The Design of Multi⁃Channel Flame Intelligent Monitoring System Based on B/S Architecture

doi:10.12422/j.issn.1672-6952.2025.02.011

Abstract

Abstract:

As a high?risk area, the fire safety has always attracted much attention. Although smoke and flame alarm have been widely used, there are still problems such as single ?point detection and easy environmental impact. In response to such problems, a multi?way flame smart video monitoring system based on the B/S architecture is designed and implemented, and it is presented in the form of a web system. In the system, an improved YOLOV5 flame detection algorithm is integrated. The Ghost convolution is used to replace in conventional convolution to achieve the lightweight of the network, and the improved attention mechanism modules and small target detection anchor frame is added to enhance small target detection ability. Finally, the flame movement information extracted from the Optical flow network and the original flame data is sent into the improved YOLOV5 flame detection algorithm to further improve the detection accuracy of the flame. A large number of on?site test proves that the system can identify and locate the flames in the plant in real time. The detecting frame rate can reach 15 ms/frame, and the detection rate reaches 100%, which has high stability. An efficient and reliable fire monitoring solution is provided for the chemical industry.

Key words: Flame detection, B/S architecture, Computer vision, Sports information, Monitoring system

摘要：

在化工厂这类高风险地区，火灾安全始终备受关注。尽管烟雾及火焰报警器已被广泛应用，但仍然存在只用于单点检测以及易受环境影响等问题。针对此类问题，设计并实现了一种基于B/S架构的化工厂区多路火焰智能视频监控系统，并以Web系统的形式呈现。首先，系统中集成了一种改进的YOLOv5火焰检测算法，该算法用Ghost卷积替换常规卷积以实现网络的轻量化；其次，添加改进的注意力机制模块和小目标检测锚框来增强小目标检测能力；最后，将由光流网络提取的火焰运动信息与原始火焰数据进行融合送入改进的YOLOv5火焰检测算法中，进一步提高对火焰的检测精度。大量的现场测试表明，该系统能够实时识别和定位厂区内火焰，检测帧率可达15 ms/帧，检出率达到100%，具有较高的稳定性，可为化工行业提供一种高效、可靠的火灾监测解决方案。

关键词: 火焰检测, B/S架构, 计算机视觉, 运动信息, 监控系统

CLC Number:

TP391.1

Ming BAN, Pengwei TIAN, Jiangtao CAO. The Design of Multi⁃Channel Flame Intelligent Monitoring System Based on B/S Architecture[J]. Journal of Liaoning Petrochemical University, 2025, 45(2): 83-89.

班铭, 田鹏伟, 曹江涛. 基于B/S架构的多路火焰智能监控系统设计[J]. 辽宁石油化工大学学报, 2025, 45(2): 83-89.

Figures/Tables 8

Fig.1 The overall design of the system

Fig.2 The topological structure of the multi?channel intelligent flame video monitoring system

Fig.3 The architecture diagram after camera detection optimization

Fig.4 The structure diagram of RAFT

Fig.5 Flame data fused with optical flow information

Fig.6 Some experimental data diagrams

Table 1 Results of ablation experiments

算法	精确率	召回率	平均精度均值	参数量	帧率/(ms·帧^-1)
YOLOv5	0.844	0.801	0.829	7 012 822	9.5
YOLOv5⁃ghost	0.825	0.812	0.812	3 675 726	10.3
YOLOv5⁃Ghost+小目标锚框	0.797	0.818	0.818	3 675 726	10.0
YOLOv5+CBAM+Ghost卷积+小目标锚框	0.841	0.838	0.808	3 708 592	11.0
YOLOv5+R⁃CBAM+Ghost卷积+小目标锚框	0.875	0.861	0.833	3 708 592	11.2
本文算法（融入光流信息）	0.892	0.884	0.857	3 708 592	11.3

