YOLOv5s-MRD： efficient fire and smoke detection algorithm for complex scenarios based on YOLOv5s

doi:10.11772/j.issn.1001-9081.2024040527

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (4): 1317-1324.DOI: 10.11772/j.issn.1001-9081.2024040527

• Multimedia computing and computer simulation • Previous Articles Next Articles

YOLOv5s-MRD： efficient fire and smoke detection algorithm for complex scenarios based on YOLOv5s

Yang HOU¹, Qiong ZHANG², Zixuan ZHAO², Zhengyu ZHU², Xiaobo ZHANG²()

^1.Department of Electronic Information Engineering，Chengdu Jincheng College，Chengdu Sichuan 611731，China
^2.School of Computing and Artificial Intelligence，Southwest Jiaotong University，Chengdu Sichuan 611756，China

Received:2024-05-06 Revised:2024-10-26 Accepted:2024-10-30 Online:2025-01-03 Published:2025-04-10
Contact: Xiaobo ZHANG
About author:HOU Yang， born in 1987， M. S.， engineer. Her research interests include internet of things （industrial automation direction）， big data.
ZHANG Qiong， born in 2000， M. S. candidate. Her research interests include artificial intelligence， machine learning.
ZHAO Zixuan， born in 1998， M. S. candidate. His research interests include machine vision， large language model.
ZHU Zhengyu， born in 2001， M. S. candidate. His research interests include computer vision.
Supported by:
National Natural Science Foundation of China(61976247);Key Research and Development Program in Sichuan Province(2023YFS0404)

基于YOLOv5s的复杂场景下高效烟火检测算法YOLOv5s-MRD

侯阳¹, 张琼², 赵紫煊², 朱正宇², 张晓博²()

^1.成都锦城学院电子信息学院，成都 611731
^2.西南交通大学计算机与人工智能学院，成都 611756

通讯作者: 张晓博
作者简介:侯阳（1987—），女，黑龙江加格达奇人，工程师，硕士，主要研究方向：物联网（工业自动化方向）、大数据
张琼（2000—），女，河北石家庄人，硕士研究生，主要研究方向：人工智能、机器学习
赵紫煊（1998—），男，福建南平人，硕士研究生，主要研究方向：机器视觉、大语言模型
朱正宇（2001—），男，江苏盱眙人，硕士研究生，主要研究方向：计算机视觉
基金资助:
国家自然科学基金资助项目(61976247);四川省重点研发计划项目(2023YFS0404)

Abstract

Abstract:

Current fire and smoke detection methods mainly rely on site inspection by staff， which results in low efficiency and poor real-time performance， so an efficient fire and smoke detection algorithm for complex scenarios based on YOLOv5s， called YOLOv5s-MRD （YOLOv5s-MPDIoU-RevCol-Dyhead）， was proposed. Firstly， the MPDIoU （Maximized Position-Dependent Intersection over Union） method was employed to modify the border loss function， thereby enhancing the accuracy and efficiency of Bounding Box Regression （BBR） by adapting to BBR in overlapping or non-overlapping scenarios. Secondly， the RevCol （Reversible Column） network model concept was applied to reconstruct the backbone of YOLOv5s， transforming it into a backbone network with multi-column network architecture. At the same time， by incorporating reversible links across various layers of the model， so that the retention of feature information was maximized， thereby improving the network’s feature extraction capability. Finally， with the integration of Dynamic head detection heads， scale awareness， spatial awareness， and task awareness were unified， thereby improving detection heads’ accuracy and effectiveness significantly without additional computational cost. Experimental results demonstrate that on DFS （Data of Fire and Smoke） dataset， compared to the original YOLOv5s algorithm， the proposed algorithm achieves a 9.3% increase in mAP@0.5 （mean Average Precision）， a 6.6% improvement in prediction accuracy， and 13.8% increase in recall. It can be seen that the proposed algorithm can meet the requirements of current fire and smoke detection application scenarios.

