检测算法的AGV避障方法研究. 包装工程. 2020(23): 154-161 . 百度学术

    其他类型引用(16)

计量
  • 文章访问数:  137
  • HTML全文浏览量:  10
  • PDF下载量:  13
  • 被引次数: 29
出版历程
  • 刊出日期:  2019-06-19

目录

    /

    返回文章
    返回