|本期目录/Table of Contents|

[1]赵杰,汪洪法,吴凯.基于特征增强及多层次融合的火灾火焰检测[J].中国安全生产科学技术,2024,20(1):93-99.[doi:10.11731/j.issn.1673-193x.2024.01.014]
　ZHAO Jie,WANG Hongfa,WU Kai.Fire flame detection based on feature enhancement and multi-level fusion[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(1):93-99.[doi:10.11731/j.issn.1673-193x.2024.01.014]
点击复制

基于特征增强及多层次融合的火灾火焰检测
分享到：

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

卷:
20
期数:
2024年1期
页码:
93-99
栏目:
职业安全卫生管理与技术
出版日期:
2024-01-31

文章信息/Info

Title:
Fire flame detection based on feature enhancement and multi-level fusion
文章编号:
1673-193X(2024)-01-0093-07
作者:
赵杰; 汪洪法; 吴凯
（1.晋中职业技术学院，山西 晋中 030600;
2.太原理工大学，山西 太原 030024）
Author(s):
ZHAO Jie;  WANG Hongfa;  WU Kai
(1.Jinzhong Vocational and Technical College,Jinzhong Shanxi 030600,China;
2.Taiyuan University of Technology,Taiyuan Shanxi 030024,China)
关键词:
火灾火焰检测; 神经网络; 特征增强; 多层次融合; 自适应多尺度
Keywords:
fire flame detection;  neural network;  feature enhancement;  multi-level fusion;  adaptive multi-scale
分类号:
TP391.4;X932
DOI:
10.11731/j.issn.1673-193x.2024.01.014
文献标志码:
A
摘要:
为提升火灾火焰识别检测方法性能，将传统图像处理与神经网络结合，提出1种基于特征增强及多层次融合的轻量级火灾火焰检测模型。模型利用多种色彩空间转换算法增强火焰特征信息，并设计双阶段多层次特征提取融合结构，配合空间注意力机制对火焰信息由粗到精进行提取；同时，针对火灾火焰特点，引入由浅到深逐步融合的自适应多尺度融合结构，提升对不同阶段火灾目标的检测精度。研究结果表明：本文模型可有效提升火灾火焰的检测效果，且具有更高的稳定性和鲁棒性，可准确高效地实现火灾火焰检测。研究结果可为现有火灾检测设备提供更准确的识别结果，从而更好地预防火灾事故发生。
Abstract:
In order to improve the recognition and detection performance of fire flame methods,a lightweight fire flame detection model based on feature enhancement and multi-level fusion was proposed by combining traditional image processing with neural network.Multiple color space conversion algorithms were used in the model to enhance the flame feature information,and a two-stage multi-level feature extraction fusion structure was designed,which was combined with spatial attention mechanism to extract the flame information from rough to fine.At the same time,based on the characteristics of fire flame,an adaptive multi-scale fusion structure that gradually integrated from shallow to deep was introduced to improve the detection accuracy of fire objects in different stages.The results show that the proposed model can effectively improve the detection effect of fire flame,and has higher stability and robustness,which can accurately and efficiently achieve the fire flame detection.The research results can provide more accurate identification results for existing fire detection equipment,so as to better prevent fire accidents.

参考文献/References:

