基于视频时序特征的多模态隧道火灾检测

doi:10.3969/j.issn.1006-2475.2025.09.012

计算机与现代化 ›› 2025, Vol. 0 ›› Issue (09): 79-89.doi: 10.3969/j.issn.1006-2475.2025.09.012

基于视频时序特征的多模态隧道火灾检测

（1.长安大学信息工程学院，陕西西安 710018； 2.长安大学电子与控制工程学院，陕西西安 710018）

出版日期:2025-09-24 发布日期:2025-09-24
作者简介: 作者简介：杨添顺（2000—），男，河北秦皇岛人，硕士研究生，研究方向:计算机视觉，E-mail: 2022124084@chd.edu.cn；宋焕生（1964—），男，陕西西安人，教授，博士生导师，博士，研究方向:图像/视频技术，E-mail: hshsong@chd.edu.cn；通信作者:梁浩翔（1995—），男，陕西西安人，讲师，博士，研究方向:计算机视觉，E-mail: lhx@chd.edu.cn；刘浩楠（2000—），男，陕西榆林人，硕士研究生，研究方向:计算机视觉，E-mail: haonanliu@chd.edu.cn；马辛洲（2000—），男，陕西西安人，硕士研究生，研究方向:计算机视觉，E-mail: m1519032743@163.com；孙士杰（1989—），男，陕西西安人，副教授，硕士生导师，博士，研究方向:计算机视觉，E-mail: shijiesun@chd.edu.cn；张绍阳（1971—），男，陕西西安人，教授，硕士生导师，博士，研究方向:交通信息大数据理论，交通信息标准化，E-mail: zhsy@chd.edu.cn。
基金资助:
基金项目：国家重点研发计划项目（2023YFB4301800）；国家自然科学基金资助项目（62072053）；中国高校产学研创新基金新一代信息技术创新项目（2022IT041）；国家资助博士后研究人员计划项目（GZC20241447）

Multimodal Tunnel Fire Detection Based on Temporal Features of Video

（1. School of Information Engineering， Chang’an University， Xi’an 710018， China；
2. School of Electronics and Control Engineering， Chang’an University， Xi’an 710018， China）

Online:2025-09-24 Published:2025-09-24

摘要/Abstract

摘要：
摘要：隧道环境封闭且狭小，一旦发生火灾，火势蔓延和有害气体产生将严重威胁生命和财产安全。现有基于单帧图像的隧道火灾检测方法难以准确区分火焰与类似火焰的灯光。为解决这一问题，本文提出一种基于YOLOV网络的多帧序列特征提取方法，利用视频序列中目标的动态特征变化，设计VSDFD模块，通过相邻间隔帧的特征相似度来区分火焰与灯光。此外，结合温度传感器采集的环境温度信息，采用DST证据理论及其推导方法TBM，提出一种MFD多模态融合方法，用于计算火灾发生概率，实现隧道火灾检测。实验结果表明，VSDFD模块在区分火焰和灯光方面表现出显著效果，MFD方法在误检情况下将融合概率控制在0.5以下，而在火灾场景中融合概率则保持在0.5以上。与其他方法相比，本文方法在检测精度上平均提高了2.8百分点，漏检率降低了2.7百分点，误检率降低了5.2百分点，在多种实际隧道火灾情况下的实验，验证了本文方法检测火灾的准确性。

关键词: 关键词：隧道火灾检测, 视频序列动态特征, 多模态融合, YOLOV网络

Abstract: Abstract: The tunnel environment is closed and narrow， and once a fire occurs， the fire spread and harmful gas generation will seriously threaten the safety of life and property. Existing tunnel fire detection methods based on single-frame images often struggle to accurately distinguish between flames and flame-like light sources. To address this issue， a multi-frame sequence feature extraction method based on the YOLOV network is proposed， which utilizes the dynamic feature variations of targets in video sequences. The VSDFD module is designed to differentiate between flames and light sources by analyzing the feature similarity of adjacent interval frames. In addition， combined with the ambient temperature information collected by the temperature sensor， an MFD multi-mode fusion method is proposed by using DST evidence theory and its derivation method TBM， which is used to calculate the fire probability and realize the tunnel fire detection. The experimental results show that the VSDFD module significantly improves the ability to distinguish between flames and light sources. The MFD method effectively controls the fusion probability below 0.5 in cases of false alarms， while maintaining the probability above 0.5 in fire scenarios. Compared with other methods， the proposed approach achieves an average improvement of 2.8 percentage points in detection accuracy， a 2.7 percentage points reduction in the missed detection rate， and a 5.2 percentage points decrease in the false detection rate. Experiments in various real tunnel fire scenarios verified the accuracy of the proposed method in fire detection.

