Karanlık Videolarda Orman Yangını Tespitine Yönelik Uzaysal- Zamansal Nesne Öznitelikleri

Abstract

Bu makalede, karanlık videolardan orman yangınının tespitine yönelik bir yöntem önerilmiştir. Gündüz orman yangınlarından farklı olarak, karanlık videolarda yangının kendisi de çevresi de görsel olarak açıkça algılanabilir bir desene sahip değildir. Karanlık videolardaki yangının bunun gibi kendine özgü görsel özellikleri, tanımlayıcı nesne öznitelikleri çıkarmayı zorlaştırmaktadır. Bu makale, karanlıkta parlayan nesneleri takip edip, uzaysal-zamansal davranışlarına dayalı öznitelikleri çıkararak bu zorlayıcı duruma çözüm üretmektedir. Önerilen özniteliklerin, videoda şehir ışıkları, el fenerleri, araba farları ve olay yerindeki yansımalar gibi aldatıcı ışık kaynakları olsa bile, orman yangınlarını %90'ın üzerinde doğrulukla sınıflandırmak için yeterince temsil edici olduğu deneysel olarak gösterilmiştir. Ayrıca, aynı uzaysal-zamansal öznitelik kümesinde topluluk ve çekirdek tabanlı sınıflandırma yöntemleri gibi çeşitli geleneksel makine öğrenmesi algoritmaları da karşılaştırma amacıyla denenmiştir. Kapsamlı deneysel test sonuçları, en yüksek tespit doğruluğunun, önerilen uzaysal-zamansal öznitelik kümesinin Rastgele Orman sınıflandırma yöntemi elde edildiğini göstermektedir.

Keywords

• Video tabanlı yangın tespiti
• SVM
• Çoğunluk Oylaması
• Rastgele Orman
• Adaboost
• IBk

Spatio-temporal Object Features for Wildfire Detection in Dark Videos

Abstract

In this paper, a wildfire detection algorithm from dark videos is proposed. Unlike the daytime wildfires, in the dark videos, neither the fire nor its surrounding has visually clearly perceptible texture. Its unique visual characteristics make it challenging to extract descriptive object features. This paper addresses the challenging problem by tracking the glowing objects in the darkness and extracting features based on the spatio-temporal behavior of them. It is experimentally shown that the proposed features are descriptive enough to classify wildfires with over 90% accuracy even there exists deceptive light sources such as city lights, flashlights, car headlights and reflections in the scene. Moreover, we investigate several conventional machine learning algorithms such as ensemble and kernel-based methods on the same spatio-temporal feature set. Comprehensive empirical test results demonstrate that the most accurate detection is obtained when the spatio-temporal feature set is classified using Random Forest.

Keywords

• Video based fire detection
• SVM
• majority voting
• Random Forest
• AdaBoostM1
• IBk

References

1. [1] DGF, “2015 Forestry Statistics”, Turkish Directorate General of Forestry, Ankara, 2015.
2. [2] DGF, (2017, Jan 29), State of Forest Fires [Online]. Available: https://www.ogm.gov.tr/Lists/GuncelOrmanYanginlari/.
3. [3] Istanbul Fire Department, “2011-2016 Statistics,” Istanbul Municipality, Istanbul, 2011.
4. [4] B. U. Toreyin, Y. Dedeoglu, and A. E. Cetin, “Flame detection in video using hidden Markov models”, IEEE Int. Conf. Image Process., vol. 2, no. October-2005, p. II-1230-3, 2005.
5. [5] Y.Dedeoglu, B.U.Toreyin, U.Gudukbay, and A.E.Cetin, “Real-timefire and flame detection in video”, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. II, pp. 669672, 2005.
6. [6] B.U.Toreyin, Y.Dedeoglu, and A.E. Cetin, “Contour based smoke detection in video using wavelets”, Eur. Signal Process. Conf., no. EUSIPCO, pp. 610, 2006.
7. [7] Y. Dedeoglu, B.U. Toreyin, U. Gudukbay, and A.E. Cetin, “Real-timefire and flame detection in video”, ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. II, pp. 669672, 2005.
8. [8] B. U. Toreyin and A. E. Cetin, “Online Detection of Fire in Video”, 2007 IEEE Conf. Comput. Vis. Pattern Recognit., pp. 15, 2007.

