Skip to main content
SpringerLink
Log in

Evaluation on algorithm reliability and efficiency for an image flame detection technology

  • Published:
Journal of Thermal Analysis and Calorimetry Aims and scope Submit manuscript

Abstract

Image-based flame detection (IBFD) algorithms are effective in flame detection, and their advantages and disadvantages directly affect the accuracy and timeliness of flame detection. However, based on the existing research in China, the IBFD algorithm still lacks a clear standard for distinguishing advantages and disadvantages. This study adopted a fuzzy comprehensive hierarchical analysis method to establish an evaluation method for IBFD and to define the rating standards for 29 third-level evaluation indexes. A three-level index system was installed for algorithm evaluation, and the masses of needles at all levels were determined. An index system was used to assign indexes to the two flame identification algorithms in the YOLOv3 series. The algorithm evaluation was completed according to the mass of the algorithm index, which indicated the reliability and validity of the algorithm evaluation method. Therefore, this study established a set of methods for the performance evaluation of IBFD and thus laid a theoretical foundation for improving relevant standards for image-based flame detectors.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Abbreviations

a ij :

The lower limit of the interval (dimensionless)

b ij :

The upper limit of the interval (dimensionless)

x i :

Eigenvalues (dimensionless)

A i :

Matrix vector (dimensionless)

w j :

Row vector (dimensionless)

W :

Mass vector (dimensionless)

K :

Level matrix (dimensionless)

References

  1. Zhang HJ, Zhang N, Xiao NF. Fire detection and identification method based on visual attention mechanism. Optik. 2015;126:5011–8. https://doi.org/10.1016/j.ijleo.2015.09.167.

    Article  Google Scholar 

  2. Çelik T, Demirel H. Fire detection in video sequences using a generic color model. Fire Saf J. 2009;44:147–58. https://doi.org/10.1016/j.firesaf.2008.05.005.

    Article  Google Scholar 

  3. Tan L, Lv X, Lian X, Wang G. YOLOv4_Drone: UAV image target detection based on an improved YOLOv4 algorithm. Comput. 2021;93:107261. https://doi.org/10.1016/j.compeleceng.2021.107261.

    Article  Google Scholar 

  4. Zhang Z, Jin Q, Wang L, Liu Z. Video-based fire smoke detection using temporal-spatial saliency features. Procedia Comput Sci. 2022;198:493–8. https://doi.org/10.1016/j.procs.2021.12.275.

    Article  Google Scholar 

  5. Huang L, Liu G, Wang Y, Yuan H, Chen T. Fire detection in video surveillances using convolutional neural networks and wavelet transform. Eng Appl Artif Intel. 2022;110:104737. https://doi.org/10.1016/j.engappai.2022.104737.

    Article  Google Scholar 

  6. Schröder T, Krüger K, Kümmerlen F. Image processing based deflagration detection using fuzzy logic classification. Fire Saf J. 2014;65:1–10. https://doi.org/10.1016/j.firesaf.2014.02.004.

    Article  CAS  Google Scholar 

  7. Li Y, Vodacek A, Zhu Y. An automatic statistical segmentation algorithm for extraction of fire and smoke regions. Remote Sens Environ. 2007;108:171–8. https://doi.org/10.1016/j.rse.2006.10.023.

    Article  Google Scholar 

  8. Yu C, Mei Z, Zhang X. A real-time video fire flame and smoke detection algorithm. Procedia Eng. 2013;62:891–8. https://doi.org/10.1016/j.proeng.2013.08.140.

    Article  Google Scholar 

  9. Marbach G, Loepfe M, Brupbacher T. An image processing technique for fire detection in video images. Fire Saf J. 2006;41:285–9. https://doi.org/10.1016/j.firesaf.2006.02.001.

    Article  Google Scholar 

  10. Rosas-Romero R. Remote detection of forest fires from video signals with classifiers based on K-SVD learned dictionaries. Eng Appl Artif Intel. 2014;33:1–11. https://doi.org/10.1016/j.engappai.2014.03.011.

    Article  Google Scholar 

  11. Hu Y, Zhan J, Zhou G, Chen A, Cai W, Guo K. Fast forest fire smoke detection using MVMNet. Knowl Based Syst. 2022;241:108219. https://doi.org/10.1016/j.knosys.2022.108219.

    Article  Google Scholar 

  12. Mohajane M, Costache R, Karimi F, Bao Pham Q, Essahlaoui A, Nguyen H. Application of remote sensing and machine learning algorithms for forest fire mapping in a mediterranean area. Ecol Indic. 2021;129:107869. https://doi.org/10.1016/j.ecolind.2021.107869.

    Article  Google Scholar 

  13. Wang Y, Yu Y, Zhu X, Zhang Z. Pattern recognition for measuring the flame stability of gas-fired combustion based on the image processing technology. Fuel. 2020;270:117486. https://doi.org/10.1016/j.fuel.2020.117486.

    Article  CAS  Google Scholar 

  14. Xu W, Wooster MJ, He J, Zhang T. Improvements in high-temporal resolution active fire detection and FRP retrieval over the Americas using GOES-16 ABI with the geostationary fire thermal anomaly (FTA) algorithm. Remote Sens. 2021;3:100016. https://doi.org/10.1016/j.srs.2021.100016.

    Article  Google Scholar 

  15. Li P, Zhao W. Image fire detection algorithms based on convolutional neural networks. Case Stud Therm Eng. 2020;19:100625. https://doi.org/10.1016/j.csite.2020.100625.

