Spatio-temporal deep learning fire smoke detection

Fan WU; Hui-qin WANG; Ke WANG

doi:10.37188/CJLCD.2020-0239

您当前的位置：

首页 >

文章列表页 >

Spatio-temporal deep learning fire smoke detection

Image Processing | 更新时间：2021-08-05

- Spatio-temporal deep learning fire smoke detection
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 8, Pages: 1186-1195(2021)
- 作者机构：
  
  西安建筑科技大学信息与控制工程学院, 陕西西安 710055
- 作者简介：
- 基金信息：
  
  Supported by Shaanxi Provincial Department of Science and Technology International Science and Technology Cooperation Program Project(2020KW-012);Shaanxi Provincial Department of Education Key Project High-end Think Tank(18JT006);Xi'an Science and Technology Bureau Project(GXYD10.1)
- DOI：10.37188/CJLCD.2020-0239
  CLC： TP391.4;TH691.9
- Received：13 September 2020，
  
  Revised：19 December 2020，
  
  Published：2021-08
- 稿件说明：
移动端阅览
Fan WU, Hui-qin WANG, Ke WANG. Spatio-temporal deep learning fire smoke detection[J]. Chinese journal of liquid crystals and displays, 2021, 36(8): 1186-1195.
DOI：

Fan WU, Hui-qin WANG, Ke WANG. Spatio-temporal deep learning fire smoke detection[J]. Chinese journal of liquid crystals and displays, 2021, 36(8): 1186-1195. DOI： 10.37188/CJLCD.2020-0239.

摘要

烟雾是火灾早期检测的重要特征。传统机器学习及二维卷积神经网络烟雾检测算法对烟雾特征的提取局限于空间领域，无法提取时域信息。现有的三维卷积神经网络检测算法则存在计算成本高、检测时效低的问题，导致检测准确率和虚警率不理想。针对上述问题，本文提出一种基于时空域深度学习的烟雾视频检测方法。利用分块运动目标检测方法提取烟雾视频的运动目标，过滤非烟雾目标；同时将三维卷积神经网络拆分，形成一种二加一维时空域网络模块，提取时空域特征，提高检测时效。为抑制无关特征，引入注意力机制，增加压缩和激励网络重新标定特征通道权重，提升烟雾检测准确率。研究结果表明，本文所用算法的平均准确率为97.12%，平均正确率为97.06%，平均虚警率为2.74%，平均检测帧率为10.49帧/s，满足火灾烟雾探测需求，检测时效得到明显提高。

Abstract

Smoke is an important feature of early fire detection. The extraction of smoke features by traditional machine learning and two-dimensional convolutional neural network smoke detection algorithms are limited to the spatial domain

and cannot extract temporal information. The existing three-dimensional convolutional neural network detection algorithm has the problems of high calculation cost and low detection time efficiency

which leads to unsatisfactory detection accuracy and false alarm rate. To solve the above problems

a smoke video detection method based on deep learning in spatio-temporal domain is proposed. The block moving target detection method is used to extract the moving targets of the smoke video and filter the non-smoke targets. At the same time

the three-dimensional convolutional neural network is split to form a two-plus-one-dimensional spatio-temporal network module

which extracts the characteristics of the spatio-temporal domain and improves the detection time efficiency. In order to suppress irrelevant features

an attention mechanism is introduced to increase the compression and incentive network to recalibrate the weight of feature channels to improve the accuracy of smoke detection. The research results show that the average accuracy rate of the algorithm used in this paper is 97.12%

the average correct rate is 97.06%

the average false alarm rate is 2.74%

and the average detection frame rate is 10.49 frame/s. The needs of fire smoke detection is met

and the detection timeliness is improved significantly.

关键词

Keywords

references

史劲亭 , 袁非牛 , 夏雪 . 视频烟雾检测研究进展 . 中国图象图形学报 , 2018 . 233 ( 3 ): 303 - 322 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201803001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201803001.htm .

J T SHI , F N YUAN , X XIA . Video smoke detection: a literature survey . Journal of Image and Graphics , 2018 . 23 ( 3 ): 303 - 322 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201803001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201803001.htm .

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.

WU F. Research and implementation of fire detection algorithm based on deep learning[D]. Hangzhou: Hangzhou Dianzi University, 2020. (in Chinese)

袁非牛 , 夏雪 , 李钢 , 等 . 面向烟雾识别与纹理分类的Gabor网络 . 中国图象图形学报 , 2019 . 24 ( 2 ): 269 - 281 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201902011.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201902011.htm .

