基于双通道深度CNN的烟雾浓度测量方法

doi:10.16451/j.cnki.issn1003-6059.202109007

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1166 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要现有基于视频图像测量烟雾浓度的方法主要通过人工提取特征,需要已知环境的大气光、背景等外界条件.为了提高烟雾浓度测量方法的直接性和实用性,文中通过烟雾化方程,建立烟雾图像与其浓度数值的对应关系,进而提出基于双通道深度卷积神经网络(DCCNN)的烟雾浓度测量方法,实现端到端的烟雾浓度直接测量.DCCNN中采用1×1卷积进行通道数据融合,引入跳跃连接解决网络层数较深时梯度消失问题,加快训练过程.同时引入自注意力机制,自动学习隐含特征的重要程度,再合并两个通道提取的特征,获得综合测量结果.实验表明,DCCNN测量烟雾浓度的平均绝对误差较低,综合性能较优.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	莫鸿飞
	谢振平

关键词 ：烟雾浓度, 深度卷积神经网络, 深度学习, 烟雾化方程, 注意力机制

Abstract：In the existing methods for measuring smoke density based on video images, features are mainly extracted manually, and the external conditions, such as ambient light and background, are required as known conditions. To improve the directness and practicability of the smoke density measurement method, the corresponding relationship between smoke images and their density values is established through the Aerosolization equation. The smoke density dataset is established as well. A smoke density measurement method based on dual-channel deep convolution neural network(DCCNN) is proposed to realize the end-to-end direct measurement of smoke density. In DCCNN, 1×1 convolution is used for channel data fusion, and jump connection is introduced to make the neural network training faster. The self-attention mechanism is also introduced to learn the importance of hidden features automatically. Finally, the features extracted from two channels are combined to obtain comprehensive measurement results. Experiments show that DCCNN gains lower mean absolute error and higher comprehensive performance.

Key words： Smoke Density Deep Convolutional Neural Network Deep Learning Aerosolization Equation Attention Mechanism

收稿日期: 2021-04-30

ZTFLH:

TP 391.4

基金资助:国家自然科学基金项目(No.61872166)、江苏省“六大人才高峰”项目(No.XYDXX-161)资助

通讯作者: 谢振平,博士,教授,主要研究方向为知识建模、认知学习.E-mail:xiezp@jiangnan.edu.cn.

作者简介: 莫鸿飞,硕士研究生, 主要研究方向为计算机视觉.E-mail:1640657648@qq.com.

引用本文:

莫鸿飞, 谢振平. 基于双通道深度CNN的烟雾浓度测量方法[J]. 模式识别与人工智能, 2021, 34(9): 844-852. MO Hongfei, XIE Zhenping. Smoke Density Measurement Method Based on Dual-Channel Deep CNN. , 2021, 34(9): 844-852.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202109007 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I9/844

