[1]田枫,白欣宇,刘芳,等.1种基于视频的油田危险区域入侵检测智能综合识别技术研究*[J].中国安全生产科学技术,2022,18(3):68-75.[doi:10.11731/j.issn.1673-193x.2022.03.010]
TIAN Feng,BAI Xinyu,LIU Fang,et al.Research on intelligent comprehensive recognition technology of intrusion detection in oilfield dangerous area based on video[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):68-75.[doi:10.11731/j.issn.1673-193x.2022.03.010]
点击复制
1种基于视频的油田危险区域入侵检测智能综合识别技术研究*
TIAN Feng,BAI Xinyu,LIU Fang,et al.Research on intelligent comprehensive recognition technology of intrusion detection in oilfield dangerous area based on video[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):68-75.[doi:10.11731/j.issn.1673-193x.2022.03.010]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 18
- 期数:
- 2022年3期
- 页码:
- 68-75
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2022-03-31
文章信息/Info
- Title:
- Research on intelligent comprehensive recognition technology of intrusion detection in oilfield dangerous area based on video
- 文章编号:
- 1673-193X(2022)-03-0068-08
- Keywords:
- area intrusion; multi-target tracking; oilfield dangerous area classification; intelligent analysis; YOLOv5
- 分类号:
- X937
- 文献标志码:
- A
- 摘要:
- 为解决油田日常生产作业中缺乏危险作业区域的等级划分与自动识别方式以及缺乏人员踏入危险区域的识别方法。提出1种基于视频智能综合识别技术的全天油田危险区域入侵检测算法，该算法首先结合油田危险因素对油田危险区域进行危险等级的划分与危险区域的识别；然后，针对光照条件良好的白天场景，在训练数据集中融合油田作业区视频数据和公开行人数据集，弥补油田作业区入侵样本不足的问题，有效地增加模型的泛化性；针对光照条件差的黑夜场景，使用三帧差分法，背景减除法等算法对运动目标进行检测。研究结果表明：本文提出算法较YOLOv5方法的精度更高，在不同油田场景下精度可达91.83%，已在油田作业现场进行部署与应用。
- Abstract:
- In order to solve the lack of classification and automatic identification methods of dangerous operation areas and the lack of identification methods for personnel entering dangerous areas in daily production operation of oilfields,an intrusion detection algorithm for all-day oilfield dangerous areas based on the video intelligent comprehensive recognition technology was put forward.Firstly,the algorithm combined the oilfield risk factors to classify the oilfield dangerous areas and identify the dangerous areas.Then,for the daytime scenes with good lighting conditions,the video data of the oilfield operation area and the public pedestrian data set were integrated into the training datasets to make up for the lack of intrusion samples in the oilfield operation area and effectively increase the generalization of the model.For the dark night scenes with poor lighting conditions,the three-frame difference method and background subtraction method and other algorithms were used to detect the moving targets.The results showed that compared with the YOLOv5 method,the proposed algorithm had an accuracy of up to 90% in different oilfield scenes,and it had been deployed and applied on the oilfield operation site.
参考文献/References:
［1］罗音宇,江田汉,邓云峰,等.含硫气井硫化氢扩散危险水平分级方法［J］.石油学报,2008(3):447-450.LUO Yinyu,JIANG Tianhan,DENG Yunfeng,et al.Danger level classification method for hydrogen sulfide diffusion in sulfur gas Wells ［J］.Acta Petrolei Sinica,2008(3):447-450.
［2］张若诚,王宇超,王建华,等.油田钻井井场危险区域的划分［J］.石油矿场机械,2012,41(5):80-83.ZHANG Ruocheng,WANG Yuchao,WANG Jianhua,et al.Division of dangerous area of oil field drilling site ［J］.Oil Field Equipment,2012,41(5):80-83.
［3］刘康,陈国明,魏超南.浮式生产系统泄漏天然气扩散规律与危险区域［J］.石油学报,2015,36(8):1018-1028.LIU Kang,CHEN Guoming,WEI Chaonan.Diffusion law and risk area of leaky natural gas in floating production system［J］.Acta PetroleiSinica,2015,36(8):1018-1028.
［4］赵宁刚,燕秋华,苗立新,等.基于三类危险源理论的油库火灾爆炸事故致因［J］.油气储运,2018,37(1):24-28.ZHAO Ninggang,YAN Qiuhua,Miao Lixin,et al.Cause of oil depot fire and explosion accident based on three types of hazard theory ［J］.Oil & Gas Storage and Transportation,2018,37(1):24-28.
