Skip to main content

Advertisement

Springer Nature Link
Log in

Fire Detection Method Based on Depthwise Separable Convolution and YOLOv3

  • Research Article
  • Published:
International Journal of Automation and Computing Aims and scope Submit manuscript

Abstract

Recently, video-based fire detection technology has become an important research topic in the field of machine vision. This paper proposes a method of combining the classification model and target detection model in deep learning for fire detection. Firstly, the depthwise separable convolution is used to classify fire images, which saves a lot of detection time under the premise of ensuring detection accuracy. Secondly, You Only Look Once version 3 (YOLOv3) target regression function is used to output the fire position information for the images whose classification result is fire, which avoids the problem that the accuracy of detection cannot be guaranteed by using YOLOv3 for target classification and position regression. At the same time, the detection time of target regression for images without fire is greatly reduced saved. The experiments were tested using a network public database. The detection accuracy reached 98% and the detection rate reached 38 fps. This method not only saves the workload of manually extracting flame characteristics, reduces the calculation cost, and reduces the amount of parameters, but also improves the detection accuracy and detection rate.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. F. Saeed, A. Paul, W. H. Hong, H. Seo. Machine learning based approach for multimedia surveillance during fire emergencies. Multimedia Tools and Applications, vol. 79, no. 23, pp. 16201–16217, 2020. DOI: https://doi.org/10.1007/s11042-019-7548-x.

    Article  Google Scholar 

  2. F. Saeed, A. Paul, A. Rehman, W. H. Hong, H. Seo. IoT-based intelligent modeling of smart home environment for fire prevention and safety. Journal of Sensor and Actuator Networks, vol. 7, no. 1, Article number 11, 2018. DOI: https://doi.org/10.3390/jsan7010011.

  3. M. J. Park, B. C. Ko. Two-step real-time night-time fire detection in an urban environment using static ELASTIC-YOLOv3 and temporal fire-tube. Sensors, vol. 20, no. 8, Article number 2202, 2020. DOI: https://doi.org/10.3390/s20082202.

  4. J. H. Li, R. X. Fan, Z. B. Chen. Forest fire recognition based on color and texture features. Journal of South China University of Technology (Natural Science Edition), vol. 48, no. 1, pp. 70–83, 2020. DOI: https://doi.org/10.12141/j.issn.1000-565X.190181. (in Chinese)

    Google Scholar 

  5. N. M. Dung, B. Choi, S. Ro. A study on the fire detection algorithm using surveillance camera systems. The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 6, pp. 921–929, 2018. DOI: https://doi.org/10.7840/kics.2018.43.6.921.

    Article  Google Scholar 

  6. V. K. Ha, J. C. Ren, X. Y. Xu, S. Zhao, G. Xie, V. Masero, A. Hussain. Deep learning based single image super-resolution: A survey. International Journal of Automation and Computing, vol. 16, no. 4, pp. 413–426, 2019. DOI: https://doi.org/10.1007/s11633-019-1183-x.

    Article  Google Scholar 

  7. G. F. Shidik, F. N. Adnan, C. Supriyanto, R. A. Pramunendar, P. N. Andono. Multi color feature, background subtraction and time frame selection for fire detection. In Proceedings of International Conference on Robotics, Biomimetics, Intelligent Computational Systems, IEEE, Jogjakarta, Indonesia, pp. 115–120, 2013. DOI: https://doi.org/10.1109/ROBIONETICS.2013.6743589.

    Google Scholar 

  8. X. F. Han, J. S. Jin, M. J. Wang, W. Jiang, L. Gao, L. P. Xiao. Video fire detection based on Gaussian mixture model and multi-color features. Signal, Image and Video Processing, vol. 11, no. 8, pp. 1419–1425, 2017. DOI: https://doi.org/10.1007/s11760-017-1102-y.

    Article  Google Scholar 

  9. S. T. Zeng, H. B. Wu, P. H. Shen. Video fire detection based on fusion of multiple features. Journal of Graphics, vol. 38, no. 4, pp. 549–557, 2017. DOI: https://doi.org/10.11996/JG.J.2095-302X.2017040549. (in Chinese)

    Google Scholar 

  10. C. E. Prema, S. S. Vinsley, S. Suresh. Multi feature analysis of smoke in YUV color space for early forest fire detection. Fire Technology, vol. 52, no. 5, pp. 1319–1342, 2016. DOI: https://doi.org/10.1007/s10694-016-0580-8.

