|本期目录/Table of Contents|

[1]沈昊旸,于海洋,徐晴晴,等.基于子块匹配法与改进FRFCM的气体泄漏红外图像增强方法*[J].中国安全生产科学技术,2025,21(2):130-138.[doi:10.11731/j.issn.1673-193x.2025.02.017]
　SHEN Haoyang,YU Haiyang,XU Qingqing,et al.Infrared image enhancement method of gas leakage based on sub-block matching method and improved FRFCM[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2025,21(2):130-138.[doi:10.11731/j.issn.1673-193x.2025.02.017]
点击复制

基于子块匹配法与改进FRFCM的气体泄漏红外图像增强方法*
分享到：

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

卷:
21
期数:
2025年2期
页码:
130-138
栏目:
职业安全卫生管理与技术
出版日期:
2025-02-28

文章信息/Info

Title:
Infrared image enhancement method of gas leakage based on sub-block matching method and improved FRFCM
文章编号:
1673-193X(2025)-02-0130-09
作者:
沈昊旸; 于海洋; 徐晴晴; 董绍华; 王明月; 陈俪赟
(1.中国石油大学（北京） 碳中和示范性能源学院，北京 102249；
2.中国石油大学（北京） 安全与海洋工程学院，北京 102249；
3.中国石油大学（北京） 管道技术与安全研究中心，北京 102249；
4.东北石油大学应用技术研究院，黑龙江 大庆 163318；
5.广州科易光电技术有限公司，广东 广州 510720)
Author(s):
SHEN Haoyang;  YU Haiyang;  XU Qingqing;  DONG Shaohua;  WANG Mingyue;  CHEN Liyun
(1.College of Carbon Neutral Energy,China University of Petroleum (Beijing),Beijing 102249,China;
2.College of Safety and Ocean Engineering,China University of Petroleum (Beijing);
3.Pipeline Technology and Safety Research Center,China University of Petroleum (Beijing);
4.Applied Technology Research Institute,Northeast Petroleum University,Daqing Heilongjiang 163318,China;
5.Guangzhou Keyi Optoelectronics Technology Co.,Ltd.,Guangzhou Guangdong 510720,China)
关键词:
羽流增强; 红外气体泄漏; FRFCM; 子块匹配法; 背景差分
Keywords:
plume enhancement;  infrared gas leakage;  FRFCM;  sub-block matching method;  background differencing
分类号:
X913
DOI:
10.11731/j.issn.1673-193x.2025.02.017
文献标志码:
A
摘要:
为应对红外气体泄漏成像过程中因设备转动等因素导致的图像不稳定及泄漏气体检测效果不佳的问题，提出1种结合图像帧子块匹配法和改进快速鲁棒模糊C均值算法(fast and robust fuzzy c-means,FRFCM)的红外图像细节增强方法。该方法利用图像帧子块匹配法配准图像帧，同时引入背景建模和差分方法从背景中分离动态气体目标，并在FRFCM基础上增加自适应调整模糊因子以优化图像帧的羽流强化特征效果。研究结果表明：该方法能够有效去除冗余信息，使图像帧匹配误差降低约75%，对比度增强值提高4.7%，羽流分割的平均交并比达到0.68，在保持较高分割准确度的同时显著提升检测速度，适用于油气田、集输站及氢气站等气体安全检测系统。研究结果可为气体泄漏监测技术的优化与应用提供参考。
Abstract:
To address the issues of image instability and poor effect of gas leakage detection caused by the equipment rotation during the process of infrared gas imaging,an infrared image detail enhancement method combining the sub-block matching method for image frame and an improved Fast and Robust Fuzzy C-Means (FRFCM) algorithm was proposed.The sub-block matching method for image frame was used for image frame registration,and the background modeling and differencing method were used to separate the dynamic gas targets from the background.Additionally,a self-adaptive adjustment fuzzy factor was incorporated into the FRFCM algorithm to optimize the plume enhancement characteristics effect of image frame.The results show that this method can effectively remove the redundant information,reducing the matching error of image frame by approximately 75%,increasing the contrast enhancement by 4.7%,and achieving a mean intersection over union (IoU) of 0.68 for plume segmentation.The proposed method not only maintains high segmentation accuracy,but also significantly improves the detection speed,making it suitable for gas safety monitoring systems in the facilities such as oil fields,gathering stations,and hydrogen stations.The research results can provide reference for the optimization and application of gas leakage monitoring technology.

