|本期目录/Table of Contents|

[1]丁莹莹,卜昌森,李晓慧,等.基于改进MobileNet-YOLOv3级联模型的内涝及受灾个体监测研究*[J].中国安全生产科学技术,2023,19(6):26-32.[doi:10.11731/j.issn.1673-193x.2023.06.004]
　DING Yingying,BU Changsen,LI Xiaohui,et al.Monitoring of waterlogging and affected individuals based on improved MobileNet-YOLOv3 cascade model[J].Journal of Safety Science and Technology,2023,19(6):26-32.[doi:10.11731/j.issn.1673-193x.2023.06.004]
点击复制

基于改进MobileNet-YOLOv3级联模型的内涝及受灾个体监测研究*

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年6期
页码:
26-32
栏目:
学术论著
出版日期:
2023-06-30

文章信息/Info

Title:
Monitoring of waterlogging and affected individuals based on improved MobileNet-YOLOv3 cascade model
文章编号:
1673-193X(2023)-06-0026-07
作者:
丁莹莹; 卜昌森; 李晓慧; 刘永强; 薛明; 尹尚先
（1.华北科技学院 安全工程学院，河北 廊坊 065201；
2.应急管理部大数据中心，北京 100013）
Author(s):
DING Yingying; BU Changsen;  LI Xiaohui;  LIU Yongqiang;  XUE Ming;  YIN Shangxian
(1.School of Safety Engineering,North China Institute of Science and Technology,Langfang Hebei 065201,China;
2.Ministry of Emergency Management Big Data Center,Beijing 100013,China)
关键词:
城市内涝; 监测预警; 积水监控; 目标监测; 自动识别
Keywords:
urban waterlogging;  monitoring and early warning;  water accumulation monitoring;  target monitoring;  automatic identification
分类号:
X913.4
DOI:
10.11731/j.issn.1673-193x.2023.06.004
文献标志码:
A
摘要:
为解决现有城市内涝监测技术机动性低、设备自身缺陷、光照不均以及其他噪声因素引起的识别精度低的问题，建立改进的MobileNet-YOLOv3级联模型。首先，利用圆形LBP算法改进MobileNet模型实现监控视频内涝自动识别；改进的MobileNet模型引进圆形LBP算子提取特征，将MobiletNet卷积提取的特征与圆形LBP算子提取的特征融合，融合后的特征经过MobileNet主体网络学习训练得到最终的特征后采用全连接层分类输出监测结果；其次，通过改进YOLOv3算法实现对内涝点车辆、行人等受灾个体视频的智能识别，改进的YOLOv3算法将模型输入改为MobileNet模型提取出的特征，并且引入CIOU损失函数；最后，将两改进算法级联实现完整的内涝及受灾个体监测功能。研究结果表明：改进模型整体识别准确率达到90%以上，实现对多个特征的融合应用，使各特征之间联系更加密切，能较为准确地对城市道路或隧道等场景进行积水监测及受灾个体识别。研究结果可为内涝灾害预防提供技术支持。
Abstract:
In order to solve the problem of low recognition accuracy caused by low mobility,equipment defects,uneven illumination and other noise factors of existing urban waterlogging monitoring technologies,an improved MobileNet-YOLOv3 cascade model was established.Firstly,the circular LBP algorithm was used to improve the MobileNet model to realize the automatic identification of waterlogging in surveillance video.In the improved MobileNet model,the circular LBP operators were introduced to extract features,and the features extracted by MobletNet convolution and circular LBP operators were fused,and together through the learning and training of MobileNet subject network,the single-layer full-connection layer classification was adopted.Secondly,the YOLOv3 algorithm was improved to realize the intelligent identification on the video of the affected individuals such as vehicles and pedestrians at the waterlogging point.The improved YOLOv3 algorithm changed the model input to the features extracted from the MobileNet model,and introduced into the CIOU loss function.Finally,the two improved algorithms were cascaded to realize the complete monitoring function of waterlogging and affected individuals.The research results show that the overall identification accuracy of the improved model is more than 90%,the integration of multiple features is realized,the relationship between various features is closer,and the water monitoring and the identification of affected individuals in urban roads,tunnels and other scenes can be more accurate.The results can provide technical support for the waterlogging disaster prevention.

