Benchmarking of wildland fire colour segmentation algorithms

Tom Toulouse; Lucile Rossi; Moulay Akhloufi; Turgay Celik; Xavier Maldague

Benchmarking of wildland fire colour segmentation algorithms

View Fulltext

Author(s): Tom Toulouse ^{1, 2} ; Lucile Rossi ² ; Moulay Akhloufi ³ ; Turgay Celik ⁴ ; Xavier Maldague ¹
- Affiliations: 1: Department of Electrical and Computer Engineering, Laval University, Quebec, QC, G1V0A6Canada ;
  2: UMR CNRS 6134 SPE, University of Corsica, 20250 Corte, France ;
  3: Department of Electronics Engineering, Universidad Tecnica Federico Santa Maria, Valparaso, Chile ;
  4: School of Computer Science, University of the Witwatersrand, Johannesburg, South Africa
Source: Volume 9, Issue 12, December 2015, p. 1064 – 1072
DOI: 10.1049/iet-ipr.2014.0935 , Print ISSN 1751-9659, Online ISSN 1751-9667

Received 01/07/2014, Accepted 09/06/2015, Revised 29/05/2015, Published 01/12/2015

Recently, computer vision-based methods have started to replace conventional sensor-based fire detection technologies. In general, visible band image sequences are used to automatically detect suspicious fire events in indoor or outdoor environments. There are several methods which aim to achieve automatic fire detection on visible band images, however, it is difficult to identify which method is the best performing as there is no fire image dataset which can be used to test the different methods. This study presents a benchmarking of state of the art wildland fire colour segmentation algorithms using a new fire dataset introduced for the first time. The dataset contains images of wildland fire in different contexts (fuel, background, luminosity, smoke etc.). All images of the dataset are characterised according to the principal colour of the fire, the luminosity, and the presence of smoke in the fire area. With this characterisation, it has been possible to determine on which kind of images each algorithm is efficient. Also a new probabilistic fire segmentation algorithm is introduced and compared to the other techniques. Benchmarking is performed in order to assess performances of 12 algorithms that can be used for the segmentation of wildland fire images.