参考文献/References:

［1］张发旺,张磊,张立新,等.乙烯厂储运联合车间储罐区VOCs气体收集及管控措施［J］.石油化工安全环保技术,2019,35(6):66-72,7.ZHANG Fawang,ZHANG Lei,ZHANG Lixin,et al.VOCs gas collection and control measures in the tank area of the combined storage and transportation workshop of ethylene plant［J］.Petrochemical Safety and Environmental Protection Technology,2019,35(6):66-72,7.
［2］PAN D,HUO Y.Risk analysis on oil and gas leakage accident in offshore oil & gas field engineer［J］.Marine Environmental Science,2009,28(4)：426-429.
［3］ZHAO L,CAO Z,DENG J.A review of leak detection methods based on pressure waves in gas pipelines［J］.Measurement,2024:115062.
［4］洪少壮.基于视觉的红外气体泄漏检测算法研究［D］.大连：大连海事大学,2020.
［5］CHANG C C,HSIAO J Y,HSIEH C P.An adaptive median filter for image denoising［C］//2008 Second International Symposium on Intelligent Information Technology Application.IEEE,2008,2:346-350.
［6］BINBIN Y.An improved infrared image processing method based on adaptive threshold denoising［J］.EURASIP Journal on Image and Video Processing,2019,2019(1):5.
［7］ZHANG Q,XIAO J,TIAN C,et al.A robust deformed convolutional neural network (CNN) for image denoising［J］.CAAI Transactions on Intelligence Technology,2023,8(2):331-342.
［8］CHEN S,SHI D,SADIQ M,et al.Image denoising with generative adversarial networks and its application to cell image enhancement［J］.IEEE Access,2020,8:82819-82831.
［9］FU W,XING G，RETRACTED ARTICLE.A modified edge-oriented spatial interpolation algorithm for consecutive blocks error concealment［J］.Journal of Electronics (China),2007,24:214-217.
［10］WANG T S,KANG S J,BYUN K Y,et al.Robust global motion estimation for video stabilization［C］//The 1st IEEE Global Conference on Consumer Electronics 2012,Tokyo,Japan,2012:623-624.
［11］SHI Z,SHI F,LAI W S,et al.Deep online fused video stabilization［C］//Proceedings of the IEEE/CVF winter conference on applications of computer vision,2022:1250-1258.
［12］XU S,HU J,WANG M,et al.Deep video stabilization using adversarial networks［J］.Computer Graphics Forum,2018,37(7):267-276.
［13］孔松涛,谢义,王松,等.红外热像增强方法发展研究综述［J］.重庆科技学院学报(自然科学版),2021,23(4):77-83.KONG Songtao，XIE Yi，WANG Song,et al.A review of the development of infrared thermal imaging enhancement methods［J］.Journal of Chongqing University of Science and Technology (Natural Science Edition),2021,23(4):77-83.
［14］LI S,JIN W,LI L,et al.An improved contrast enhancement algorithm for infrared images based on adaptive double plateaus histogram equalization［J］.Infrared Physics and Technology,2018,90:164-174.
［15］ZHANG H,QIAN W,WAN M,et al.Infrared image enhancement algorithm using local entropy mapping histogram adaptive segmentation［J］.Infrared Physics & Technology,2022,120:104000.
［16］ZHAO Q,NIE X,LUO D,et al.An effective method for gas-leak area detection and gas identification with mid-infrared image［C］//Photonics.MDPI,2022,9(12):992.
［17］WANG Y,HUANG L,CHENG Z,et al.Flow faster RCNN:deep learning approach for infrared gas leak eetection in complex chemical plant surroundings［C］//2023 42nd Chinese Control Conference (CCC).IEEE,2023:7823-7830.
［18］HUANG E,CHEN L,LV T,et al.GLRNet:gas leak recognition via temporal difference in infrared video［C］//CAAI International Conference on Artificial Intelligence.Cham:Springer Nature Switzerland,2022:515-520.
［19］WANG Q,XING M,SUN Y,et al.Optical gas imaging for leak detection based on improved DeepLabv3+model［J］.Optics and Lasers in Engineering,2024,175:108058.
［20］SHIRLEY C P,RAJA J I J,EVANGELIN SONIA S V,et al.Recognition and monitoring of gas leakage using infrared imaging technique with machine learning［J］.Multimedia Tools and Applications,2024,83(12):35413-35426.
［21］张跃飞.车载摄像机数字稳像技术研究［D］.成都：电子科技大学,2011.
［22］TAO L,XIAOHONG J,YANNING Z,et al.Significantly fast and robust fuzzy c-means clustering algorithm based on morphological reconstruction and membership filtering［J］.IEEE Transactions on Fuzzy Systems,2018,26(5):3027-3041.
［23］ZHOU K,WANG Y,LV T,et al.Explore spatio-temporal aggregation for insubstantial object detection:benchmark dataset and baseline［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2022:3104-3115.
［24］REYNOLDS D A.Gaussian mixture models［J］.Encyclopedia of Biometrics,2009,741:659-663.
［25］ROMERA E,ALVAREZ J M,BERGASA L M,et al.Erfnet:efficient residual factorized convnet for real-time semantic segmentation［J］.IEEE Transactions on Intelligent Transportation Systems,2017,19(1):263-272.
［26］HUANG H,LIN L,TONG R,et al.Unet 3+:a full-scale connected unet for medical image segmentation［C］//ICASSP 2020-2020 IEEE international conference on acoustics,speech and signal processing (ICASSP).IEEE,2020:1055-1059.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2024-09-19
* 基金项目： 中国石油科技创新基金研究项目（2021DQ02-0801）
作者简介： 沈昊旸，本科生，主要研究方向为计算机视觉。
通信作者： 徐晴晴，博士，讲师，主要研究方向为储气库设备完整性评价技术。
更新日期/Last Update: 2025-03-04