参考文献/References:

［1］王浩,梅超,刘家宏.海绵城市系统构建模式［J］.水利学报,2018,48(9):1009-1014,1022. WANG Hao,MEI Chao,LIU Jiahong.Systematic construction pattern of thesponge city［J］.Journal of Hydraulic Engineering,2018,48(9):1009-1014,1022.
［2］彭恒明,王铁骊.基于Z-numbers的城市内涝灾害应急能力评价研究［J］.中国安全生产科学技术,2020,16(5):115-121. PENG Hengming,WANG Tieli.Study on evaluation of emergency capacity for urban waterlogging disaster based on Z-numbers［J］.Journal of Safety Science and Technology,2020,16(5):115-121.
［3］王喆,杨栋梁,况星园,等.考虑提示学习的洪涝灾害应急决策自动问答模型研究［J］.中国安全生产科学技术,2022,18(11):12-18. WANG Zhe,YANG Dongliang,KUANG Xingyuan,et al.Research on automatic question answering model of flood disaster emergency decision-making considering Prompt-learning［J］.Journal of Safety Science and Technology,2022,18(11):12-18.
［4］宋英华,高晓茜,霍非舟,等.考虑洪涝灾害风险的城市应急避难场所选址研究［J］.中国安全生产科学技术,2022,18(6):31-37. SONG Yinghua,GAO Xiaoxi,HUO Feizhou,et al.Study on site selection of urban emergency shelters consider risk of flood disaster［J］.Journal of Safety Science and Technology,2022,18(6):31-37.
［5］陈勇,刘佐东,熊非凡,等.基于深度学习的城市积涝监控预警系统［J］.电脑知识与技术,2020,16(1):174-175. CHEN Yong,LIU Zuodong,XIONG Feifan,et al.Urban flood monitoring and warning system based on deep learning［J］.Computer Knowledge and Technoogy,2020,16(1):174-175.
［6］徐湃,朱代强,蒋树屏,等.重庆长大公路隧道结构安全保障技术及策略研究［J］.现代隧道技术,2022,59(4):18-28,39. XU Pai,ZHU Daiqiang,JIANG Shuping,et al.Study on thestructural safety assurance technology and strategy for long and large highway tunnels in Chongqing［J］.Modern Tunnelling Technology,2022,59(4):18-28,39.
［7］栾清华,秦志宇,王东,等.城市暴雨道路积水监测技术及其应用进展［J］.水资源保护,2022,38(1):106-116,140. LUAN Qinghua,QIN Zhiyu,WANG Dong,et al.Review on monitoring technology of urban road waterlogging after rainstorm and its application［J］.Water Resources Protection,2022,38(1):106-116,140.
［8］周宏,刘俊,高成,等.我国城市内涝防治现状及问题分析［J］.灾害学,2018,33(3):147-151. ZHOU Hong,LIU Jun,GAO Cheng,et al.Analysis of current situation and problems of urban waterlogging control in China［J］.Journal of Catastrophology,2018,33(3):147-151.
［9］高淑萍,赵清源,齐小刚,等.改进MobileNet的图像分类方法研究［J］.智能系统学报,2021,16(1):11-20. GAO Shuping,ZHAO Qingyuan,QI Xiaogang,et al.Research on the improved image classification method of MobileNet ［J］.CAAI Transactionson Intelligent Systems,2021,16(1):11-20.
［10］白岗岗,侯精明,韩浩,等.基于深度学习的道路积水智能监测方法［J］.水资源保护,2021,37(5):75-80. BAI Ganggang,HOU Jingming,HAN Hao,et al.Intelligent monitoring method for road inundation based on deep learning［J］.Water Resources Protection,2021,37(5):75-80.