9. [9] B.U. Toreyin and A.E. Cetin, “Computer vision based forest fire detection”, 2008 IEEE 16th Signal Process. Commun. Appl. Conf., p. 6800, 2008.
10. [10] K. Dimitropoulos, K. Köse, N. Grammalidis, and A. E. Çetin, ‘Fire detection and 3D fire propagation estimation for the protection of cultural heritage areas’, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 38, no. 8, pp. 620–625, 2010.
11. [11] O. Gunay, A. E. Cetin, and B. U. Töreyin, “Online adaptive decision fusion framework based on projections onto convex sets with application to wildfire detection in video,” Optical Engineering, vol. 50, no. 7, p. 077202, 2011.
12. [12] Y. H. Habiboglu, O. Gunay, and A. E. Cetin, “Real-time wildfire detection using correlation descriptors,” in 2011 19th European Signal Processing Conference, 2011, pp. 894–898.
13. [13] O. Gunay, B. U. Toreyin, K. Kose, and A. E. Cetin, “Entropy-functional-based online adaptive decision fusion framework with application to wildfire detection in video,” IEEE Transactions on Image Processing, vol. 21, no. 5, pp. 2853–2865, 2012.
14. [14] Y. H. Habiboğlu, O. Günay, and A. E. Çetin, “Covariance matrix-based fire and flame detection method in video,” Machine Vision and Applications, vol. 23, no. 6, pp. 1103–1113, 2012.
15. [15] F. Erden et al., “Wavelet based flickering flame detector using differential PIR sensors,” Fire Safety Journal, vol. 53, pp. 13–18, 2012.
16. [16] S. G. Kong, D. Jin, S. Li, and H. Kim, “Fast fire flame detection in surveillance video using logistic regression and temporal smoothing,” Fire Safety Journal, vol. 79, pp. 37–43, 2016.
17. [17] S. Verstockt et al., “A multi-modal video analysis approach for car park fire detection,” Fire safety journal, vol. 57, pp. 44–57, 2013.
18. [18] K. Dimitropoulos et al., “Flame detection for video-based early fire warning for the protection of cultural heritage,” Euro-Mediterranean Conference, 2012, pp. 378–387.
19. [19] T. Toulouse, L. Rossi, T. Celik, and M. Akhloufi, “Automatic fire pixel detection using image processing: a comparative analysis of rule-based and machine learning-based methods,” Signal, Image and Video Processing, vol. 10, no. 4, pp. 647–654, 2016.
20. [20] K. Dimitropoulos, P. Barmpoutis, and N. Grammalidis, “Spatio-temporal flame modeling and dynamic texture analysis for automatic video-based fire detection,” IEEE transactions on circuits and systems for video technology, vol. 25, no. 2, pp. 339–351, 2014.
21. [21] A. E. Çetin et al., “Video fire detection–review,” Digital Signal Processing, vol. 23, no. 6, pp. 1827–1843, 2013.
22. [22] K. Tasdemir, O. Gunay, B. U. Toreyin, and A. E. Cetin, “Video based fire detection at night,” in 2009 IEEE 17th Signal Processing and Communications Applications Conference, 2009, pp. 720–723.
23. [23] A. K. Agirman and K. Taşdemir, “Short to mid-range night fire detection,” in 2017 25th Signal Processing and Communications Applications Conference (SIU), 2017, pp. 1–4.
24. [24] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE transactions on systems, man, and cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
25. [25] C.-C. Chang and C.-J. Lin, “LIBSVM: a library for support vector machines,” ACM transactions on intelligent systems and technology (TIST), vol. 2, no. 3, pp. 1–27, 2011.
26. [26] Y. Wan, Y. Chen, and K. Li, “Identification and spatiotemporal distribution analysis of global biomass burning based on Suomi-NPP VIIRS Nightfire data,” Journal of Cleaner Production, vol. 359, p. 131959, 2022.
27. [27] A. Bouguettaya, H. Zarzour, A. M. Taberkit, and A. Kechida, “A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms,” Signal Processing, vol. 190, p. 108309, 2022.