    Article  Google Scholar 

  11. C. E. Prema, S. S. Vinsley, S. Suresh. Efficient flame detection based on static and dynamic texture analysis in forest fire detection. Fire Technology, vol. 54, no. 1, pp. 255–288, 2018. DOI: https://doi.org/10.1007/s10694-017-0683-x.

    Article  Google Scholar 

  12. L. Shi, F. F. Shi, T. Wang, L. P. Bu, X. G. Hou. A new fire detection method based on the centroid variety of consecutive frames. In Proceedings of the 2nd International Conference on Image, Vision and Computing, IEEE, Chengdu, China, pp. 437–442, 2017. DOI: https://doi.org/10.1109/ICIVC.2017.7984594.

    Google Scholar 

  13. P. Foggia, A. Saggese, M. Vento. Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 9, pp. 1545–1556, 2015. DOI: https://doi.org/10.1109/TCSVT.2015.2392531.

    Article  Google Scholar 

  14. S. Q. Li, W. Liu, H. D. Ma, H. Y. Fu. Multi-attribute based fire detection in diverse surveillance videos. In Proceedings of the 23rd International Conference on Multimedia Modeling, Springer, Reykjavik, Iceland, pp. 238–250, 2017. DOI: https://doi.org/10.1007/978-3-319-51811-4_20.

    Google Scholar 

  15. S. Frizzi, R. Kaabi, M. Bouchouicha, J. M. Ginoux, E. Moreau, F. Fnaiech. Convolutional neural network for video fire and smoke detection. In Proceedings of the 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, pp. 877–882, 2016. DOI: https://doi.org/10.1109/IECON.2016.7793196.

  16. K. Muhammad, J. Ahmad, I. Mehmood, S. Rho, S. W. Baik. Convolutional neural networks based fire detection in surveillance videos. IEEE Access, vol. 6, pp. 18174–18183, 2018. DOI: https://doi.org/10.1109/ACCESS.2018.2812835.

    Article  Google Scholar 

  17. K. Muhammad, J. Ahmad, Z. H. Lv, P. Bellavista, P. Yang, S. W. Baik. Efficient deep CNN-based fire detection and localization in video surveillance applications. IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 49, no. 7, pp. 1419–1434, 2019. DOI: https://doi.org/10.1109/TSMC.2018.2830099.

    Article  Google Scholar 

  18. F. Saeed, A. Paul, P. Karthigaikumar, A. Nayyar. Convolutional neural network based early fire detection. Multimedia Tools and Applications, vol. 79, no. 13, pp. 9083–9099, 2020.

    Article  Google Scholar 

  19. B. Kim, J. Lee. A video-based fire detection using deep learning models. Applied Science, vol. 9, no. 14, Article number 2862, 2019. DOI: https://doi.org/10.3390/app9142862.

  20. H. Liau, N. Yamini, Y. L. Wong. Fire SSD: Wide fire modules based single shot detector on edge device. [Online], Available: https://arxiv.org/abs/1806.05363, 2018.

  21. D. Q. Shen, X. Chen, M. Nguyen, W. Q. Yan. Flame detection using deep learning. In Proceedings of the 4th International Conference on Control, Automation and Robotics, IEEE, Auckland, New Zealand, pp. 416–420, 2018. DOI: https://doi.org/10.1109/ICCAR.2018.8384711.

    Google Scholar 

  22. C. X. Du, Y. Y. Yan, Y. A. Liu, S. B. Gao. Video fire detection method based on YOLOv2. Computer Science, vol. 46, no. 6, pp. 301–304, 2019. DOI: https://doi.org/10.11896/j.issn.1002-137x.2019.06.045. (in Chinese)

    Google Scholar 

  23. J. F. Ren, W. H. Xiong, Z. H. Wu, M. Jiang. Fire detection and identification based on improved YOLOv3. Computer Systems and Applications, vol. 28, no. 12, pp. 171–176, 2019. (in Chinese)

    Google Scholar 

  24. L. Ma, M. C. Li, X. X. Ma, L. Cheng, P. J. Du, Y. X. Liu. A review of supervised object-based land-cover image classification. ISPRS Journal of Photogrammetry and Remote Sensing, vol. 130, pp. 277–293, 2017. DOI: https://doi.org/10.1016/j.isprsjprs.2017.06.001.

