改进YOLOv5s的煤矿烟火检测算法

doi:10.3778/j.issn.1002-8331.2302-0039

摘要/Abstract

摘要： 针对传统的煤矿烟火检测存在检测时间长、误检率高等特点，提出了一种基于改进YOLOv5s的煤矿烟火检测算法。为了弥补后续改进带来的参数量和计算量等问题，使用GhostNet重构YOLOv5s的颈部，使得网络更加轻量化；为了解决小目标检测问题，提出了全局上下文特征提取模块BoT3（bottleneck transformer），该模块可以为小目标提供全局上下文信息，帮助模型更好地预测小目标。同时，在每个检测头位置加入SA（shuffle attention）注意力机制，使模型更聚焦小目标信息，抑制噪声的干扰；将边界框回归损失函数CIoU替换为SIoU，提高回归精度，加速模型的收敛。实验结果表明，改进之后的YOLOv5s参数量、计算量更小，精度更高，能够满足煤矿烟火检测要求。

关键词: 煤矿烟火检测, YOLOv5s, SA注意力机制, 小目标检测, SIoU

Abstract: Aimed at the characteristics of long detection time and high false detection rate in traditional coal mine smoke and fire detection, an improved coal mine smoke and fire detection algorithm of YOLOv5s is proposed. First, in order to make up for the amount of parameters and calculations caused by subsequent improvements, GhostNet is used to reconstruct the neck of YOLOv5s to make the network more lightweight; second, in order to solve the problem of small target detection, the global context feature extraction module BoT3（bottleneck transformer） is proposed, which can provide global context information for small targets and help the model to predict them better. At the same time, an SA（shuffle attention） attention mechanism is added to each head position to make the model focus more on small target information and suppress noise interference; finally, the bounding box regression loss function CIoU is replaced with SIoU to improve regression accuracy and speed up the model of convergence. The experimental results show that the improved YOLOv5s has less parameters, less calculation, and higher accuracy, which can meet the requirements of coal mine pyrotechnic detection.

Key words: coal mine smoke and fire detection, YOLOv5s, shuffle attention（SA）attention mechanism, small target detection, SIoU

刘春霞, 李超, 潘理虎, 樊森霖. 改进YOLOv5s的煤矿烟火检测算法[J]. 计算机工程与应用, 2023, 59(17): 286-294.

LIU Chunxia, LI Chao, PAN Lihu, FAN Senlin. Improved Coal Mine Smoke and Fire Detection Algorithm of YOLOv5s[J]. Computer Engineering and Applications, 2023, 59(17): 286-294.

参考文献

[1] ZHOU Z，SHI Y，GAO Z，et al.Wildfire smoke detection based on local extremal region segmentation and surveillance[J].Fire Safety Journal，2016，85：50-58.
[2] 耿庆田，于繁华，赵宏伟，等.基于颜色特征的火焰检测新算法[J].吉林大学学报（工学版），2014，44（6）：1787-1792.
GENG Q T，YU F H，ZHAO H W，et al.A new algorithm for flame detection based on color features[J].Journal of Jilin University（Engineering Edition），2014，44（6）：1787-1792.
[3] BU T，DEDEOLU Y，ENIS A，et al.Wavelet based real-time smoke detection in video[C]//European Signal Processing Conference，2005.
[4] CHENG Y H，WANG J.A motion image detection method based on the inter-frame difference method[J].Applied Mechanics & Materials，2014，490/491：1283-1286.
[5] TIAN H，LI W，LEI W，et al.A novel video-based smoke detection method using image separation[C]//2012 IEEE International Conference on Multimedia and Expo（ICME），2012.
[6] FRIZZI S，KAABI R.Convolutional neural network for video fire and smoke detection[C]//Conference of the IEEE Industrial Electronics Society，2016：877-882.
[7] YIN Z，WAN B，YUAN F，et al.A deep normalization and convolutional neural network for image smoke detection[J].IEEE Access，2017，5：18429-18438.
[8] FAISAL D A，NUR G R.Real time fire detection using color probability segmentation and DenseNet model for classifier[J].International Journal of Advanced Computer Science and Applications（IJACSA），2022，13（9）：300-305.
[9] HUANG G，LIU Z，LAURENS V，et al.Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017.
[10] 回天，哈力旦·阿布都热依木，杜晗.结合Faster R-CNN的多类型火焰检测[J].中国图象图形学报，2019，24（1）：73-83.
HUI T，HALIDAN A，DU H.Multi-type flame detection combined with Faster R-CNN[J].Journal of Image and Graphics，2019，24（1）：73-83.
[11] 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 & Machine Intelligence，2017，39（6）：1137-1149.
[12] 卢鹏，赵亚琴，陈越，等.复杂背景环境下基于SSD_ MobileNet深度学习模型的火焰图像识别研究[J].火灾科学，2020，29（3）：142-149.
LU P，ZHAO Y Q，CHEN Y，et al.Research on flame image recognition based on SSD_MobileNet deep learning model in complex background environment[J].Fire Safety Science，2020，29（3）：142-149.
[13] HOWARD A，SANDLER M，CHU G，et al.Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：1314-1324.
[14] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[15] 王斌，李靖，赵康，等.面向火焰快速检测的轻量化深度网络研究[J].计算机工程与应用，2022，58（17）：256-262.
WANG B，LI J，ZHAO K，et al.Research on lightweight deep network for fast fire flame detection[J].Computer Engineering and Applications，2022，58（17）：256-262.
[16] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[17] HAN K，WANG Y，TIAN Q，et al.Ghostnet：more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1580-1589.
[18] ZHANG Q L，YANG Y B.Sa-net：shuffle attention for deep convolutional neural networks[C]//2021 IEEE International Conference on Acoustics，Speech and Signal Processing（ICASSP），2021：2235-2239.
[19] GEVORGYAN Z.SIoU loss：more powerful learning for bounding box regression[J].arXiv：2205.12740，2022.
[20] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[21] SRINIVAS A，LIN T Y.Bottleneck transformers for visual recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：16519-16529.
[22] MA N，ZHANG X，ZHENG H T.Shufflenet v2：practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：116-131.
[23] 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.
[24] YANG L，ZHANG R Y，LI L，et al.SimAM：a simple，parameter-free attention module for convolutional neural networks[C]//International Conference on Machine Learning，2021.
[25] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13713-13722.
[26] 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.
[27] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[28] LIU Y，SHAO Z，HOFFMANN N.Global attention mechanism：retain information to enhance channel-spatial interactions[J].arXiv：2112.05561，2021.
[29] HE J，ERFANI S，MA X，et al.Alpha-IoU：a family of power intersection over union losses for bounding box regression[C]//Advances in Neural Information Processing Systems，2021：20230-20242.
[30] 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.
[31] GE Z，LIU S，WANG F，et al.Yolox：exceeding yolo series in 2021[J].arXiv：2107.08430，2021.
[32] LI C，LI L，JIANG H，et al.YOLOv6：a single-stage object detection framework for industrial applications[J].arXiv：2209.02976，2022.
[33] 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[J].arXiv：2207.02696，2022.