［11］ZANG D,CHAl Z L,CHENG J J,et al.Vehicel license plate recognition using visual attention model and deep learning［J］.Journal of Electroniclmaging,2015,24(3):033001.
［12］周午阳,孙志民,汤舒.深层隧道排水区域液位在线监测系统研究［J］.中国给水排水,2018,34(1):1-6. ZHOU Wuyang,SUN Zhimin,TANG Shu.Research on liquid level on-line monitoring system of deep tunnel drainage basin［J］.China Water & Wastewater,2018,34(1):1-6.
［13］钟道清,郑颖,叶嘉毅,等.城市隧道水位监测与现场警示系统［C］//中国水利学会2020学术年会论文集第五分册,2020:370-375.
［14］乔建刚,陶瑞,刘翔.改进组件树在隧道裂缝识别中的应用［J］.中国安全生产科学技术,2022,18(6):105-110. QIAO Jiangang,TAO Rui,LIU Xiang.Application of improved component tree in tunnel crack identification［J］.Journal of Safety Science and Technology,2022,18(6):105-110.
［15］江河瑞通（北京）技术有限公司.城市内涝监测方法及电子设备:110956783B［P］.2021-11-16.
［16］珠江水利委员会珠江水利科学研究院.城市内涝监测预报预警方法、装置、系统及存储介质:111882830B［P］.2021-12-14.
［17］张男男,李丽莎,王宝珠,等.基于MobileNet的地基云图分割方法研究［J］.电子技术与软件工程,2022(18):129-132. ZHANG Nanan,LI Lisha,WANG Baozhu,et al.Research on segmentation method of ground-based cloud image based on MobileNet［J］.Electronic Technology & Software Engineering,2022(18):129-132.
［18］牛洪超,胡晓兵,罗耀俊.基于M-YOLO的自动驾驶下目标识别算法［J］.计算机工程与设计,2022,43(8):2213-2220. NIU Hongchao,HU Xiaobing,LUO Yaojun.Target recognition algorithm in autonomous driving based on M-YOLO［J］.Computer Engineering and Design,2022,43(8):2213-2220.
［19］郭克友,王苏东,李雪,等.基于Dim env-YOLO算法的昏暗场景车辆多目标检测［J］.计算机工程,2023,49(3):312-320. GUO Keyou,WANG Sudong,LI Xue,et al.Vehicle detection based on Dim env-YOLO in dim scene［J］.Computer Engineering,2023,49(3):312-320.
［20］袁帅,孙亚男,何卫锋,等.基于多尺度特征提取的高光谱星载分类算法［J］.激光与光电子学进展,2023,60(10):70-81. YUAN Shuai,SUN Yanan,HE Weifeng,et al.Hyperspectral on-board classification algorithm based on multi-scalefeature extraction［J］.Laser & Optoelectronics Progress,2023,60(10):70-81.
［21］邓源,施一萍,江悦莹,等.基于MobileNetV2与LBP特征融合的婴幼儿表情识别算法［J］.电子科技,2022,35(8):47-52. DENG Yuan,SHl Yiping,JIANG Yueying,et al.Infant expression recognition algorithm based on MobileNetV2 and LBP feature fusion［J］.Electronic Science and Technology,2022,35(8):47-52.
［22］宋晓茹,杨佳,高嵩,等.基于注意力机制与多尺度特征融合的行人重识别方法［J］.科学技术与工程,2022,22(4):1526-1533. SONG Xiaoru,YANG Jia,GAO Song,et al.Person re-identification method based on attention mechanism and multi-scale feature fusion［J］.Science Technology and Engineering,2022,22(4):1526-1533.
［23］刘翀豪,潘理虎,杨帆,等.改进YOLOv5的轻量化口罩检测算法［J］.计算机工程与应用,2023,59(7)：232-241. LIU Chonghao,PAN Lihu,YANG Fan,et al.lmproved YOLOv5 lightweight mask detection algorithm［J］.Computer Engineering and Applications,2023,59(7)：232-241.