［5］赵春兰,殷慧敏,王兵,等.基于结构方程与蒙特卡洛方法的钻井现场作业风险评价［J］.天然气工业,2019,39(2):84-93.ZHAO Chunlan,YIN Huimin,WANG Bing,et al.Drilling field operation risk assessment based on structural equation and monte carlo method ［J］.Natural Gas Industry,2019,39(2):84-93.
［6］刘扬,张阳,魏立新,等.危险度分级法对原油稳定装置的安全评价［J］.油气储运,2008(6):34-36,14-15,62.LIU Yang,ZHANG Yang,WEI Lixin,et al.Safety evaluation of crude oil stabilizer by hazard classification method ［J］.Oil & Gas Storage and Transportation,2008(6):34-36,14-15,62.
［7］王瑞,史天运,包云.一种基于视频的铁路周界入侵检测智能综合识别技术研究［J］.仪器仪表学报,2020,41(9):188-195.WANG Rui,SHI Tianyun,BAO Yun.Research on intelligent comprehensive recognition technology of railway perimeter intrusion detection based on video ［J］.Chinese Journal of Scientific Instrument,2020,41(9):188-195.
［8］王伟,吕山可,张雨果,等.基于BIM与机器视觉技术结合的建筑施工危险区域入侵预警研究［J］.安全与环境工程,2020,27(2):196-203.WANG Wei,LYU Shanke,ZHANG Yuguo,et al.Research on building construction hazard zone intrusion warning based on BIM and machine vision ［J］.Safety and Environmental Engineering,2020,27(2):196-203.
［9］LOWE D G.Distinctive image features from scale invariant keypoints［J］.International Journal of Computer Vision,2004,60(2):91-110.
［10］ZHAO J,ZHANG X,YAN J,et al.A wheat spike detection method in UAV images based on improved YOLOv5［J］.Remote Sensing,2021,13(16):3095.
［11］付国栋,黄进,杨涛,等.改进CBAM的轻量级注意力模型\[J\].计算机工程与应用,2021,57(20):150-156.FU Guodong,HUANG Jin,YANG Tao,et,al.Improved lightweight attention model of CBAM\[J\]Computer Engineering and Applications,2021,57(20):150-156.
［12］ZHAO B J,ZHAO B Y,TANG L B,et al.Multiscale object detection by top-down and bottom-up feature pyramid network［J］.Journal of Systems Engineering and Electronics,2019,30(1):1-12.
［13］CHEN Y,FU Q,WANG G.Surface Defect Detection of Nonburr Cylinder Liner Based on Improved YOLOv4\[J\].Mobile Information Systems,2021,2021(9):1-13.
［14］WEI S,QU Q,WU Y,et al.PRI modulation recognition based on squeeze and excitation networks［J］.IEEE Communications Letters,2020,PP(99):1-1.
［15］KALSOTRA,RIDRIKA,ARORA,et.al.Background subtraction for moving object detection: explorations of recent developments and challenges［J］.The Visual Computer,2021:1-28.
［16］JIANG Y,JIN Z,ZHAO T,et al.Strain field of reinforced concrete under accelerated corrosion by digital image correlation technique［J］.Journal of Advanced Concrete Technology,2017,15(7):290-299.
［17］JU J H,XING J S.Moving object detection based on smoothing three frame difference method fused with RPCA［J］.Multimedia Tools and Applications,2019,78(21):29937-29951.
［18］江平,刘民士.射线法判断点与包含简单曲线多边形关系的完善［J］.测绘科学,2009,34(5):220-222.JIANG Ping,LIU Minshi.Improvement of the relation between points and polygons containing simple curves by ray method ［J］.Science of Surveying and Mapping,2009,34(5):220-222.
［19］EVERINGHAM M,ESLAMI S M,VAN GOOL L,et al. The pascal visual object classes challenge:A retrospective［J］.International Journal of Computer vision,2015,111(1):98-136.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-06-21
* 基金项目： 国家自然科学基金项目（61502094）；黑龙江省省属本科高校基本科研业务费项目（KYCXTD201903，2020YDL-11）；东北石油大学研究生教育创新工程项目（JYCX_11_2020）
作者简介： 田枫，博士，教授，主要研究方向为计算机视觉。
通信作者： 刘芳，博士研究生，副教授，主要研究方向为计算机视觉。