［1］曹江涛,秦跃雁,姬晓飞.基于视频的火焰检测算法综述［J］.数据采集与处理,2020,35(1):35-52. CAO Jiangtao,QIN Yueyan,JI Xiaofei.Review on video based flame detection algorithm［J］.Journal of Data Acquisition and Processing,2020,35(1):35-52.
［2］刘洪涛.基于视觉图像的火灾检测算法研究与实现［D］.秦皇岛：燕山大学,2021.
［3］KHAN F,XU Z,SUN J,et al.Recent advances in sensors for fire detection［J］.Sensors,2022,22(9):3310.
［4］恽新星,褚新惠,官洪运.基于光纤传感的火灾检测技术［J］.仪表技术与传感器,2006(9):59-60. YUN Xinxing,CHU Xinhui,GUAN Hongyun.Fire detection technology based on fiber-optic sensor［J］.Instrument Technique and Sensor,2006(9):59-60.
［5］WANG X,LI Y,LI Z.Research on flame detection algorithm based on multi-feature fusion［C］//2020 IEEE 4th Information Technology,Networking,Electronic and Automation Control Conference (ITNEC).IEEE,2020,1:184-189.
［6］缪伟志,陆兆纳,王俊龙,等.基于视觉的火灾检测研究［J］.森林工程,2022,38(1):86-92. MIAO Weizhi,LU Zhaona,WANG Junlong,et al.Fire detection research based on vision［J］.Forest Engineering,2022,38(1):86-92.
［7］王生营.基于计算机视觉的森林火灾检测算法研究［D］.宁夏：北方民族大学,2021.
［8］TOPTA�瘙塁 B,HANBAY D.A new artificial bee colony algorithm-based color space for fire/flame detection［J］.Soft Computing,2020,24(14):10481-10492.
［9］张建东,刘学君,沙芸,等.基于改进图像多特征的危化品火灾检测算法［J］.自动化与仪表,2021,36(8):52-57. ZHANG Jiandong,LIU Xuejun,SHA Yun,et al.Dangerous chemicals fire detection algorithm based on improved image multi features ［J］.Automation & Instrumentation,2021,36(8):52-57.
［10］王林,赵红.改进YOLOv3的火灾检测［J］.计算机系统应用,2022,31(4):143-153. WANG Lin,ZHAO Hong.Fire detection based on improved YOLOv3 ［J］.Computer Systems & Applications,2022,31(4):143-153.
［11］WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:2023:7464-7475.
［12］张融,张为.基于改进GhostNet-FCOS的火灾检测算法［J］.浙江大学学报（工学版）,2022,56(10):1891-1899. ZHANG Rong,ZHANG Wei.Fire detection algorithm based on improved GhostNet-FCOS ［J］.Journal of Zhejiang University (Engineering Science),2022,56 (10):1891-1899.
［13］汪子健,高焕兵,侯宇翔,等.改进YOLOX-nano的火灾火焰烟雾检测［J］.计算机系统应用,2023(1):3-12. WANG Zijian,GAO Huanbing,HOU Yuxiang,et al.Flame and smoke detection of fires based on improved YOLOX-nano［J］.Computer Systems & Applications,2023(1):3-12.
［14］张剑飞,柯赛.改进YOLOX火灾场景检测方法的研究［J］.计算机与数字工程,2022,50(2):318-322,349. ZHANG Jianfei,KE Sai.Research on improved YOLOX fire scene detection method［J］.Computer & Digital Engineering,2022,50(2):318-322,349.
［15］RYU J,KWAK D.Flame detection using appearance-based pre-processing and Convolutional Neural Network［J］.Applied Sciences,2021,11(11):5138.
［16］SHAHID M,CHIEN I F,SARAPUGDI W,et al.Deep spatial-temporal networks for flame detection［J］.Multimedia Tools and Applications,2021,80:35297-35318.
［17］DUNNINGS A J,BRECKON T P.Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection［C］//2018 25th IEEE international conference on image processing (ICIP).IEEE,2018:1558-1562.
［18］KWAK J,NAM J.Wildfire smoke detection using temporospatial features and random forest classifiers［J］.Optical Engineering,2012,51(1):7208.
［19］CUI C,GAO T,WEI S,et al.PP-LCNet:A lightweight CPU convolutional neural network［J］.arXiv preprint arXiv,2021:2109.15099.
［20］HU J,SHEN L,SUN G.Squeeze-and-excitation networks［C］//Proceedings of the IEEE conference on computer vision and pattern recognition.2018:7132-7141.
［21］WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional block attention module［C］//Proceedings of the European conference on computer vision (ECCV).2018:3-19.