相似文献/References:

[1]汪嘉俊,倪顺江.电力设备火灾危险性分析与防控技术*[J].中国安全生产科学技术,2022,18(9):189.[doi:10.11731/j.issn.1673-193x.2022.09.027]
　WANG Jiajun,NI Shunjiang.Fire risk analysis and fire prevention and control technology of power equipment[J].Journal of Safety Science and Technology,2022,18(6):189.[doi:10.11731/j.issn.1673-193x.2022.09.027]
[2]罗宏森,谭涛,杨琴.城市内涝灾害中考虑紧迫度的排涝设备调度研究*[J].中国安全生产科学技术,2023,19(8):178.[doi:10.11731/j.issn.1673-193x.2023.08.026]
　LUO Hongsen,TAN Tao,YANG Qin.Study on dispatching of drainage equipment considering urgency in urban waterlogging disasters[J].Journal of Safety Science and Technology,2023,19(6):178.[doi:10.11731/j.issn.1673-193x.2023.08.026]
[3]周福宝,袁亮,程卫民,等.矿井粉尘职业健康防护技术2013—2023年研究进展*[J].中国安全生产科学技术,2023,19(12):5.[doi:10.11731/j.issn.1673-193x.2023.12.001]
　ZHOU Fubao,YUAN Liang,CHENG Weimin,et al.Research progress on occupational health protection technology of mine dust from 2013 to 2023[J].Journal of Safety Science and Technology,2023,19(6):5.[doi:10.11731/j.issn.1673-193x.2023.12.001]
[4]尹萌萌,刘梦婷,朱伟,等.城市内涝灾害韧性评估及影响因子分析*——以福州市为例[J].中国安全生产科学技术,2024,20(10):61.[doi:10.11731/j.issn.1673-193x.2024.10.008]
　YIN Mengmeng,LIU Mengting,ZHU Wei,et al.Resilience assessment and influencing factors analysis of urban waterlogging disaster:a case study of Fuzhou City[J].Journal of Safety Science and Technology,2024,20(6):61.[doi:10.11731/j.issn.1673-193x.2024.10.008]
[5]杨晓琳,于正兴,龚敬,等.救援现场次生灾害风险预警与防控指挥车*——多灾种模块化系统设计与应用[J].中国安全生产科学技术,2025,21(7):191.[doi:10.11731/j.issn.1673-193x.2025.07.025]
　YANG Xiaolin,YU Zhengxing,GONG Jing,et al.Command vehicle for rescue site secondary disaster risk early warning and prevention：multi-hazard modular system design and application[J].Journal of Safety Science and Technology,2025,21(6):191.[doi:10.11731/j.issn.1673-193x.2025.07.025]
[6]吴健波,岳伟涛,王恩元,等.专利数据视角下冲击地压监测预警技术创新特征与发展趋势研究*[J].中国安全生产科学技术,2026,22(3):101.[doi:10.11731/j.issn.1673-193x.2026.03.013]
　WU Jianbo,YUE Weitao,WANG Enyuan,et al.Research on innovation characteristics and development trends of rockburst monitoring and early warning technology from a patent data perspective[J].Journal of Safety Science and Technology,2026,22(6):101.[doi:10.11731/j.issn.1673-193x.2026.03.013]
[7]吕伟,姜雅娟,李晓恋,等.人群聚集拥挤度的量化表征方法*[J].中国安全生产科学技术,2023,19(1):14.[doi:10.11731/j.issn.1673-193x.2023.01.002]
　LYU Wei,JIANG Yajuan,LI Xiaolian,et al.Quantitative method for characterizing congestion degree of gathering crowd[J].Journal of Safety Science and Technology,2023,19(6):14.[doi:10.11731/j.issn.1673-193x.2023.01.002]

备注/Memo

备注/Memo:
收稿日期： 2023-01-07
* 基金项目： 国家重点研发计划项目（2021YFB3901200）；北京市科技计划项目（Z211100004121004）
作者简介： 丁莹莹，硕士研究生，主要研究方向为应急信息化技术、水文地质学等。
通信作者： 李晓慧，硕士，工程师，主要研究方向为应急信息化技术。
更新日期/Last Update: 2023-07-09