Key words: Key words: tunnel fire detection, dynamic features of video sequences, multimodal fusion, YOLOV network

中图分类号:

中图分类号：TP391

杨添顺1, 宋焕生1, 梁浩翔2, 刘浩楠1, 马辛洲1, 孙士杰1, 张绍阳1. 基于视频时序特征的多模态隧道火灾检测[J]. 计算机与现代化, 2025, 0(09): 79-89.

YANG Tianshun1, SONG Huansheng1, LIANG Haoxiang2, LIU Haonan1, MA Xinzhou1, SUN Shijie1, ZHANG Shaoyang1. Multimodal Tunnel Fire Detection Based on Temporal Features of Video[J]. Computer and Modernization, 2025, 0(09): 79-89.

参考文献

［1］交通运输部. 2022年交通运输行业发展统计公报［N］. 中国交通报， 2023-06-16.
［2］曾旭阳，孙卡. 基于DI-Guy的校园消防训练仿真［J］. 计算机与现代化， 2021（8）:35-39.
［3］徐鹏，任波. 基于单高斯模型的森林火灾烟图像目标检测［J］. 计算机与现代化， 2009（2）:18-20.
［4］张永梅，杜国平，邢阔. 一种快速火灾识别方法［J］. 计算机与现代化， 2016（3）:58-63.
［5］ VENKATARAMANAN V， KAVITHA G， JOEL M R， et al. Forest fire detection and temperature monitoring alert using iot and machine learning algorithm［C］// 2023 5th International Conference on Smart Systems and Inventive Technology. IEEE， 2023:17-23.
［6］ CHMELAR P， BENKRID A. Efficiency of HSV over RGB Gaussian mixture model for fire detection［C］// 2014 24th International Conference Radioelektronika. IEEE， 2014:1-4.
［7］ WAHYONO， HARJOKO A， DHARMAWAN A， et al. Real-time forest fire detection framework based on artificial intelligence using color probability model and motion feature analysis［J］. Robotics & Machine Learning Daily News， 2022（15）:61-62.
［8］ YUAN C， LIU Z， ZHANG Y. Fire detection using infrared images for UAV-based forest fire surveillance［C］// 2017 International Conference on Unmanned Aircraft Systems （ICUAS）. ACM， 2017:876-889.
［9］ KO B C， CHEONG K H， NAM J Y. Fire detection based on vision sensor and support vector machines［J］. Fire Safety Journal， 2009，44（3）:322-329.
［10］陆雅诺，陈炳才. 融合注意力机制的无锚点森林火灾检测算法［J］. 计算机与现代化， 2021（11）:61-66.
［11］傅天驹，郑嫦娥，田野，等. 复杂背景下基于深度卷积神经网络的森林火灾识别［J］. 计算机与现代化， 2016（3）:52-57.
［12］ LI P L，ZHANG J W，LI W. Smoke detection method based on optical flow improvement and YOLOv3［J］. Journal of Zhejiang University of Technology， 2021，49（1）:9-15.
［13］ LIN J， LIN H F， WANG F. A. Semi-supervised method for real-time forest fire detection algorithm based on adaptively spatial feature fusion［J］. Forests， 2023，14（2）:361-368.
［14］ MUHAMMAD K， KHAN S， ELHOSENY M， et al. Efficient fire detection for uncertain surveillance environment［J］. IEEE Transactions on Industrial Informatics， 2019，15（5）:3113-3122.
［15］ BARMPOUTIS P， DIMITROPOULOS K， KAZA K， et al. Fire detection from images using faster R-CNN and multidimensional texture analysis［C］// 2019 IEEE International Conference on Acoustics， Speech and Signal Processing. IEEE， 2019:1047-1058.
［16］王艺成，张国良，张自杰. 基于改进YOLOv5的小目标检测方法［J］. 计算机与现代化， 2023（5）:100-105.
［17］ SHI Y H， WANG N Y， GUO X J. YOLOV: Making still image object detectors great at video object detection［EB/OL］. （2023-05-05）［2024-02-08］. https://arxiv.org/abs/2208.09686.
［18］ SHAFER G. A Mathematical Theory of Evidence［M］. England: Princeton University Press， 1976:95-113.
［19］ SMETS P， KENNES R. The transferable belief model［M］// Classic Works of the Dempster-Shafer Theory of Belief Functions， Studies in Fuzziness and Soft Computing. Spring， 2008:693-736.
［20］ GE Z， LIU S T， WANG F， et al. YOLOX: Exceeding YOLO Series in 2021［EB/OL］. （2021-08-06）［2024-02-10］. https://arxiv.org/abs/2107.08430.
［21］ WANG C Y， MARK LIAO H Y， WU Y H， et al. CSPNet: A new backbone that can enhance learning capability of CNN［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. IEEE， 2020:1571-1580.