相似文献/References:

[1]欧韬,周长春.基于神经网络的民航安全态势评估模型及仿真[J].中国安全生产科学技术,2011,7(2):34.
　OU Tao,ZHOU Chang chun.Situation assessment model of civil aviation safety based on neural network and its simulation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(1):34.
[2]周忠科,王立杰.基于BP神经网络的煤矿安全预警评估机制研究[J].中国安全生产科学技术,2011,7(4):134.
　ZHOU Zhong-ke,?WANG Li-jie.Study on safety early-warning assessment in coal mine based on bp neural networks[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(1):134.
[3]王以恒.基于BP神经网络算法的北京市地铁站应急疏散能力仿真评估模型[J].中国安全生产科学技术,2012,8(1):5.
　WANG Yi-heng.Virtual assessment model on emergency evacuation capacity of Beijing subway based on BP neural network algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(1):5.
[4]甘旭升,端木京顺,丛伟,等.基于支持向量机的飞行安全隐患危险性评价[J].中国安全生产科学技术,2010,6(3):206.
　GAN Xu-sheng,DUANMU Jing-shun,CONG Wei,et al.Fatalness assessment of flight safety hidden danger based on support vector machine[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(1):206.
[5]周瑾.基于神经网络的建筑物火险评价[J].中国安全生产科学技术,2013,9(10):177.[doi:10.11731/j.issn.1673-193x.2013.10.032]
　ZHOU Jin.Fire risk assessment for buildings based on neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(1):177.[doi:10.11731/j.issn.1673-193x.2013.10.032]
[6]刘海滨,李光荣,刘 欢,等.基于ART-2人工神经网络的煤矿安全风险评价[J].中国安全生产科学技术,2014,10(2):81.[doi:10.11731/j.issn.1673-193x.2014.02.014]
　LIU Hai bin,LI Guang rong,LIU Huan,et al.Coal mine safety risk assessment based on ART2 neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(1):81.[doi:10.11731/j.issn.1673-193x.2014.02.014]
[7]杜燮祎,张敏,王颖,等.基于改进BP神经网络的职业危害预警模型*[J].中国安全生产科学技术,2009,5(5):63.
　DU Xie yi,ZHANG Min,WANG Ying,et al.The early warning model for occupational hazards based on improved BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2009,5(1):63.
[8]于瓅,刘泽功.基于神经网络模型的燃料空气混合物爆炸威力预测研究[J].中国安全生产科学技术,2015,11(9):83.[doi:10.11731/j.issn.1673-193x.2015.09.013]
　YU Li,LIU Ze-gong.Prediction on explosion power of fuel air mixture based on neural network model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(1):83.[doi:10.11731/j.issn.1673-193x.2015.09.013]
[9]邓力,刘全义,胡林,等.基于BP神经网络的受限空间火灾联合探测方法[J].中国安全生产科学技术,2020,16(1):158.[doi:10.11731/j.issn.1673-193x.2020.01.026]
　DENG Li,LIU Quanyi,HU Lin,et al.Joint detection method of fire in confined space based on BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(1):158.[doi:10.11731/j.issn.1673-193x.2020.01.026]
[10]司旭彤,张希恒,赵佳,等.基于神经网络的闸阀模糊可靠度计算[J].中国安全生产科学技术,2021,17(2):123.[doi:10.11731/j.issn.1673-193x.2021.02.019]
　SI Xutong,ZHANG Xiheng,ZHAO Jia,et al.Fuzzy reliability calculation of gate valve based on neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(1):123.[doi:10.11731/j.issn.1673-193x.2021.02.019]

备注/Memo

备注/Memo:
收稿日期： 2023-08-08
作者简介： 赵杰，硕士，副教授，主要研究方向为图像处理，计算机网络应用，智能系统。
更新日期/Last Update: 2024-02-19