    Article  Google Scholar 

  25. H. Wu, Z. W. Chen, G. H. Tian, Q. Ma, M. L. Jiao. Item ownership relationship semantic learning strategy for personalized service robot. International Journal of Automation and Computing, vol. 17, no. 3, pp. 390–402, 2020. DOI: https://doi.org/10.1007/s11633-019-1206-7.

    Article  Google Scholar 

  26. Q. F. Liu, H. L. Zhang, Y. L. Wang. Real-time pixel-wise classification of agricultural images based on depthwise separable convolution. Scientia Agricultura Sinica, vol. 51, no. 19, pp. 3673–3682, 2018. DOI: https://doi.org/10.3864/j.issn.0578-1752.2018.19.005. (in Chinese)

    Google Scholar 

  27. B. Liu, S. Z. Wang, J. S. Zhao, M. F. Li. Ship tracking and recognition based on Darknet network and YOLOv3 algorithm. Journal of Computer Applications, vol. 39, no. 6, pp. 1663–1668, 2019. DOI: https://doi.org/10.11772/j.issn.1001-9081.2018102190. (in Chinese)

    Google Scholar 

  28. M. R. Ju, H. B. Luo, Z. B. Wang, M. He, Z. Chang, B. Hui. Improved YOLOv3 algorithm and its application in small target detection. Acta Optica Sinica, vol. 39, no. 7, Article number 0715004, 2019. DOI: https://doi.org/10.3788/AOS201939.0715004. (in Chinese)

  29. W. J. Chai, L. M. Wang. Recognition of Chinese characters using deep convolutional neural network. Journal of Image and Graphics, vol. 23, no. 3, pp. 410–417, 2018. DOI: https://doi.org/10.11834/jig.170399. (in Chinese)

    Google Scholar 

Download references

Acknowledgements

This work was supported by Liaoning Provincial Science Public Welfare Research Fund Project (No. 2016 002006), and Liaoning Provincial Department of Education Scientific Research Service Local Project (No. L201708).

Author information

Authors and Affiliations

  1. School of Information and Control Engineering, Liaoning Shihua University, Fushun, 113001, China

    Yue-Yan Qin & Jiang-Tao Cao

  2. School of Automation, Shenyang Aerospace University, Shenyang, 110136, China

    Xiao-Fei Ji

Authors
  1. Yue-Yan Qin
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jiang-Tao Cao
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Xiao-Fei Ji
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Xiao-Fei Ji.

Additional information

Colored figures are available in the online version at https://link.springer.com/journal/11633

Yue-Yan Qin is a master student in control theory and control engineering at Liaoning Shihua University, China.

Her research interests include image processing and intelligent video analysis.

E-mail: 18341318515@163.com

ORCID iD: 0000-0002-6225-3519

Jiang-Tao Cao received the Ph.D. degree in intelligent control from University of Portsmouth, China in 2009. Now, he is a professor and M.Sc. supervisor at Liaoning Shihua University, China.

His research interests include intelligent method and its application, and video analysis.

E-mail: cigroup@126.com

Xiao-Fei Ji received the M.Sc. in control theory and control engineering from Liaoning Shihua University, China in 2003, and the Ph.D. degree in pattern recognition and intelligent systems from University of Portsmouth, UK in 2010. From 2003 to 2012, she was a lecturer with School of Automation, Shenyang Aerospace University, China. Since 2013, she has been an associate professor with Shenyang Aerospace University, China. She has published over 40 technical research papers and 3 books. She is the leader of National Natural Science Foundation Project (61103123) and six national and local government projects.

Her research interests include vision analysis and pattern recognition, information processing and fusion.

E-mail: jixiaofei7804@126.com (Corresponding author)

ORCID iD: 0000-0001-8279-7727

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qin, YY., Cao, JT. & Ji, XF. Fire Detection Method Based on Depthwise Separable Convolution and YOLOv3. Int. J. Autom. Comput. 18, 300–310 (2021). https://doi.org/10.1007/s11633-020-1269-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11633-020-1269-5

Keywords