Skip to main content

Fire and Smoke Detection Using Capsule Network

Fire Technology volume 59, pages 581–594 (2023)Cite this article

Abstract

Video surveillance and image processing approaches are widely used nowadays for security and safety purposes. Such systems are also effective for smoke and fire detection and are one of the safety techniques to eliminate the drastic situation in their early stage. Detection of fire and smoke incidents in their early stages is of utmost importance. The conventional detectors having several limitations are now being replaced with intelligent video-based sensors. Training an efficient fire and smoke detection system using smart video-based detectors required a massive amount of annotated data describing unique fire patterns. This work presents a real-time video-based fire and smoke detection in its early stages while suppressing false alarms due to varying illumination (i.e., weather conditions), burning patterns, fog, cloud, and distinctive characteristics of fire and smoke, etc. The model is trained using Capsule Network-based architecture on different fire and smoke patterns obtained from publicly available datasets. Experimental results showed that the proposed architecture improved significantly in terms of accuracy, final model size, and false-positive rate on both binary and multiclass classification of fire and smoke compared with various state-of-the-art studies. These results validate the proposed architecture's generalizability and suitability for intelligent video-based fire and smoke detection using CCTV cameras.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

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

Figure 1
Figure 2
Figure 3
Figure 4

References

  1. Pritam D, Dewan JH (2017) Detection of fire using image processing techniques with LUV color space. In: 2017 2nd international conference for Convergence in Technology (I2CT). https://doi.org/10.1109/i2ct.2017.8226309

  2. Wu X, Lu X, Leung H (2018) A video based fire smoke detection using robust AdaBoost. Sensors. https://doi.org/10.3390/s18113780

    Article  Google Scholar 

  3. Ojo JA, Oladosu JA (2014) Video-based smoke detection algorithms: a chronological survey. Comput Eng Intell Syst 5:38–50

    Google Scholar 

  4. Toulouse T, Rossi L, Campana A, Celik T, Akhloufi MA (2017) Computer vision for wildfire research: an evolving image dataset for processing and analysis. Fire Saf J 92:188–194

    Article  Google Scholar 

  5. Avgerinakis K, Briassouli A, Kompatsiaris I (2012) Smoke detection using temporal hoghof descriptors and energy colour statistics from video. In: International workshop on multi-sensor systems and networks for fire detection and management, pp 3–6

  6. Töreyin BU, Dedeoğlu Y, Çetin AE (2005) Wavelet based real-time smoke detection in video. In: 2005 13th European signal processing conference, pp 1–4

  7. Healey G, Slater D, Lin T, Drda B, Goedeke AD (1993) A system for real-time fire detection. In: Proceedings of IEEE conference on computer vision and pattern recognition. IEEE Computing Society Press. pp 605–606

  8. Mohammed TA, Mohammed AA (2017) Real time video surveillance system for fire and smoke detection based on wavelet transform. J Zankoy Sulaimani A 19:229–238

    Article  Google Scholar 

  9. Toreyin BU, Cetin AE (2007) Online detection of fire in video. In: 2007 IEEE conference on computer vision and pattern recognition. IEEE, p 1–5

  10. Zhang Q, Xu J, Xu L, Guo H (2016) Deep convolutional neural networks for forest fire detection. In: Proceedings of the 2016 international forum on management, education and information technology application. Atlantis Press, Paris. pp 568–575

  11. Muhammad K, Ahmad J, Lv Z, Bellavista P, Yang P, Baik SW (2019) Efficient deep CNN-based fire detection and localization in video surveillance applications. IEEE Trans Syst Man Cybern 49:1419–1434

    Article  Google Scholar 

  12. Tripathi A, Swarup S (2017) Visual smoke detection. Springer, Cham, pp 1–14

    Google Scholar 

  13. Appana DK, Islam R, Khan SA, Kim J-M (2017) A video-based smoke detection using smoke flow pattern and spatial-temporal energy analyses for alarm systems. Inf Sci. https://doi.org/10.1016/j.ins.2017.08.001

    Article  Google Scholar 

  14. Saeed F, Paul A, Karthigaikumar P, Nayyar A (2019) Convolutional neural network based early fire detection. Multimed Tools Appl Multimed Tools Appl. https://doi.org/10.1007/s11042-019-07785-w

    Article  Google Scholar 

  15. Huttner V, Steffens CR, da Costa Botelho SS (2017) First response fire combat: deep leaning based visible fire detection. 2017 Latin American Robotics Symposium (LARS) and 2017 Brazilian Symposium on Robotics (SBR). https://doi.org/10.1109/sbr-lars-r.2017.8215312

  16. Chenebert A, Breckon TP, Gaszczak A (2011) A non-temporal texture driven approach to real-time fire detection. In: 2011 18th IEEE international conference on image processing. https://doi.org/10.1109/icip.2011.6115796

