施工现场火焰检测和预警机器人设计及应用

doi:10.16265/j.cnki.issn1003-3033.2021.04.019

中国安全科学学报 ›› 2021, Vol. 31 ›› Issue (4): 141-146.doi: 10.16265/j.cnki.issn1003-3033.2021.04.019

施工现场火焰检测和预警机器人设计及应用

李继超¹, 郭聖煜^**1 副教授, 孔刘林² 副教授, 原毅璨¹, 孙阳³

1 中国地质大学武汉经济管理学院,湖北武汉 430074;
2 中国地质大学武汉工程学院,湖北武汉 430074;
3 中国地质大学武汉机械与电子信息学院,湖北武汉 430074

收稿日期:2021-01-25 修回日期:2021-03-20 出版日期:2021-04-28 发布日期:2021-12-20
通讯作者: **郭聖煜 (1988—),男,湖北咸宁人,博士,副教授,主要从事工程质量与安全管理、安全风险管理等方面的研究。E-mail: gsy.yu@foxmail.com。
作者简介:李继超 (1995—),男,山东济宁人,硕士研究生,研究方向为工程安全管理。E-mail: jichao.l19@gmail.com。
基金资助:
国家自然科学基金青年基金资助(71801197);中国地质大学(武汉)中央高校基本科研业务费专项资金资助项目。

Design and application of a fire detection and early warning robot in construction site

LI Jichao¹, GUO Shengyu¹, KONG Liulin², YUAN Yican¹, SUN Yang³

1 School of Economics and Management, China University of Geosciences, Wuhan Hubei 430074, China;
2 Faculty of Engineering, China University of Geosciences, Wuhan Hubei 430074, China;
3 School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan Hubei 430074, China

Received:2021-01-25 Revised:2021-03-20 Online:2021-04-28 Published:2021-12-20

摘要/Abstract

摘要： 为预防施工现场火灾事故,提高火焰检测性能,设计基于单点多盒检测器(SSD)和MobileNet模型相结合的火焰检测和预警机器人。首先,处理采集的火焰视频图像数据集,并将其划分为真实火焰图片与疑似火焰图片2类;其次,结合迁移学习思想,微调SSD_MobileNet模型中的网络参数值;最后,将获得的检测模型集成到机器人视频监控平台,进行火焰检测与预警,并在某工地上测试其应用效果。结果表明:在检测模型50%的置信度阈值下,机器人能够准确检测出工地场景中的火焰,多帧视频准确率达到90%以上,并可实现实时预警。

关键词: 施工现场, 火焰检测, 火灾预警, 机器人, 单点多盒检测器(SSD)_MobileNet

Abstract: In order to prevent fire accidents at construction sites and improve fire detection performance, a detection and early warning robot based on combination of SSD and MobileNet model was designed. Firstly, data set of collected fire video images was processed and divided into two categories, namely real fire images and non-fire images. Secondly, network parameter values in SSD_MobileNet model were fine-tuned based on idea of migration learning. Finally, the obtained model was integrated into robot video surveillance platform for fire detection and early warning, and its application effect was tested on a construction site. The results show that the robot can accurately detect fire in construction sites with a 50% confidence threshold of detection model. Accuracy of multi-frame video exceeds 90%, and real-time warning can be achieved.

Key words: construction site, fire detection, fire warning, robot, single shot multibox detector (SSD)_MobileNet

中图分类号:

X924.3

李继超, 郭聖煜, 孔刘林, 原毅璨, 孙阳. 施工现场火焰检测和预警机器人设计及应用[J]. 中国安全科学学报, 2021, 31(4): 141-146.

LI Jichao, GUO Shengyu, KONG Liulin, YUAN Yican, SUN Yang. Design and application of a fire detection and early warning robot in construction site[J]. China Safety Science Journal, 2021, 31(4): 141-146.