Key words: object detection, RevCol (Reversible Column) network, YOLOv5, Dynamic head detection head, MPDIoU (Maximized Position-Dependent Intersection over Union), fire and smoke detection

摘要：

现有的烟火检测方法主要依赖员工现场巡视，效率低且实时性差，因此，提出一种基于YOLOv5s的复杂场景下的高效烟火检测算法YOLOv5s-MRD （YOLOv5s-MPDIoU-RevCol-Dyhead）。首先，采用MPDIoU （Maximized Position-Dependent Intersection over Union）方法改进边框损失函数，以适应重叠或非重叠的边界框回归（BBR），从而提高BBR的准确性和效率；其次，利用可逆柱状结构RevCol（Reversible Column）网络模型思想重构YOLOv5s模型的主干网络，使它具有多柱状网络架构，并在模型的不同层之间加入可逆链接，从而最大限度地保持特征信息以提高网络的特征提取能力；最后，引入Dynamic head检测头，以统一尺度感知、空间感知和任务感知，从而在不额外增加计算开销的条件下显著提高目标检测头的准确性和有效性。实验结果表明：在DFS（Data of Fire and Smoke）数据集上，与原始YOLOv5s算法相比，所提算法的平均精度均值（mAP@0.5）提升了9.3%，预测准确率提升了6.6%，召回率提升了13.8%。可见，所提算法能满足当前烟火检测应用场景的要求。

关键词: 目标检测, RevCol网络, YOLOv5, Dynamic head检测头, MPDIoU, 烟火检测

CLC Number:

TP301.6

Yang HOU, Qiong ZHANG, Zixuan ZHAO, Zhengyu ZHU, Xiaobo ZHANG. YOLOv5s-MRD： efficient fire and smoke detection algorithm for complex scenarios based on YOLOv5s[J]. Journal of Computer Applications, 2025, 45(4): 1317-1324.

侯阳, 张琼, 赵紫煊, 朱正宇, 张晓博. 基于YOLOv5s的复杂场景下高效烟火检测算法YOLOv5s-MRD[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1317-1324.

Figures/Tables 16

Fig. 1 Overall network architecture

Fig. 2 Architecture of RevCol network

Fig. 3 YOLOv5s backbone

Fig. 4 Reconstructed network backbone based on RevCol

Fig. 5 Dyhead detection head structure

Fig. 6 MPDIoU parameter example

Fig. 7 Examples of different scenario data

Fig. 8 Some different types of fire and smoke pictures

Fig. 9 Noisy data

Fig. 10 Box_loss line charts of training set and validation set

Fig. 11 Confusion matrix

Fig. 12 Object detection results

Tab. 1 Influence of different improved methods on model detection performance

实验轮次	MPDIoU	RevCol	Dyhead	计算量/ GFLOPs	mAP@0.5	准确率	召回率
1				24.00	0.43	0.91	0.80
2	√			23.80	0.44	0.91	0.83
3	√	√		17.72	0.45	0.94	0.85
4	√	√	√	17.61	0.47	0.97	0.91

Tab. 2 Comparison results of different algorithms on DFS dataset

算法	准确率	召回率
BoWFire	0.90	0.66
Xception	0.90	0.86
KutralNet	0.92	0.67
FireNet	0.93	0.90
YOLOv6s	0.92	0.84
YOLOv8s	0.93	0.85
YOLOv9s	0.96	0.90
YOLOv5s-MRD	0.98	0.91

Tab. 3 Comparison results of different algorithms on Fire Detection and D-Fire datasets

算法	Fire Detection		D-Fire
算法	准确率	召回率	准确率	召回率
BoWFire	0.90	0.57	0.79	0.61
Xception	0.85	0.80	0.89	0.95
KutralNet	0.93	0.92	0.85	0.85
FireNet	0.92	0.86	0.87	0.89
YOLOv6s	0.92	0.90	0.89	0.85
YOLOv8s	0.93	0.92	0.88	0.88
YOLOv9s	0.91	0.87	0.84	0.70
YOLOv5s-MRD	0.94	0.93	0.99	0.83