［22］ KIM S W， KOOK H K， SUN J Y， et al. Parallel feature pyramid network for object detection［C］// Computer Vision-ECCV 2018， Lecture Notes in Computer Science. Springer， 2018:239-256.
［23］ LIU S， QI L， QIN H F， et al. Path aggregation network for instance segmentation［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2018:8759-8768.
［24］ TIAN Z， SHEN C H， CHEN H， et al. FCOS: Fully convolutional one-stage object detection［C］// 2019 IEEE/CVF International Conference on Computer Vision. IEEE， 2019:9626-9639.
［25］ ZHANG Y F， REN W， ZHANG Z， et al. Focal and efficient IOU loss for accurate bounding box regression［J］. Neurocomputing， 2022，506:146-157.
［26］ GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2014 :580-587.
［27］ REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN: Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017，39（6）:1137-1149.
［28］ DAI J F， LI Y， HE K M， et al. R-FCN: Object detection via region-based fully convolutional networks［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. ACM， 2016:379-387.
［29］ HE K M， GKIOXARI G， DOLLÁR P， et al. Mask R-CNN［C］// 2017 IEEE International Conference on Computer Vision. IEEE， 2020:386-397.
［30］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［EB/OL］. （2023-08-02）［2024-1-19］. https://arxiv.org/abs/1706.03762.
［31］ HU H， GU J Y， ZHANG Z， et al. Relation networks for object detection［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018:1156-1164.
［32］ DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16×16 words: Transformers for image recognition at scale［J］. arXiv preprint arXiv:2010.11929， 2020.
［33］ RUSSELL B C， TORRALBA A， MURPHY K P， et al. LabelMe: A database and web-based tool for image annotation［J］. International Journal of Computer Vision， 2008，77:157-173.
［34］ LI S B， YAN Q D， LIU P. An efficient fire detection method based on multiscale feature extraction， implicit deep supervision and channel attention mechanism［J］. IEEE Transactions on Image Processing， 2020，29:8467-8475.
［35］ MAJID S， ALENEZI F， MASOOD S， et al. Attention based CNN model for fire detection and localization in real-world images［J］. Expert Systems with Applications， 2022，189. DOI: 10.1016/j.eswa.2021.116114.
［36］ LI P， ZHAO W D. Image fire detection algorithms based on convolutional neural networks［J］. Case Studies in Thermal Engineering， 2020，19. DOI: 10.1016/j.csite.2020.100625.
［37］ KIM B， LEE J. A Bayesian network-based information fusion combined with DNNs for robust video fire detection［J］. Applied Sciences， 2021，11（16）. DOI: 10.3390/app
11167624.
［38］ ABDEL-ZAHER M， HISHAM M， YOUSRI R， et al. Light-weight convolutional neural network for fire detection［C］// 2021 IEEE International Conference on Electronic Engineering. IEEE， 2021:1-5.

[1]	翟俊龙, 谷林. 基于文本引导的多模态情绪识别[J]. 计算机与现代化, 2025, 0(07): 83-89.
[2]	韦云松1, 2, 李加强1, 2, 何超1, 2, 3, 于海生1, 2, 陈彦林1, 2, 赵龙庆1, 2, 魏荣琨1, 2. 智能驾驶中基于视觉信息与LiDAR的3D目标检测方法研究进展[J]. 计算机与现代化, 2025, 0(05): 91-102.
[3]	黄文栋, 王怡凡. 基于模态类别的多模态信息处理与融合综述[J]. 计算机与现代化, 2024, 0(07): 47-62.
[4]	杨娟, 滕飞, 郭大林. 多模态融合的特征提取方法在SA检测中的应用[J]. 计算机与现代化, 2022, 0(10): 121-126.
[5]	梅欣, 缪梓敬. 拥抱融合的多模态灾害分析算法[J]. 计算机与现代化, 2022, 0(10): 82-87.

基于视频时序特征的多模态隧道火灾检测

Multimodal Tunnel Fire Detection Based on Temporal Features of Video

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价