参考文献

[1] 李云, 张晴, 沈子豪, 等. FMF的火焰显著性检测[J]. 中国安全科学学报, 2019, 29(5): 56-61.
LI Yun, ZHANG Qing, SHEN Zihao, et al. Flame saliency detection based on FMF [J]. China Safety Science Journal, 2019, 29(5): 56-61.
[2] U.S. Fire Administration. U.S. fire statistics [EB/OL]. [2020-08-01]. https://www.usfa.fema.gov/data/statistics/.
[3] 应急管理部消防救援局. 2019年全国接报火灾23.3万件[EB/OL]. [2020-08-01].https://www.119.gov.cn/article/3xBeEJjR54K.
[4] 何永勃, 董玉珊, 雷建, 等. 飞机货舱火灾多传感器探测方法研究 [J]. 中国安全科学学报, 2018, 28(5): 74-79.
HE Yongbo, DONG Yushan, LEI Jian, et al. Research on multi-sensor method for detecting aircraft cargo fire [J]. China Safety Science Journal, 2018, 28(5): 74-79.
[5] QIU Xuanbing, XI Tingyu, SUN Dongyuan, et al. Fire detection algorithm combined with image processing and flame emission spectroscopy [J]. Fire Technology, 2018, 54(5): 1 249-1 263.
[6] 张科, 叶影, 张红. 基于边缘计算的森林火警监测系统[J]. 大数据, 2019, 5(2): 79-88.
ZHANG Ke, YE Ying, ZHANG Hong. Forest fire monitoring system based on edge computing [J]. Big Data Research, 2019, 5(2): 79-88.
[7] 杨柳, 张德, 王亚慧, 等. 城市火灾视频监控目标区域图像准确检测仿真[J]. 计算机仿真, 2019, 36(4): 425-431.
YANG Liu, ZHANG De, WANG Yahui, et al. A detection and simulation algorithm for video surveillance in urban fire [J].Computer Simulation, 2019, 36(4): 425-431.
[8] 王琳, 姚新, 雷丹. 公路隧道火灾初期视频火焰检测[J]. 中国公路学报, 2018, 31(11): 121-129.
WANG Lin, YAO Xin, LEI Dan. Video-based on recognition of early fire flame in road tunnel [J].China Journal of Highway and Transport, 2018, 31(11): 121-129.
[9] 段锁林, 顾川林. 基于BP神经网络视频火灾火焰检测方法[J]. 常州大学学报:自然科学版, 2017, 29(2): 65-70.
DUAN Suolin, GU Chuanlin. Rsearch on the detection method based on the optimized BP neural network for the visual fire flame recognition [J]. Journal of Changzhou University:Natural Science Edition, 2017, 29(2): 65-70.
[10] MUHAMMAD K, AHMAD J, BAIK S W. Early fire detection using convolutional neural networks during surveillance for effective disaster management [J]. Neurocomputing, 2018, 288: 30-42.
[11] 严云洋, 朱晓妤, 刘以安, 等. 基于Faster R-CNN模型的火焰检测[J]. 南京师大学报:自然科学版, 2018, 41(3): 1-5.
YAN Yunyang, ZHU Xiaoyu, LIU Yi'an, et al. Flame detection based on faster R-CNN model [J]. Journal of Nanjing Normal University:Natural Science Edition, 2018, 41(3): 1-5.
[12] JIAO Zhentian, ZHANG Youmin, XIN Jing, et al. A deep learning based forest fire detection approach using UAV and YOLOv3 [C]. 2019 1^st International Conference on Industrial Artificial Intelligence (IAI), 2019: 1-5.
[13] 李俊伟. 自主巡逻机器人行进避障及火灾预警研究 [D]. 呼和浩特:内蒙古工业大学, 2017.
LI Junwei. Research on obstacle avoidance and fire early warning of autonomous patrol robot [D]. Hohhot: Inner Mongolia University of Technology, 2017.
[14] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector [C]. European Conference on Computer Vision, 2016: 21-37.
[15] HOWARD A G, ZHU Menglong, CHEN Bo, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications [Z/OL]. (2017-04-17). https://arxiv.org/abs/1704.04861.
[16] 任锴, 陈俊, 叶宇煌, 等. 基于SSD-MobileNet的火情检测预警系统 [J]. 电气开关, 2020, 58(1): 34-38.
REN Kai, CHEN Jun, YE Yuhuang, et al. Fire detection early warning system based on SSD-Mobile net [J]. Electric Switchgear, 2020, 58(1): 34-38.
[17] EVERINGHAM M, WINN J. The pascal visual object classes challenge 2007 (voc2007) development kit [J]. International Journal of Computer Vision, 2006, 111(1): 98-136.
[18] 刘鑫鹏, 栾悉道, 谢毓湘,等. 迁移学习研究和算法综述[J]. 长沙大学学报, 2018, 32(5): 28-31.
LIU Xinpeng, LUAN Xidao, XIE Yuxiang, et al. Transfer learning research and algorithm review [J]. Journal of Changsha University, 2018, 32(5): 28-31.
[19] 任宇杰, 杨剑, 刘方涛, 等. 基于SSD和MobileNet网络的目标检测方法的研究[J]. 计算机科学与探索, 2019, 13(11): 1 881-1 893.
REN Yujie, YANG Jian, LIU Fangtao, et al. Research on target detection method based on SSD and mobilenet network[J]. Journal of Frontiers of Computer Science and Technology, 2019, 13(11): 1 881-1 893.

施工现场火焰检测和预警机器人设计及应用

Design and application of a fire detection and early warning robot in construction site

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	秦海伟, 陆从飞, 蒋永生, 周旭, 程斌. 轨道式攀爬机器人系统设计与图像处理[J]. 中国安全科学学报, 2019, 29(7): 117-122.
[2]	李云, 张晴, 沈子豪, 左保川. FMF的火焰显著性检测[J]. 中国安全科学学报, 2019, 29(5): 56-61.
[3]	李伟, 阳富强. 基于SLP的地铁施工场地安全布局优化方案[J]. 中国安全科学学报, 2019, 29(1): 161-166.
[4]	胡瑾秋, 唐静静. 自适应神经网络在FPSO火灾预警中的应用[J]. 中国安全科学学报, 2017, 27(12): 8-13.
[5]	张海涛，吴伟巍，李响，李启明. 基于循证方法的施工现场安全事故预防体系研究[J]. 中国安全科学学报, 2012, 22(12): 17-.
[6]	吴海彬，杨剑鸣. 机器人在人机交互过程中的安全性研究进展[J]. 中国安全科学学报, 2011, 21(11): 79-.
[7]	韩书葵，方跃法，任红亚. 一种五自由度并联机器人奇异位形分析[J]. 中国安全科学学报, 2005, 15(11): 27-.
[8]	郭盛，方跃法. 一种可以实现救援对接的4自由度并联机器人设计方法[J]. 中国安全科学学报, 2004, 14(8): 22-.
[9]	贺耀荣，汪莉，李祥，宋存义. 基于BP网络的建筑安装施工现场安全综合评价的研究[J]. 中国安全科学学报, 2004, 14(12): 100-.
[10]	胡准庆，房海蓉，方跃法. 机器人精确轨迹控制方法的研究[J]. 中国安全科学学报, 2003, 13(3): 8-.
[11]	房海蓉，方跃法，杨延昭，胡准庆. 基于隧道火灾的消防机器人系统研究[J]. 中国安全科学学报, 2003, 13(10): 34-.