Fig.7 Test diagram of the multi?channel flame detection system

References 20

1	马庆禄，马恋，孔国英，等. 基于红外热成像的隧道火焰检测技术研究［J］. 火灾科学， 2022， 31（4）： 244⁃251.
	MA Q L， MA L， KONG G Y， et al. Research on tunnel flame detection technology based on thermal infrared imaging［J］. Fire Safety Science， 2022， 31（4）： 244⁃251.
2	鲍文霞，孙强，梁栋，等. 结合感受野模块与并联RPN网络的火焰检测［J］. 中国图象图形学报， 2023， 28（2）： 418⁃429.
	BAO W X， SUN Q， LIANG D， et al. Flame detection combined with receptive field and parallel RPN［J］. Journal of Image and Graphics， 2023， 28（2）： 418⁃429.
3	ATEEQ Z， MOMANI M. Wireless sensor networks using image processing for fire detection［C］//2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications （CITISIA）. Sydney：IEEE，2020：1⁃10.
4	YOON M， LEE C， LIM G， et al. A fire detection scheme using 5G network⁃based KNN algorithm［C］//2022 13th International Conference on Information and Communication Technology Convergence （ICTC）. Jeju Island：IEEE，2022：2163⁃2165.
5	SUSHMITHA E C. IoT based fire detection and warning system for surveillance applications using deep learning model［C］//2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies （ViTECoN）. Vellore：IEEE，2023：1⁃5.
6	MUHAMMAD K， AHMAD J， LV Z H， et al. Efficient deep CNN⁃based fire detection and localization in video surveillance applications［J］. IEEE Transactions on Systems， Man， and Cybernetics： Systems， 2019， 49（7）： 1419⁃1434.
7	SRIDHAR P， THANGAVEL S K， PARAMESWARAN L， et al. Fire sensor and surveillance camera⁃based GTCNN for fire detection system［J］. IEEE Sensors Journal， 2023， 23（7）： 7626⁃7633.
8	YAR H， HUSSAIN T， AGARWAL M， et al. Optimized dual fire attention network and Medium⁃Scale fire classification benchmark［J］. IEEE Transactions on Image Processing： A Publication of the IEEE Signal Processing Society， 2022， 31： 6331⁃6343.
9	WANG L K. Research on smoke flame detection based on improved YOLOv3［C］//2023 4th International Conference on Information Science， Parallel and Distributed Systems （ISPDS）. Guangzhou： IEEE， 2023： 249⁃254.
10	SUN X Q， XIN S J. Flame detection algorithm baesd on YOLOv4［C］//2022 7th International Conference on Intelligent Computing and Signal Processing （ICSP）. Xi'an： IEEE， 2022： 314⁃317.
11	MSEDDI W S， GHALI R， JMAL M， et al. Fire detection and segmentation using YOLOv5 and U⁃NET［C］//2021 29th European Signal Processing Conference （EUSIPCO）. Dublin： IEEE， 2021： 741⁃745.
12	LU X F. Design and implementation of intelligent parking management system based on OpenCV and B/S architecture［C］//2023 IEEE International Conference on Image Processing and Computer Applications （ICIPCA）. Changchun： IEEE， 2023： 1746⁃1750.
13	THAKUR P， JADON P. Django： Developing web using python［C］//2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering （ICACITE）. Greater Noida： IEEE， 2023： 303⁃306.
14	庞峰，窦立君. 无线局域网多域间端到端安全重路由协议研究［J］. 计算机仿真， 2023， 40（6）： 444⁃448.
	PANG F， DOU L J. Research on end⁃to⁃end secure rerouting protocol between multi domains in WLAN［J］. Computer Simulation， 2023， 40（6）： 444⁃448.
15	李华东，张学亮，王晓磊，等. Kubernetes集群中多节点合作博弈负载均衡策略［J］. 西安电子科技大学学报， 2021， 48（6）： 16⁃22.
	LI H D， ZHANG X L， WANG X L， et al. Multi⁃node cooperative game load balancing strategy in the Kubernetes cluster［J］. Journal of Xidian University， 2021， 48（6）： 16⁃22.
16	TEED Z， DENG J. Recurrent all⁃paire field transforms for optical flow［C］//Computer Vision–ECCV 2020. Cham： Springer， 2020： 402⁃419.
17	崔毅博，汤仁东，邢大军，等. 视觉光流计算技术及其应用［J］. 电子与信息学报， 2023， 45（8）： 2710⁃2721.
	CUI Y B， TANG R D， XING D J， et al. Visual optical flow computing： Algorithms and applications［J］. Journal of Electronics & Information Technology， 2023， 45（8）： 2710⁃2721.
18	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： Unified， real⁃time object detection［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas： IEEE， 2016： 779⁃788.
19	刘洪宁. 基于GhostNet的轻量化遥感图像目标检测方法［J］. 通信与信息技术， 2023（1）： 77⁃81.
	LIU H N. Lightweight remote sensing image target detection method based on ghostnet［J］. Communication & Information Technology， 2023（1）： 77⁃81.
20	WOO S， PARK J， LEE J Y， et al. CBAM： Convolutional block attention module［C］//Computer Vision–ECCV 2018. Cham： Springer， 2018： 3⁃19. （编辑王亚新）

[1]	Jiyang Han, Jiangtao Cao, Henan Wang, Xiaofei Ji. A Review of Fabric Defect Detection Methods Based on Computer Vision [J]. Journal of Liaoning Petrochemical University, 2022, 42(1): 70-77.
[2]	Gao Weiwei, Cao Jiangtao. A Research of Flame Size Detection Method  Based on RGB and HIS Color Space [J]. Journal of Liaoning Petrochemical University, 2014, 34(4): 63-66.
[3]	DENG Shu-xian, LI Min, CHENG Lan. Detection Method of Foamed Slag Height Based on Computer Vision [J]. Journal of Liaoning Petrochemical University, 2007, 27(3): 60-63.