Tab. 4 Comparison of time complexity

模型	计算量/GFLOPs
YOLOv6s	44.90
YOLOv8s	28.82
YOLOv9s	39.64
YOLOv5s-MRD	17.61

References 32

1	DE LEÓN-RUIZ J E， CARVAJAL-MARISCAL I， DE LA CRUZ-ÁVILA M， et al. Image convolution-based experimental technique for flame front detection and dimension estimation： a case study on laminar-to-transition jet diffusion flame height measurement［J］. Measurement Science and Technology， 2022， 33（7）： No.075406.
2	JEON M， CHOI H S， LEE J， et al. Multi-scale prediction for fire detection using convolutional neural network［J］. Fire Technology， 2021， 57（5）：2533-2551.
3	BAI X， WANG Z. Research on forest fire detection technology based on deep learning［C］// Proceedings of the 2021 International Conference on Computer Network， Electronic and Automation. Piscataway： IEEE， 2021： 85-90.
4	WANG Z， WU L， LI T， et al. A smoke detection model based on improved YOLOv5［J］. Mathematics， 2022， 10（7）： No.1190.
5	吴凡. 基于深度学习的火灾检测算法研究与实现［D］. 杭州：杭州电子科技大学， 2020：1-67.
	WU F. Research and implementation of fire detection algorithm based on deep learning［D］. Hangzhou： Hangzhou Dianzi University， 2020：1-67.
6	ZHOU X， WANG D， KRÄHENBÜHL P. Objects as points［EB/OL］. ［2024-04-25］..
7	谢书翰，张文柱，程鹏，等. 嵌入通道注意力的YOLOv4火灾烟雾检测模型［J］. 液晶与显示， 2021， 36（10）： 1445-1453.
	XIE S H， ZHANG W Z， CHENG P， et al. Firesmoke detection model based on YOLOv4 with channel attention［J］. Chinese Journal of Liquid Crystals and Displays， 2021， 36（10）： 1445-1453.
8	邹辉军，焦良葆，孟琳，等. 基于CG-yolo的烟火检测［J］. 计算机与数字工程， 2022， 50（1）： 206-212.
	ZOU H J， JIAO L B， MENG L， et al. Detection of fireworks based on CG-yolo［J］. Computer and Digital Engineering， 2022， 50（1）： 206-212.
9	HE Y， HU J， ZENG M， et al. DCGC-YOLO： the efficient dual-channel bottleneck structure YOLO detection algorithm for fire detection［J］. IEEE Access， 2024， 12： 65254-65265.
10	WANG Y， HU Y. Smoke and fire detection algorithm based on improved YOLOv5［C］// Proceedings of the 6th International Conference on Intelligent Autonomous Systems. Piscataway： IEEE， 2023： 82-87.
11	XU S， JI Y， WANG G， et al. GFSPP-YOLO： a light YOLO model based on group fast spatial pyramid pooling［C］// Proceedings of the IEEE 11th International Conference on Information， Communication and Networks. Piscataway： IEEE， 2023： 733-738.
12	PHAN D T， YAP K H， GARG K， et al. Vision-based early fire and smoke detection for smart factory applications using FFS-YOLO［C］// Proceedings of the IEEE 25th International Workshop on Multimedia Signal Processing. Piscataway： IEEE， 2023： 1-6.
13	WANG X， JING Z， SHI L， et al. MA-YOLO： a lightweight vehicle detection framework based on YOLO［C］// Proceedings of the 2023 International Conference on Artificial Intelligence and Automation Control. Piscataway： IEEE， 2023： 277-281.
14	CAI Y， ZHOU Y， HAN Q， et al. Reversible column networks［EB/OL］. ［2023-02-01］..
15	MA S， XU Y. MPDIoU： a loss for efficient and accurate bounding box regression［EB/OL］. ［2023-07-14］..
16	DAI X， CHEN Y， XIAO B， et al. Dynamic head： unifying object detection heads with attentions［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 7369-7378.
17	DAI J， QI H， XIONG Y， et al. Deformable convolutional networks［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 764-773.
18	GIRSHICK R. Fast R-CNN［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 1440-1448.
19	HE K， GKIOXARI G， DOLLÁR P， et al. Mask R-CNN［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 2980-2988.
20	REN S， HE K， 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. Piscataway： IEEE， 2017， 39（6）： 1137-1149.
21	TIAN Z， SHEN C， CHEN H， et al. FCOS： fully convolutional one-stage object detection［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 9626-9635.
22	WANG X， ZHANG S， YU Z， et al. Scale-equalizing pyramid convolution for object detection［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 13356-13365.
23	YANG Z， LIU S， HU H， et al. RepPoints： point set representation for object detection［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 9656-9665.
24	ZHANG S， CHI C， YAO Y， et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 9756-9765.
25	CHEN Y， DAI X， LIU M， et al. Dynamic ReLU［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12364. Cham： Springer， 2020： 351-367.
26	DUNNINGS A J， BRECKON T P. Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection［C］// Proceedings of the 25th IEEE International Conference on Image Processing. Piscataway： IEEE， 2018： 1558-1562.
27	SHAMSOSHOARA A， AFGHAH F， RAZI A， et al. Aerial imagery pile burn detection using deep learning： the FLAME dataset［J］. Computer Networks， 2021， 193： No.108001.
28	AYALA A， FERNANDES B， CRUZ F， et al. KutralNet： a portable deep learning model for fire recognition［C］// Proceedings of the 2020 International Joint Conference on Neural Networks. Piscataway： IEEE， 2020： 1-8.
29	LI C， LI L， JIANG H， et al. YOLOv6： a single-stage object detection framework for industrial applications［EB/OL］. ［2024-09-07］..
30	Ultralytics. YOLOv8［EB/OL］. ［2024-04-26］..
31	WANG C Y， YEH I H， LIAO H Y M. YOLOv9： learning what you want to learn using programmable gradient information［C］// Proceedings of the 2024 European Conference on Computer Vision， LNCS 15089. Cham： Springer， 2025： 1-21.
32	CHINO D Y T， AVALHAIS L P S， RODRIGUES J F， et al. BoWFire： detection of fire in still images by integrating pixel color and texture analysis［C］// Proceedings of the 28th SIBGRAPI Conference on Graphics， Patterns and Images. Piscataway： IEEE， 2015： 95-102.

