J. For. Sci., 2019, 65(4):150-159 | DOI: 10.17221/82/2018-JFS

Early smoke detection of forest fires based on SVM image segmentationOriginal Paper

Ding Xiong*, Lu Yan
School of Electrical and Information Engineering, Hunan International Economics University, Changsha, China

A smoke detection method is proposed in single-frame video sequence images for forest fire detection in large space and complex scenes. A new superpixel merging algorithm is further studied to improve the existing horizon detection algorithm. This method performs Simple Linear Iterative Clustering (SLIC) superpixel segmentation on the image, and the over-segmentation problem is solved with a new superpixel merging algorithm. The improved sky horizon line segmentation algorithm is used to eliminate the interference of clouds in the sky for smoke detection. According to the spectral features, the superpixel blocks are classified by support vector machine (SVM). The experimental results show that the superpixel merging algorithm is efficient and simple, and easy to program. The smoke detection technology based on image segmentation can eliminate the interference of noise such as clouds and fog on smoke detection. The accuracy of smoke detection is 77% in a forest scene, it can be used as an auxiliary means of monitoring forest fires. A new attempt is given for forest fire warning and automatic detection.

Keywords: Support Vector Machines (SVM); single frame; horizon detection; superpixel merging; forest fire prevention

Published: April 30, 2019  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Xiong D, Yan L. Early smoke detection of forest fires based on SVM image segmentation. J. For. Sci. 2019;65(4):150-159. doi: 10.17221/82/2018-JFS.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Achanta R., Shaji A., Smith K. (2012): SLIC superpixels compared toctate-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis & Machine Intelligence, 34: 2274-2282. Go to original source... Go to PubMed...
    2. Celik T., Demirel H., Ozkaramanli H. et al. (2007): Fire detection using statistical color model in video sequences, Journal of Visual Communication and Image Representation, 18: 176-185. Go to original source...
    3. Celik T., Ozkaramanli H., Demirel H. (2007): Fire and smoke detection without sensors: Image processing based approach. 15th European Signal Processing Conference (EUSIPCO 2007), Poznan, Poland, September 3-7, 2007: 1794-1798.
    4. Chang C.C, Lin C.J. (2011): LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2: 389-396. Go to original source...
    5. Chen P., Lin C., Bernhard S. (2005): A tutorial on ν-support vector machines. Applied Stochastic Models in Business and Industry, 21: 111-136. Go to original source...
    6. Chunyao W. et al. (2014): A Review of research on superpixel segmentation algorithms. Computer Applications, 31: 6-12.
    7. Cortes C., Vapnik V. (1995): Support vector networks. Machine Learning, 20: 273-295. Go to original source...
    8. Ettinger S.M., Nechyba M.C. (2002): Towards flight autonomy: vision-based horizon detection for micro air vehicles. In: Proceedings of the Florida conference on recent advances in robotics, Miami, May 18-21, 2002: 1-8.
    9. Fujiwara N., Terada K. (2004): Extraction of a smoke region using fractal coding. In: IEEE International Symposium on Communications and Information Technology, Sapporo, Japan, October 26-29, 2004: 808-814.
    10. Genovese A., Labati R.D., Piuri V. et al. (2011): Wildfire smoke detection using computational intelligence techniques. In: IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA). Ottawa, Canada: IEEE Press, September, 19-21, 2011: 1-6. Go to original source...
    11. Guohe F. (2011): SVM classification kernel function and parameter selection comparison. Computer Engineering and Applications, 47: 123-124.
    12. Haris K., Efstratiadis S.N., Maglaveras N. et al. (1998): Hybrid image segmentation using watershed and fast region merging. IEEE Trans on Image Processing, 7: 1684-1699. Go to original source... Go to PubMed...
    13. Hui T., Halidan A. et al. (2019): Multi-type flame detection combined with Faster R-CNN. Journal of Image and Graphics, 24: 73-83.
    14. Jakovčević T., Braović M., Stipaničev D. et al. (2011): Review of wildfire smoke detection techniques based on visible spectrum video analysis. In: International Symposium on Image and Signal Processing and Analysis, Dubrovnik, Croatia: IEEE Press, September 4-6, 2011: 480-484.
    15. Liu K., Wei Y.X. et al. (2018): Design of forest fire identification algorithm based on computer vision. Forest Engineering, 34: 89-95.
    16. Mei J.J., Zhang W. (2018): Early fire detection algorithm based on vibe and machine learning.Acta Optica Sinica, 38: 52-59. Go to original source...
    17. Qun H., Yong S. et al. (2010): A horizon detection al-gorithm based on variance between classes. Acta Aeronautica Sinica, 31: 2056-2061.
    18. Wang H.T., Chen Y.L. (2019): A smoke image segmentation algorithm based on rough set and region growing. Journal of Forest Science, 65: 120-131. Go to original source...
    19. Weidong C. et al. (2001): Research on support vector machines. Computer Engineering and Applications, 37: 58-61.
    20. Wang T., Liu Y., Xie Z.P. (2011): Flutter analysis based video smoke detection. Journal of Electronics & Information Technology, 35: 1024-1029. Go to original source...
    21. Zhao W., Yu F.F. et al. (2018): Fire image recognition simulation of unmanned aerial vehicle forest fire protection system. Computer Simulation, 35: 459-464.

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content