F N YUAN , X XIA , G LI , 等 . GaborNet for smoke recognition and texture classification . Journal of Image and Graphics , 2019 . 24 ( 2 ): 269 - 281 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201902011.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201902011.htm .

BARMPOUTIS P, DIMITROPOULOS K, GRAMMALIDIS N. Smoke detection using spatio-temporal analysis, motion modeling and dynamic texture recognition[C]// Proceedings of the 201422 nd European Signal Processing Conference . Lisbon: IEEE, 2014: 1078-1082.

PARK J O, KO B C, NAM J Y, et al . Wildfire smoke detection using spatiotemporal bag-of-features of smoke[C]// Proceedings of 2013 IEEE Workshop on Applications of Computer Vision . Clearwater Beach: IEEE, 2013: 200-205.

李红娣 , 袁非牛 . 采用金字塔纹理和边缘特征的图像烟雾检测 . 中国图象图形学报 , 2015 . 20 ( 6 ): 772 - 780 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201506006.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201506006.htm .

H D LI , F N YUAN . Image based smoke detection using pyramid texture and edge features . Journal of Image and Graphics , 2015 . 20 ( 6 ): 772 - 780 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201506006.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201506006.htm .

Y Q ZHAO , Q J LI , Z GU . Early smoke detection of forest fire video using CS Adaboost algorithm . Optik-International Journal for Light and Electron Optics , 2015 . 126 ( 19 ): 2121 - 2124 . DOI: 10.1016/j.ijleo.2015.05.082 http://doi.org/10.1016/j.ijleo.2015.05.082 .

陈献明 , 王阿川 , 王春艳 . 基于深度学习的木材表面缺陷图像检测 . 液晶与显示 , 2019 . 34 ( 9 ): 879 - 887 . DOI: 10.3788/YJYXS20193409.0879 http://doi.org/10.3788/YJYXS20193409.0879 .

X M CHEN , A C WANG , C Y WANG . Image detection of wood surface defects based on deep learning . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 9 ): 879 - 887 . DOI: 10.3788/YJYXS20193409.0879 http://doi.org/10.3788/YJYXS20193409.0879 .

Y J KIM , E G KIM . Image based fire detection using convolutional neural network . Journal of the Korea Institute of Information and Communication Engineering , 2016 . 20 ( 9 ): 1649 - 1656 . DOI: 10.6109/jkiice.2016.20.9.1649 http://doi.org/10.6109/jkiice.2016.20.9.1649 .

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 . DOI: 10.3969/j.issn.1001-0548.2016.06.020 http://doi.org/10.3969/j.issn.1001-0548.2016.06.020 .

J Z CHEN , Z J WANG , H H CHEN , 等 . Dynamic smoke detection using cascaded convolutional neural network for surveillance videos . Journal of University of Electronic Science and Technology of China , 2016 . 46 ( 6 ): 992 - 996 . DOI: 10.3969/j.issn.1001-0548.2016.06.020 http://doi.org/10.3969/j.issn.1001-0548.2016.06.020 .

孙颖. 基于3D残差密集网络的视频烟雾检测研究[D]. 长春: 东北师范大学, 2019.

SUN Y. Video smoke detection based on 3D residual dense network[D]. Changchun: Northeast Normal University, 2019. (in Chinese)

程淑红 , 马继勇 , 张仕军 , 等 . 改进的混合高斯与YOLOv2融合烟雾检测算法 . 计量学报 , 2019 . 40 ( 5 ): 798 - 803 . DOI: 10.3969/j.issn.1000-1158.2019.05.10 http://doi.org/10.3969/j.issn.1000-1158.2019.05.10 .

S H CHENG , J Y MA , S J ZHANG , 等 . Smoke detection algorithm combined with improved Gaussian mixture and YOLOv2 . Acta Metrologica Sinica , 2019 . 40 ( 5 ): 798 - 803 . DOI: 10.3969/j.issn.1000-1158.2019.05.10 http://doi.org/10.3969/j.issn.1000-1158.2019.05.10 .

纪青华 , 禹素萍 . 基于Surendra背景减除法和四帧差分法的目标检测算法 . 计算机应用与软件 , 2014 . 31 ( 12 ): 242 - 244 . DOI: 10.3969/j.issn.1000-386x.2014.12.058 http://doi.org/10.3969/j.issn.1000-386x.2014.12.058 .

