面向火焰快速检测的轻量化深度网络研究

doi:10.3778/j.issn.1002-8331.2204-0498

摘要/Abstract

摘要： 在易燃易爆场合火灾控制中火焰极速检测意义重大，其对算法实时性、准确度、抗干扰性有较高要求。为此提出一种基于改进YOLOv4-tiny轻量化抗干扰火焰检测深度网络。引入类火目标图像与真实火焰图像并通过Mosaic数据增强方式建立鲁棒性火焰检测数据集；对YOLOv4-tiny骨干网络采用深度可分离卷积进行改进，使得原网络更加轻量化；在特征金字塔网络FPN（feature pyramid network）中融合多尺度特征提高网络对多层特征的学习表示能力，并引出多检测头以适应火焰爆发过程中不同尺度火焰的精准检测；在FPN中引入ECA（efficient channel attention）通道注意力机制进一步提高检测精度。实验结果表明，提出的YOLOv4-tiny-L4参数量仅为4.22?MB，准确率高达94.1%，执行时间仅为46?ms，满足火焰快速检测基本要求。

关键词: 火焰检测, 轻量化网络, 改进YOLOv4-tiny, 注意力机制, 多尺度特征

Abstract: Extremely fast detection to flame is of great significance for fire control in flammable and explosive occasions. It has high requirements for real-time, accuracy and anti-interference of the algorithm. To this end, the lightweight anti-interference flame detection depth network based on improved YOLOv4-tiny is proposed. Firstly, the robust flame detection data set is established by Mosaic data enhancement and the pseudo target（image similar to flame）. Secondly, the YOLOv4-tiny backbone network is improved by deep separable convolution, which makes the original network lighter. Then, these multi-scale features are fused in the feature pyramid network（FPN） to improve the learning and representation ability of the network for multi-layer features, and multiple detection heads are introduced to adapt to the accurate detection of different scale flames in the process of flame explosion. Finally, ECA（efficient channel attention） attention mechanism is introduced into FPN to further improve the detection accuracy. Experimental results show that the parameter quantity of YOLOv4-tiny-L4 is only 4.22?MB; the accuracy is as high as 94.1%; the execution time is only 46?ms, which meets the basic requirements of rapid flame detection.

Key words: flame detection, lightweight network, improved YOLOv4-tiny, attention mechanism, multiscale feature

王斌, 李靖, 赵康, 周温. 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 Bin, LI Jing, ZHAO Kang, ZHOU Wen. Research on Lightweight Depth Network for Rapid Flame Detection[J]. Computer Engineering and Applications, 2022, 58(17): 256-262.