  17. Jadon A, Omama M, Varshney A, Ansari MS, Sharma R (2019) FireNet: a Specialized Lightweight Fire & Smoke Detection Model for Real-Time IoT Applications. arXiv [cs.CV]. http://arxiv.org/abs/1905.11922

  18. Afshar P, Heidarian S, Naderkhani F, Oikonomou A, Plataniotis KN, Mohammadi A (2020) COVID-CAPS: a capsule network-based framework for identification of COVID-19 cases from X-ray images. Pattern Recognit Lett 138:638–643

    Article  Google Scholar 

  19. Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. arXiv [cs.CV]. http://arxiv.org/abs/1710.09829

  20. Hinton G, Sabour S, Frosst N. MATRIX CAPSULES WITH EM ROUTING

  21. Mivia. Fire Detection Dataset. [cited 2021 May 28]. https://mivia.unisa.it/datasets/video-analysis-datasets/fire-detection-dataset/

  22. DeepQuestAI. DeepQuestAI/Fire-Smoke-Dataset. [cited 2021 May 28]. https://github.com/DeepQuestAI/Fire-Smoke-Dataset

  23. Muhammad K, Ahmad J, Mehmood I, Rho S, Baik SW (2018) Convolutional neural networks based fire detection in surveillance videos. IEEE Access. https://doi.org/10.1109/access.2018.2812835

    Article  Google Scholar 

  24. Muhammad K, Ahmad J, Baik SW (2018) Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing. https://doi.org/10.1016/j.neucom.2017.04.083

    Article  Google Scholar 

  25. Gotthans J, Gotthans T, Marsalek R (2020) Deep convolutional neural network for fire detection. In: 2020 30th international conference radioelektronika (RADIOELEKTRONIKA). 2020. https://doi.org/10.1109/radioelektronika49387.2020.9092344

  26. Jadon A, Varshney A, Ansari MS (2020) Low-complexity high-performance deep learning model for real-time low-cost embedded fire detection systems. Proc Comput Sci 171:418–426

    Article  Google Scholar 

  27. Foggia P, Saggese A, Vento M (2015) Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/tcsvt.2015.2392531

    Article  Google Scholar 

  28. Lascio RD, Di Lascio R, Greco A, Saggese A, Vento M (2014) Improving fire detection reliability by a combination of videoanalytics. Lect Notes Comput Sci. https://doi.org/10.1007/978-3-319-11758-4_52

    Article  Google Scholar 

  29. Habiboğlu YH, Günay O, Enis Çetin A (2012) Covariance matrix-based fire and flame detection method in video. Mach Vis Appl. https://doi.org/10.1007/s00138-011-0369-1

    Article  Google Scholar 

  30. Rafiee A, Dianat R, Jamshidi M, Tavakoli R, Abbaspour S (2011) Fire and smoke detection using wavelet analysis and disorder characteristics. In: 2011 3rd international conference on computer research and development. https://doi.org/10.1109/iccrd.2011.5764295

  31. Çelik T, Demirel H (2009) Fire detection in video sequences using a generic color model. Fire Saf J. https://doi.org/10.1016/j.firesaf.2008.05.005

    Article  Google Scholar 

  32. Khudayberdiev O, Butt MH (2020) Fire detection in surveillance videos using a combination with PCA and CNN. Acad J Comput Inf Sci 3:3

    Google Scholar 

  33. Avula SB, Badri SJ, Reddy G (2020) A novel forest fire detection system using fuzzy entropy optimized thresholding and STN-based CNN. In: 2020 international conference on COMmunication Systems & NETworkS (COMSNETS) 2020 Jan 7, pp 750–755. IEEE

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, COMSATS University Islamabad, Lahore Campus, 1.5 KM Defence Road Off Raiwind Road, Lahore, Pakistan

    Rafaqat Alam Khan, Ali Hussain, Usama Ijaz Bajwa & Muhammad Waqas Anwar

  2. Electronics and Power Engineering Department, Pakistan Navy Engineering College (PNEC), National University of Sciences and Technology (NUST), Habib Ibrahim Rehmatullah Road, Karachi, Pakistan

    Rana Hammad Raza

Authors
  1. Rafaqat Alam Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ali Hussain
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Usama Ijaz Bajwa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rana Hammad Raza
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Muhammad Waqas Anwar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Usama Ijaz Bajwa.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Khan, R.A., Hussain, A., Bajwa, U.I. et al. Fire and Smoke Detection Using Capsule Network. Fire Technol 59, 581–594 (2023). https://doi.org/10.1007/s10694-022-01352-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10694-022-01352-w

Keywords

  • Capsule network
  • CCTV surveillance videos
  • Deep learning
  • Fire detection
  • FPR
  • Smoke detection
  • Model size