Q H JI , S P YU . Object detection algorithm based on surendra background subtraction and four-frame difference . Computer Applications and Software , 2014 . 31 ( 12 ): 242 - 244 . DOI: 10.3969/j.issn.1000-386x.2014.12.058 http://doi.org/10.3969/j.issn.1000-386x.2014.12.058 .

TRAN D, WANG H, TORRESANI L, et al . A closer look at spatiotemporal convolutions for action recognition[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6450-6459.

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32 nd International Conference on Machine Learning . Lille: JMLR. org, 2015: 448-456.

X GLOROT , A BORDES , Y BENGIO . Deep sparse rectifier neural networks . Journal of Machine Learning Research , 2011 . 15 315 - 323 . http://www.researchgate.net/publication/215616967_Deep_Sparse_Rectifier_Neural_Networks http://www.researchgate.net/publication/215616967_Deep_Sparse_Rectifier_Neural_Networks .

J HU , L SHEN , S ALBANIE , 等 . Squeeze-and-excitation networks . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 . 42 ( 8 ): 2011 - 2023 . DOI: 10.1109/TPAMI.2019.2913372 http://doi.org/10.1109/TPAMI.2019.2913372 .

张斌 , 魏维 , 高联欣 , 等 . 基于时空域深度神经网络的野火视频烟雾检测 . 计算机应用与软件 , 2019 . 36 ( 9 ): 236 - 242, 259 . DOI: 10.3969/j.issn.1000-386x.2019.09.042 http://doi.org/10.3969/j.issn.1000-386x.2019.09.042 .

B ZHANG , W WEI , L X GAO , 等 . Wildfire video smoke detection based on spatio-temporal deep neural network . Computer Applications and Software , 2019 . 36 ( 9 ): 236 - 242, 259 . DOI: 10.3969/j.issn.1000-386x.2019.09.042 http://doi.org/10.3969/j.issn.1000-386x.2019.09.042 .

F N YUAN . Video-based smoke detection with histogram sequence of LBP and LBPV pyramids . Fire Safety Journal , 2011 . 46 ( 3 ): 132 - 139 . DOI: 10.1016/j.firesaf.2011.01.001 http://doi.org/10.1016/j.firesaf.2011.01.001 .

王涛 , 宫宁生 , 蒋贵祥 . 基于深度学习的烟雾识别研究 . 电子技术应用 , 2018 . 44 ( 10 ): 131 - 135 . https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY201810031.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY201810031.htm .

T WANG , N S GONG , G X JIANG . Smoke recognition based on the depth learning . Application of Electronic Technique , 2018 . 44 ( 10 ): 131 - 135 . https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY201810031.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY201810031.htm .

王洋 , 程江华 , 刘通 , 等 . 一种多网络模型融合的烟雾检测方法 . 计算机工程与科学 , 2019 . 41 ( 10 ): 1771 - 1776 . DOI: 10.3969/j.issn.1007-130X.2019.10.008 http://doi.org/10.3969/j.issn.1007-130X.2019.10.008 .

Y WANG , J H CHENG , T LIU , 等 . A smoke detection method based on fusing multiple network models . Computer Engineering and Science , 2019 . 41 ( 10 ): 1771 - 1776 . DOI: 10.3969/j.issn.1007-130X.2019.10.008 http://doi.org/10.3969/j.issn.1007-130X.2019.10.008 .

Views

372

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

3D hand reconstruction method based on adaptive occlusion recovery and topology-pose bidirectional perception

Fatigue driving detection based on improved YOLOv8n-Pose

Remote sensing scene classification model based on improved ShuffleNetV2 network

Lens-free adversarial encoded imaging method based on convolutional attention mechanism

Related Author

Fan WU

Hui-qin WANG

Ke WANG

LIU Jia

HUANG Nanxuan

CHEN Dapeng

WEI Lina

CAI Zhongqi

Related Institution

College of Information and Control Engineering， Xi'an University of Architecture and Technology

School of Automation， Nanjing University of Information Science & Technology

School of Computer and Computing Science， Hangzhou City University

School of Advanced Manufacturing， Fuzhou University

Fujian Science and Technology Innovation Laboratory for Photoelectric Information

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