参考文献

[1] CHAOXIA C，SHANG W，ZHANG F，et al.Weakly aligned multimodal flame detection for fire-fighting robots[J].IEEE Transactions on Industrial Informatics，doi：10.1109/TII.2022.3158668.
[2] JAIN A，SRIVASTAVA A.Privacy-preserving efficient fire detection system for indoor surveillance[J].IEEE Transactions on Industrial Informatics，2022，18（5）：3043-3054.
[3] BUSHNAQ O M，CHAABAN A，AL-NAFFOURI T Y.The role of UAV-IoT networks in future wildfire detection[J].IEEE Internet of Things Journal，2021，23（8）：16984-16999.
[4] SILVA J，HUANG C，NOGUEIRA F，et al.EdgeFire-Smoke：a novel lightweight CNN model for real-time video fire-smoke detection[J].IEEE Transactions on Industrial Informatics，doi：10.1109/TII.2021.3138752.
[5] ZHANG N，SUN L，SUN Z.GF-4 satellite fire detection with an improved contextual algorithm[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2022，15：163-172.
[6] WANG T，BU L，YANG Z，et al.A new fire detection method using a multi-expert system based on color dispersion，similarity and centroid motion in indoor environment[J].IEEE/CAA Journal of Automatica Sinica，2020，7（1）：263-275.
[7] XIE Y，ZHU J，CAO Y，et al.Efficient video fire detection exploiting motion-flicker-based dynamic features and deep static features[J].IEEE Access，2020，8：81904-81917.
[8] HUANG X，DU L.Fire detection and recognition optimization based on virtual reality video image[J].IEEE Access，2020，8：77951-77961.
[9] 李欣健，张大胜，孙利雷，等.复杂场景下基于CNN的轻量火焰检测方法[J].模式识别与人工智能，2021，34（5）：415-422.
LI Xinjian，ZHANG Dasheng，SUN Lilei，et al.CNN-based lightweight flame detection method in complex scenes[J].Pattern Recognition and Artificial Intelligence，2021，34（5）：415-422.
[10] 王鑫鹏，王晓强，林浩，等.深度学习典型目标检测算法的改进综述[J].计算机工程与应用，2022，58（6）：42-57.
WANG Xinpeng，WANG Xiaoqiang，LIN Hao，et al.Review on improvement of typical object detection algorithms in deep learning[J].Computer Engineering and Applications，2022，58（6）：42-57.
[11] 谷典典，石屹宁，刘譞哲，等.基于元算子的深度学习框架缺陷检测方法[J].计算机学报，2022，45（2）：240-255.
GU Diandian，SHI Yining，LIU Xuanzhe，et al.Defect detection for deep learning frameworks based on meta operators[J].Chinese Journal of Computers，2022，45（2）：240-255.
[12] 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.
[13] LI S，YAN Q，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.
[14] BARI A，SAINI T，KUMAR A.Fire detection using deep transfer learning on surveillance videos[C]//2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks（ICICV），2021：1061-1067.
[15] SHARMA J，GRANMO O C，GOODWIN M，et al.Deep convolutional neural networks for fire detection in images[J].Communications in Computer and Information Science，2017：183-193.
[16] BARMPOUTIS P，DIMITROPOULOS K，KAZA K，et al.Fire detection from images using faster R-CNN and multidimensional texture analysis[C]//Proceedings-ICASSP，IEEE International Conference on Acoustics，Speech and Signal Processing，2019：8301-8305.
[17] LI P，ZHAO W.Image fire detection algorithms based on convolutional neural networks[J].Case Studies in Thermal Engineering，2020，19：100625.
[18] SUN K，ZHAO Q，WANG X.Using knowledge inference to suppress the lamp disturbance for fire detection[J].Journal of Safety Science and Resilience，2021，2（3）：124-130.
[19] MUHAMMAD K，AHMAD J，LV Z，et al.Efficient deep CNN-based fire detection and localization in video surveillance applications[J].IEEE Transactions on Image Processing，2018，29：8467-8475.
[20] WANG S，CHEN T，LV X，et al.Forest fire detection based on lightweight Yolo[C]//2021 33rd Chinese Control and Decision Conference（CCDC），2021：1560-1565.
[21] SHEN C，HU J，WANG C，et al.LFNet：lightweight fire smoke detection for uncertain surveillance environment[C]//2020 6th International Conference on Big Data and Information Analytics（BigDIA），Shenzhen，China，2020：11-17.
[22] 周天宇，朱启兵，黄敏，等.基于轻量级卷积神经网络的载波芯片缺陷检测[J].计算机工程与应用，2022，58（7）：213-219.
ZHOU Tianyu，ZHU Qibing，HUANG Min，et al.Defect detection of chip on carrier based on lightweight convolutional neural network[J].Computer Engineering and Applications，2022，58（7）：213-219.
[23] 王欣，王美丽，边党伟.融合MobileNetv2和注意力机制的轻量级人像分割算法[J].计算机工程与应用，2022，58（7）：220-228.
WANG Xin，WANG Meili，BIAN Dangwei.Algorithm for portrait segmentation combined with MobileNetv2 and attention mechanism[J].Computer Engineering and Applications，2022，58（7）：220-228.
[24] 马利，刘新宇，李皓宇，等.应用空洞卷积的神经网络轻量化方法[J].计算机工程与应用，2022，58（5）：85-93.
MA Li，LIU Xinyu，LI Haoyu，et al.Neural network lightweight method with dilated convolution[J].Computer Engineering and Applications，2022，58（5）：85-93.
[25] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：770-778.
[26] ADDABBO T.Smart gravimetric system for enhanced security of accesses to public places embedding a MobileNet neural network classifier[J].IEEE Transactionson Instrumentation and Measurement，2022，71：1-10.
[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），Seattle，WA，USA，2020：11531-11539.
[28] HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[29] BOCHKOVSKIY A，WANG C Y，LIAO H.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[30] LOSHCHILOV I，HUTTER F.SGDR：stochastic gradient descent with warm restarts[J].arXiv：1608.03983，2016.
[31] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020：10781-10790.
[32] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Computer Vision-ECCV 2018，2018：3-19.
[33] ROY A G，NAVAB N，WACHINGER C.Concurrent spatial and channel squeeze & excitation in fully convolutional networks[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention，2018.