改进的YOLOv5烟雾检测模型

doi:10.3778/j.issn.1002-8331.2209-0421

摘要/Abstract

摘要： 针对烟雾发生场景复杂，小目标烟雾检测困难的问题，提出一种改进的YOLOv5烟雾检测模型。为了增加模型对目标烟雾的检测精度，结合加权双向特征金字塔网络（BiFPN）结构对特征融合过程进行修改，并在通道和空间维度上加入混合注意力机制对融合特征图的权重进行重新赋值，在增强烟雾目标特征的同时抑制无关区域特征，使烟雾特征表达具有更高的鲁棒性；使用α-CIOU替换G-IOU作为预测框回归损失，提升预测框的预测精度；剔除分类损失以降低模型的复杂度。实验结果表明，改进后的YOLOv5烟雾检测模型相比于YOLOv5模型检测精度更高，其准确率达到99.35%，召回率达到99.18%，并且检测速度可达46?frame/s，该算法能有效提取烟雾的整体特征，对于复杂场景下的烟雾以及小目标烟雾检测任务更为适用。

关键词: 烟雾检测, YOLOv5, BiFPN, 注意力机制, α-CIOU

Abstract: Aiming at the problems of complex smoke occurrence scene and difficult smoke detection of small targets, an improved YOLOv5 smoke detection model is proposed. Firstly, in order to increase the detection accuracy of the target smoke, the feature fusion process is modified by combining the weighted bidirectional feature Pyramid network（BiFPN） structure, and the mixed attention mechanism is added to the channel and spatial dimensions to reassign the weight of the fused feature map. In enhanced characteristics of the smoke target inhibition has nothing to do with regional characteristics at the same time, the smoke has higher robustness characteristics of expression. Secondly, α-CIOU is used to replace G-IOU as the prediction box regression loss to improve the prediction accuracy of the prediction box. The classification loss is removed to reduce the complexity of the model. Experimental results show that the improved YOLOv5 smoke detection model has higher detection accuracy than the YOLOv5 model, with an accuracy of 99.35% and a recall rate of 99.18% and a detection speed of 46 frame/s. The proposed algorithm can effectively extract the overall characteristics of smoke, which is more suitable for smoke detection tasks in complex scenes and small targets.

Key words: smoke detection, YOLOv5, BiFPN, attention mechanism, α-CIOU

郑远攀, 许博阳, 王振宇. 改进的YOLOv5烟雾检测模型[J]. 计算机工程与应用, 2023, 59(7): 214-221.

ZHENG Yuanpan, XU Boyang, WANG Zhenyu. Improved YOLOv5 Smoke Detection Model[J]. Computer Engineering and Applications, 2023, 59(7): 214-221.

参考文献

[1] 夏雪，袁非牛，章琳，等.从传统到深度：视觉烟雾识别、检测与分割[J].中国图象图形学报，2019，24（10）：1627-1647.
XIA X，YUAN F N，ZHANG L，et al.From traditional methods to deep ones：review of visual smoke recognition，detection，and segmentation[J].Journal of Image and Graphics，2019，24（10）：1627-1647.
[2] APPANA D K，ISLAM R，KHAN S A，et al.A video-based smoke detection using smoke flow pattern and spatial-temporal energy analyses for alarm systems[J].Information Sciences，2017，418/419：91-101.
[3] YUAN F.A fast accumulative motion orientation model based on integral image for video smoke detection[J].Pattern Recognition Letters，2008，29（7）：925-932.
[4] YE W，ZHAO J H，WANG S，et al.Dynamic texture based smoke detection using surfacelet transform and HMT model[J].Fire Safety Journal，2015，73：91-101.
[5] TAO C Y，ZHANG J，WANG P.Smoke detection based on deep convolutional neural networks[C]//Proceedings of the 2nd International Conference on Industrial Informatics-Computing Technology，Intelligent Technology，Industrial Information Integration（ICIICII），2016：150-153.
[6] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems，2012：1097-1105.
[7] YIN Z J，WAN B Y，YUAN F N，et al.A deep normalization and convolutional neural network for image smoke detection[J].IEEE Access，2017，5：18429-18438.
[8] 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，CHEN 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.
[9] HUO Y，ZHANG Q，JIA Y，et al.A deep separable convolutional neural network for multiscale image-based smoke detection[J].Fire Technology，2022（1）.
[10] CAI W，WANG C，HUANG H，et al.A real-time smoke detection model based on YOLO-smoke algorithm[C]//Proceedings of the 2020 Cross Strait Radio Science & Wireless Technology Conference（CSRSWTC），2020：1-3.
[11] LIN T Y，P DOLLáR，GIRSHICK R，et al.Feature pyramid networks for object detection[J].arXiv：1612.03144，2016.
[12] LIU S，QI L，QIN H F，et al.Path aggregation network for instance segmentation[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[13] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020：10778-10787.
[14] FU J，LIU J，JIANG J，et al.Scene segmentation with dual relation-aware attention network[J].IEEE Transactions on Neural Networks and Learning Systems，2021，32（6）：2547-2560.
[15] PENG Y，HE X，ZHAO J.Object-part attention model for fine-grained image classification[J].IEEE Transactions on Image Processing，2018，27（3）：1487-1500.
[16] NING X，GONG K，LI W，et al.JWSAA：joint weak saliency and attention aware for person re-identification[J].Neurocomputing，2021，453：801-811.
[17] LIN J C W，SHAO Y N，DJENOURI Y，et al.ASRNN：a recurrent neural network with an attention model for sequence labeling[J].Knowledge-Based Systems，2021，212：106548.
[18] GALASSI A，LIPPI M，TORRONI P.Attention in natural language processing[J].IEEE Transactions on Neural Networks and Learning Systems，2021，32（10）：4291-4308.
[19] BASIRI M E，NEMATI S，ABDAR M，et al.ABCDM：an attention-based bidirectional CNN-RNN deep model for sentiment analysis[J].Future Generation Computer Systems，2021，115：279-294.
[20] REZATOFIGHI H，TSOI N，GWAK J，et al.Generalized Intersection over union：a metric and a loss for bounding box regression[C]//Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2019：658-666.
[21] YU J，JIANG Y，WANG Z，et al.UnitBox：an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia，2016.
[22] 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.