References

1. 1)
  - 9. Celik, T., Demirel, H., Ozkaramanli, H., Uyguroglu, M.: ‘Fire detection using statistical color model in video sequences’, J. Vis. Commun. Image Represent., 2007, 18, (2), pp. 176–185, (doi: 10.1016/j.jvcir.2006.12.003).
2. 2)
  - 30. ‘The Bilkent VisiFire web-page and dataset’, http://www.signal.ee.bilkent.edu.tr/VisiFire, accessed April 2015.
3. 3)
  - 14. Marbach, G., Loepfe, M., Brupbacher, T.: ‘An image processing technique for fire detection in video images’, Fire Safety J., 2006, 41, (4), pp. 285–289 (doi: 10.1016/j.firesaf.2006.02.001).
4. 4)
  - 1. ‘European Forest Fire Information System’, http://www.forest.jrc.ec.europa.eu/effis/ accessed April 2015.
5. 5)
  - 17. Liu, C.B., Ahuja, N.: ‘Vision based fire detection’. Proc. of the 17th Int. Conf. on Pattern Recognition (ICPR), 2004, vol. 4, pp. 134–137.
6. 6)
  - 28. Van Rijsbergen, C.J.: ‘Information retrieval’ (Butterworth-Heinemann, London, 1979, 2nd edn.).
7. 7)
  - 4. Santoni, P.A., Simeoni, A., Rossi, J.L., et al: ‘Instrumentation of wildland fire: characterisation of a fire spreading through a Mediterranean shrub’, Fire Safety J., 2006, 41, (3), pp. 171–184 (doi: 10.1016/j.firesaf.2005.11.010).
8. 8)
  - 23. Martin, D., Fowlkes, C., Tal, D., Malik, J.: ‘A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics’. Proc. Eighth IEEE Int. Conf. on Computer Vision (ICCV), 2001, vol. 2, pp. 416–423.
9. 9)
  - 31. Péteri, R., Fazekas, S., Huiskes, M.J.: ‘DynTex: a comprehensive database of dynamic textures’, Pattern Recognit. Lett., 2010, 31, (12), pp. 1627–1632 (doi: 10.1016/j.patrec.2010.05.009).
10. 10)
  - 22. Santana, P., Gomes, P., Barata, J.: ‘A vision-based system for early fire detection’. Proc. IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC), October 2012, pp. 739–744.
11. 11)
  - 29. Hafiane, A., Chabrier, S., Rosenberger, C., Laurent, H.: ‘A new supervised evaluation criterion for region based segmentation methods’. Proc. Advanced Concepts for Intelligent Vision Systems, Delft, Netherlands, August 2007, pp. 439–448.
12. 12)
  - 24. Habiboğlu, Y.H., Günay, O., Çetin, A.E.: ‘Covariance matrix-based fire and flame detection method in video’, Mach. Vis. Appl., 2011, 23, (6), pp. 1103–1113 (doi: 10.1007/s00138-011-0369-1).
13. 13)
  - 3. Balbi, J.H., Rossi, J.L., Marcelli, T., Chatelon, F.J.: ‘Physical modeling of surface fire under nonparallel wind and slope conditions’, Combus. Sci. Technol., 2010, 182, (7), pp. 922–939 (doi: 10.1080/00102200903485178).
14. 14)
  - 11. Collumeau, J.F., Laurent, H., Hafiane, A., Chetehouna, K.: ‘Fire scene segmentations for forest fire characterization: a comparative study’. Proc. 18th IEEE Int. Conf. on Image Processing (ICIP), September 2011, pp. 2973–2976.
15. 15)
  - 6. Çetin, A.E., Dimitropoulos, K., Gouverneur, B., et al: ‘Video fire detection – review’, Digital Signal Process., 2013, 23, (6), pp. 1827–1843 (doi: 10.1016/j.dsp.2013.07.003).
16. 16)
  - 7. Phillips, W.III, , Shah, M., da Vitoria Lobo, N.: ‘Flame recognition in video’, Pattern Recognit. Lett., 2002, 23, (1), pp. 319–327 (doi: 10.1016/S0167-8655(01)00135-0).
17. 17)
  - 26. Jiang, X.: ‘Performance evaluation of image segmentation algorithms’, Handb. Pattern Recognit. Comput. Vis., 2005, 3, pp. 525–542 (doi: 10.1142/9789812775320_0028).
18. 18)
  - 2. Grishin, A.M., Albini, F.A.: ‘Mathematical modeling of forest fires and new methods of fighting them’ (Publishing House of the Tomsk State University, 1997).
19. 19)
  - 18. Chen, T.H., Wu, P.H., Chiou, Y.C.: ‘An early fire-detection method based on image processing’. Proc. Int. Conf. on Image Processing (ICIP), 2004, vol. 3, pp. 1707–1710.
20. 20)
  - 19. Rossi, L., Akhloufi, M., Tison, Y.: ‘Dynamic fire 3D modeling using a realtime stereovision system’, J. Commun. Comput., 2010, 6, (10), p. 54.
21. 21)
  - 27. Matthews, B.W.: ‘Comparison of the predicted and observed secondary structure of T4 phage lysozyme’, Biochim. Biophys. Acta (BBA)-Protein Struct., 1975, 405, (2), pp. 442–451 (doi: 10.1016/0005-2795(75)90109-9).
22. 22)
  - 33. ‘Work with Color’, http://www.workwithcolor.com/color-names-01.htm, accessed April 2015.
23. 23)
  - 32. Zhao, J., Zhang, Z., Han, S., Qu, C., Yuan, Z., Zhang, D.: ‘SVM based forest fire detection using static and dynamic features’, Comput. Sci. Inf. Syst., 2011, 8, (3), pp. 821–841 (doi: 10.2298/CSIS101012030Z).
24. 24)
  - 21. Rudz, S., Chetehouna, K., Hafiane, A., Sero-Guillaume, O., Laurent, H.: ‘On the evaluation of segmentation methods for wildland fire’. Proc. Advanced Concepts for Intelligent Vision Systems, Bordeaux, France, September 2009, pp. 12–23.
25. 25)
  - 13. Rudz, S., Chetehouna, K., Hafiane, A., Laurent, H., Sero-Guillaume, O.: ‘Investigation of a novel image segmentation method dedicated to forest fire applications’, Meas. Sci. Technol., 2013, 24, (7), p. 075403 (doi: 10.1088/0957-0233/24/7/075403).
26. 26)
  - 25. Hooke, R., Jeeves, T.A.: ‘‘direct search’ solution of numerical and statistical problems’, J. ACM, 1961, 8, (2), pp. 212–229 (doi: 10.1145/321062.321069).
27. 27)
  - 10. Ko, B.C., Cheong, K.H., Nam, J.Y.: ‘Fire detection based on vision sensor and support vector machines’, Fire Safety J., 2009, 44, (3), pp. 322–329 (doi: 10.1016/j.firesaf.2008.07.006).
28. 28)
  - 5. Toreyin, B.U., Dedeoglu, Y., Cetin, A.E.: ‘Computer vision based method for real-time fire and flame detection’, Pattern Recognit. Lett., 2006, 27, (1), pp. 49–58 (doi: 10.1016/j.patrec.2005.06.015).
29. 29)
  - 20. Chitade, A.Z., Katiyar, S.K.: ‘Colour based image segmentation using k-means clustering’, Int. J. Eng. Sci. Technol., 2010, 2, (10), pp. 5319–5325.
30. 30)
  - 15. Celik, T.: ‘Fast and efficient method for fire detection using image processing’, ETRI J., 2010, 32, (6), pp. 881–890 (doi: 10.4218/etrij.10.0109.0695).
31. 31)
  - 12. Celik, T., Demirel, H.: ‘Fire detection in video sequences using a generic color model’, Fire Safety J., 2009, 44, (2), pp. 147–158 (doi: 10.1016/j.firesaf.2008.05.005).
32. 32)
  - 16. Horng, W.B., Peng, J.W., Chen, C.Y.: ‘A new image-based realtime flame detection method using color analysis’. Proc. IEEE Networking, Sensing and Control, 2005, pp. 100–105.
33. 33)
  - 5. Rothermel, R.C., Anderson, H.E.: ‘Fire spread characteristics determined in the laboratory’ (Intermountain Forest and Range Experiment Station, Forest Service, US Department of Agriculture, 1966).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Benchmarking of wildland fire colour segmentation algorithms

References

Related content