    Article  Google Scholar 

  16. Li P, Yang Y, Zhao W, Zhang M. Evaluation of image fire detection algorithms based on image complexity. Fire Saf J. 2021;121:103306. https://doi.org/10.1016/j.firesaf.2021.103306.

    Article  Google Scholar 

  17. Wei YY, Zhang JY, Wang J. Research on building fire risk fast assessment method based on fuzzy comprehensive evaluation and SVM. Procedia Eng. 2018;211:1141–50. https://doi.org/10.1016/j.proeng.2017.12.121.

    Article  Google Scholar 

  18. Zhao Y, Li Q, Gu Z. Early smoke detection of forest fire video using CS adaboost algorithm. Optik. 2015;126:2121–4. https://doi.org/10.1016/j.ijleo.2015.05.082.

    Article  Google Scholar 

  19. Liu Z, Zhang K, Wang C, Huang S. Research on the identification method for the forest fire based on deep learning. Optik. 2020;223:165491. https://doi.org/10.1016/j.ijleo.2020.165491.

    Article  Google Scholar 

  20. Singh KR, Neethu KP, Madhurekaa K, Harita A, Mohan P. Parallel SVM model for forest fire prediction. Soft Comput. 2021;3:100014. https://doi.org/10.1016/j.socl.2021.100014.

    Article  Google Scholar 

  21. Wang SD, Miao LL, Peng GX. An improved algorithm for forest fire detection using HJ data. Procedia Environ. 2012;13:140–50. https://doi.org/10.1016/j.proenv.2012.01.014.

    Article  Google Scholar 

  22. Rao GN, Jagadeeswara Rao P, Duvvuru R, Bendalam S, Gemechu R. An enhanced real-time forest fire assessment algorithm based on video by using texture analysis. Perspect Sci. 2016;8:618–20. https://doi.org/10.1016/j.pisc.2016.06.037.

    Article  Google Scholar 

  23. Xie S, Dong S, Chen Y, Peng Y, Li X. A novel risk evaluation method for fire and explosion accidents in oil depots using bow-tie analysis and risk matrix analysis method based on cloud model theory. Reliab Eng Syst Saf. 2021;215:107791. https://doi.org/10.1016/j.ress.2021.107791.

    Article  Google Scholar 

  24. Qu N, Li Z, Li X, Zhang S, Zheng T. Multi-parameter fire detection method based on feature depth extraction and stacking ensemble learning model. Fire Saf J. 2022;128:103541. https://doi.org/10.1016/j.firesaf.2022.103541.

    Article  Google Scholar 

  25. Wu H, Zhang A, Han Y, Nan J, Li K. Fast stochastic configuration network based on an improved sparrow search algorithm for fire flame recognition. Knowl Based Syst. 2022;245:108626. https://doi.org/10.1016/j.knosys.2022.108626.

    Article  Google Scholar 

  26. Cho S, Cha BH, Gawecki M, Jay Kuo CC. Block-based image steganalysis: algorithm and performance evaluation. J Vis Commun Image Rep. 2013;24:846–56. https://doi.org/10.1016/j.jvcir.2013.05.007.

    Article  Google Scholar 

  27. Wooster MJ, Xu W, Nightingale T. Sentinel-3 SLSTR active fire detection and FRP product: pre-launch algorithm development and performance evaluation using MODIS and ASTER datasets. Remote Sens Environ. 2012;120:236–54. https://doi.org/10.1016/j.rse.2011.09.033.

    Article  Google Scholar 

  28. Che L, Zhang Y, Wang J, Bai M. A new method for deriving weights in group fuzzy analytic hierarchy process and evaluation measures. IFAC. 2020;53:7941–6. https://doi.org/10.1016/j.ifacol.2020.12.2183.

    Article  Google Scholar 

  29. Han B, Ming Z, Zhao Y, Wen T, Xie M. Comprehensive risk assessment of transmission lines affected by multi-meteorological disasters based on fuzzy analytic hierarchy process. Int J Electr Power Energy Syst. 2021;133:107190. https://doi.org/10.1016/j.ijepes.2021.107190.

    Article  Google Scholar 

Download references

Acknowledgments

This project was supported by National Natural Science Foundation of China (Grant no. 51904229), the Natural Science Basic Research Program of Shaanxi (Grant no. 2020JQ-753). We wish to express our sincere thanks to these organizations.

Author information

Authors and Affiliations

  1. College of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an, 710054, China

    Yi Yang, Xue-Feng Wang & Meng-Yi Pan

  2. Zhengzhou Airport Economy Zone Fire Brigade, Zhengzhou, 450000, China

    Pu Li

  3. College of Safety Science and Engineering, Nanjing Tech University, Nanjing, 211816, China

    Yun-Ting Tsai

Authors
  1. Yi Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xue-Feng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meng-Yi Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yun-Ting Tsai
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All the authors contributed to the specific ideas and assumptions of the study. YY, X-FW, M-YP, PL and Y-TT completed the data induction and analysis. The first draft was written by X-FW: all the authors participated in the discussion of the previous version. All authors viewed and identified the final manuscript.

Corresponding author

Correspondence to Yun-Ting Tsai.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, Y., Wang, XF., Pan, MY. et al. Evaluation on algorithm reliability and efficiency for an image flame detection technology. J Therm Anal Calorim 148, 5063–5070 (2023). https://doi.org/10.1007/s10973-023-12012-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10973-023-12012-8

Keywords

Search

Navigation