[1]	Qingqing ZHAO, Bin HU. Moving pedestrian detection neural network with invariant global sparse contour point representation [J]. Journal of Computer Applications, 2025, 45(4): 1271-1284.
[2]	Liwei ZHANG, Quan LIANG, Yutao HU, Qiaole ZHU. Channel shuffle attention mechanism based on group convolution [J]. Journal of Computer Applications, 2025, 45(4): 1069-1076.
[3]	Chuanhao ZHANG, Xiaohan TU, Xuehui GU, Bo XUAN. LiDAR-camera 3D object detection based on multi-modal information mutual guidance and supplementation [J]. Journal of Computer Applications, 2025, 45(3): 946-952.
[4]	Songsen YU, Zhifan LIN, Guopeng XUE, Jianyu XU. Lightweight large-format tile defect detection algorithm based on improved YOLOv8 [J]. Journal of Computer Applications, 2025, 45(2): 647-654.
[5]	Sheng YANG, Yan LI. Contrastive knowledge distillation method for object detection [J]. Journal of Computer Applications, 2025, 45(2): 354-361.
[6]	Jiayang GUI, Shunji WANG, Zhengkang ZHOU, Jiashan TANG. Tunnel foreign object detection algorithm based on improved YOLOv8n [J]. Journal of Computer Applications, 2025, 45(2): 655-661.
[7]	Shijia WEN, Shijun JING. Dynamic visual SLAM algorithm incorporating object detection and feature point association [J]. Journal of Computer Applications, 2025, 45(2): 610-615.
[8]	Zhongwei ZHANG, Jun WANG, Shudong LIU, Zhiheng WANG. Object detection in remote sensing image based on multi-scale feature fusion and weighted boxes fusion [J]. Journal of Computer Applications, 2025, 45(2): 633-639.
[9]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[10]	Yeheng LI, Guangsheng LUO, Qianmin SU. Logo detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2024, 44(8): 2580-2587.
[11]	Yingjun ZHANG, Niuniu LI, Binhong XIE, Rui ZHANG, Wangdong LU. Semi-supervised object detection framework guided by curriculum learning [J]. Journal of Computer Applications, 2024, 44(8): 2326-2333.
[12]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[13]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.
[14]	Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977.
[15]	Yaping DENG, Yingjiang LI. Review of YOLO algorithm and its applications to object detection in autonomous driving scenes [J]. Journal of Computer Applications, 2024, 44(6): 1949-1958.

YOLOv5s-MRD： efficient fire and smoke detection algorithm for complex scenarios based on YOLOv5s

基于YOLOv5s的复杂场景下高效烟火检测算法YOLOv5s-MRD

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 32

Related Articles 15

Recommended Articles

Metrics