[1] YUAN F N, FANG Z, WU S, et al. Real-Time Image Smoke Detection Using Staircase Searching-Based Dual Threshold AdaBoost and Dynamic Analysis. IET Image Processing, 2015, 9(10): 849-856.
[2] 赵建华,袁宏永,苏国锋,等.烟雾浓度及粒径的激光探测实验研究.激光与红外, 2000, 30(5): 277-279.
(ZHAO J H, YUAN H Y, SU G F, et al. Experimental Study on the Laser Detection of Concentration and Particle Size of Smoke. Laser and Infrared, 2000, 30(5): 277-279.)
[3] 张棚,刘路路,李传亮,等.基于Mie散射的可吸入颗粒检测仪的设计.光谱学与光谱分析, 2014, 34(8): 2298-2302.
(ZHANG P, LIU L L, LI C L, et al. Design of Inhalable Particulate Matters Measurement Based on the Mie Scattering Extinction. Spectroscopy and Spectral Analysis, 2014, 34(8): 2298-2302.)
[4] 马天颖.基于图像结构相似度的烟雾浓度视频测量方法研究.硕士学位论文.武汉:华中科技大学, 2017.
(MA T Y. Smoke Concentration Measurement Method Based on Stru-cture Similarity Index with Video. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2017.)
[5] 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.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. Journal of Image and Graphics, 2019, 24(10): 1627-1647.)
[6] ALAMGIR N, NGUYEN K, CHANDRAN V, et al. Combining Multi-channel Color Space with Local Binary Co-occurrence Feature Descriptors for Accurate Smoke Detection from Surveillance Videos. Fire Safety Journal, 2018, 102: 1-10.
[7] 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. Information Sciences, 2017, 418/419: 91-101.
[8] GUBBI J, MARUSIC S, PALANISWAMI M. Smoke Detection in Video Using Wavelets and Support Vector Machines. Fire Safety Journal, 2009, 44(8): 1110-1115.
[9] 陈俊周,汪子杰,陈洪瀚,等.基于级联卷积神经网络的视频动态烟雾检测.电子科技大学学报, 2016, 46(6): 992-996.
(CHEN J Z, WANG Z J, CHEN H H, et al. Dynamic Smoke Detection Using Cascaded Convolutional Neural Network for Survei-llance Videos. Journal of University of Electronic Science and Technology of China, 2016, 46(6): 992-996.)
[10] YIN Z J, WAN B Y, YUAN F N, et al. A Deep Normalization and Convolutional Neural Network for Image Smoke Detection. IEEE Access, 2017, 5: 18429-18438.
[11] YUAN F N, ZHANG L, WAN B Y, et al. Convolutional Neural Networks Based on Multi-scale Additive Merging Layers for Visual Smoke Recognition. Machine Vision and Applications, 2019, 30: 345-358.
[12] GU K, XIA Z F, QIAO J F, et al. Deep Dual-Channel Neural Network for Image-Based Smoke Detection. IEEE Transactions on Multimedia, 2020, 22(2): 311-323.
[13] COZMAN F, KROTKOV E. Depth from Scattering // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 1997: 801-806.
[14] HE K M, SUN J, TANG X O. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[15] 王新玲.基于图像的烟雾浓度检测技术研究.硕士学位论文.太原:中北大学, 2012.
(WANG X L. Research on a Smoke Concentration Detection Technology Based on Image. Master Dissertation. Taiyuan, China: North University of China, 2012.)
[16] 袁飞阁.基于烟雾浓度的火灾视频检测方法.硕士学位论文.武汉:华中科技大学, 2013.
(YUAN F G. Fire Detection Method Based on Smoke Density with Video. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2013.)
[17] MIAO L G, CHEN Y J, WANG A Z. Video Smoke Detection Algorithm Using Dark Channel Priori // Proc of the 33rd Chinese Control Conference. Washington, USA: IEEE, 2014: 7405-7408.
[18] 吴昊.瞬态烟雾浓度的测试方法研究.硕士学位论文.太原:中北大学, 2020.
(WU H. Research on Measurement Method of Transient Smoke Concentration. Master Dissertation. Taiyuan, China: North University of China, 2020.)
[19] YUAN F N, ZHANG L, XIA X, et al. A Wave-Shaped Deep Neural Network for Smoke Density Estimation. IEEE Transactions on Image Processing, 2020, 29: 2301-2313.
[20] WANG X L, GIRSHICK R, GUPTA A, et al. Non-local Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 7794-7803.
[21] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
[22] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2021-04-02]. https://arxiv.org/pdf/1409.1556v4.pdf.
[23] NAH S, KIM T H, LEE K M. Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Wa-shington, USA: IEEE, 2016: 3883-3891.
[24] WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional Block Attention Module // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19.
[25] Turkey Bilkent University. Computer Vision Based Fire Detection Software[DB/OL]. [2021-04-02]. http://signal.ee.bilkent.edu.tr/VisiFire/index.html.
[26] VEZZANI R, CUCCHIARA R. Video Surveillance Online Repository(ViSOR): An Integrated Framework. Multimedia Tools and Applications, 2010, 50: 359-380.