Semantic Fire Segmentation Model Based on Convolutional Neural Network for Outdoor Image


In this paper, we proposed a semantic fire image segmentation method using a convolutional neural network. The simple but powerful method proposed is middle skip connection achieved through the residual network, which is widely used in image-based deep learning. To enhance the middle skip connection, we constructed a pair of convolution layers, hereafter referred to as input convolution and output convolution, to be inserted in front and behind of the entire architecture. Consequently, the middle skip connection yields a stronger feedback effect compared to when only the short skip connection of the residual block and the long skip connection are used. The validity of the proposed method has been confirmed by using the FiSmo dataset and the Corsican Fire Database based on various evaluation metrics. Comparative analysis shows that the proposed model outperforms previous fire segmentation deep learning models and image processing algorithms.

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

Figure 1
Figure 2
Figure 3
Figure 4


  1. 1.

    Celik T, Demirel H (2009) Fire detection in video sequences using a generic color model. Fire Safety J 44(2):147–158

    Article  Google Scholar 

  2. 2.

    Do YT (2012) Visual sensing of fires using color and dynamic features. J Sensor Sci Technol 21(3):211–216

    Article  Google Scholar 

  3. 3.

    Ronneberger O, Fischer P, Brox T (2015). U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention (pp. 234–241). Springer, Cham

  4. 4.

    Quan T M, Hildebrand DG, Jeong WK (2016) Fusionnet: A deep fully residual convolutional neural network for image segmentation in connectomics. arXiv:1612.05360

  5. 5.

    Drozdzal M, Chartrand G, Vorontsov E, Shakeri M, Di Jorio L, Tang A, Kadoury S (2018) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13

    Article  Google Scholar 

  6. 6.

    Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (pp 91–99)

  7. 7.

    Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC. (2016, October). SSD: Single shot multibox detector. In: European conference on computer vision (pp 21–37). Springer, Cham

  8. 8.

    He K, Gkioxari G, Dollár P, Girshick R (2017). Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision (pp 2961–2969)

  9. 9.

    Dunnings AJ, Breckon TP (2018, October). Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection. In: 2018 25th IEEE International Conference on Image Processing (ICIP) (pp 1558–1562) IEEE.

  10. 10.

    Yuan F, Zhang L, Xia X, Wan B, Huang Q, Li X (2019) Deep smoke segmentation. Neurocomputing 357:248–260

    Article  Google Scholar 

  11. 11.

    Lin G, Zhang Y, Xu G, Zhang Q (2019) Smoke detection on video sequences using 3D convolutional neural networks. Fire Technol 55(5):1827–1847

    Article  Google Scholar 

  12. 12.

    Chhor G, Aramburu CB, Bougdal-Lambert I (2017) Satellite image segmentation for building detection using U-Net. Web:

  13. 13.

    Tikoo S, Malik N. (2017). Detection, segmentation and recognition of face and its features using neural network. arXiv:1701.08259

  14. 14.

    Kumar P, Saini R, Roy PP, Dogra DP (2016) Study of text segmentation and recognition using leap motion sensor. IEEE Sensors J 17(5):1293–1301

    Article  Google Scholar 

  15. 15.

    Akhloufi MA, Tokime RB, Elassady H (2018, April). Wildland fires detection and segmentation using deep learning. In: Pattern Recognition and Tracking XXIX (Vol. 10649, p. 106490B). International Society for Optics and Photonics

  16. 16.

    Mlích J, Koplík K, Hradiš M, Zemčík P, (2020) Fire Segmentation in Still Images. In: Blanc-Talon J, Delmas P, Philips W, Popescu D, Scheunders P (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2020. Lecture notes in computer science, vol 12002. Springer, Cham

  17. 17.

    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 Safety J 92:188–194

    Article  Google Scholar 

  18. 18.

    Cazzolato MT, Avalhais LP, Chino DY, Ramos JS, de Souza JA, Rodrigues-Jr JF, Traina AJ. (2017). Fismo: A compilation of datasets from emergency situations for fire and smoke analysis. In SBC (pp 213–223)

  19. 19.

    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 25(9):1545–1556

    Article  Google Scholar 

  20. 20.

    Labati RD, Genovese A, Piuri V, Scotti F (2013) Wildfire smoke detection using computational intelligence techniques enhanced with synthetic smoke plume generation. IEEE Trans Syst Man Cybern Syst 43(4):1003–1012

    Article  Google Scholar 

  21. 21.

    Tuba V, Capor-Hrosik R, Tuba E (2017) Forest Fires Detection in Digital Images Based on Color Features. Int J Ed Learn Syst, 2

  22. 22.

    Dzigal D, Akagic A, Buza E, Brdjanin A, Dardagan N. (2019, November). Forest Fire Detection based on Color Spaces Combination. In: 2019 11th International Conference on Electrical and Electronics Engineering (ELECO) (pp. 595-599). IEEE

  23. 23.

    Töreyin BU, Dedeoğlu Y, ğithan U, & Cetin AE. (2006) Computer vision based method for real-time fire and flame detection. Pattern Recognit Lett 27(1):49–58

    Article  Google Scholar 

  24. 24.

    Yamagishi H, Yamaguchi JUNICHI (1999, November). Fire flame detection algorithm using a color camera. In: MHS’99. Proceedings of 1999 International Symposium on Micromechatronics and Human Science (Cat. No. 99TH8478) (pp. 255-260). IEEE

  25. 25.

    Kim DK (2009) Flame detection using region expansions and on-line variances in infrared image. J Korea Multimedia Soc 12(11):1547–1556

    Google Scholar 

  26. 26.

    Long J, Shelhamer E, Darrell T. (2015). Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431-3440)

  27. 27.

    Noh H, Hong S, Han B (2015). Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE international conference on computer vision (pp 1520–1528)

  28. 28.

    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp 770–778)

  29. 29.

    Drozdzal M, Vorontsov E, Chartrand G, Kadoury S, Pal C (2016). The importance of skip connections in biomedical image segmentation. In: Deep Learning and Data Labeling for Medical Applications (pp 179–187). Springer, Cham

  30. 30.

    Xiong Y, Liao R, Zhao H, Hu R, Bai M, Yumer E, Urtasun R (2019). Upsnet: A unified panoptic segmentation network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 8818-8826)

  31. 31.

    Chen LC, Papandreou G, Schroff F, Adam H (2017). Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587

  32. 32.

    Veit A, Wilber MJ, Belongie S (2016) Residual networks behave like ensembles of relatively shallow networks. In: Advances in neural information processing systems (pp 550–558)

  33. 33.

    He K, Zhang X, Ren S, Sun J (2016, October) Identity mappings in deep residual networks. In: European conference on computer vision (pp 630–645). Springer, Cham

Download references


Myungjoo Kang was supported by the National Research Foundation of Korea (2015R1A5A1009350) and the ICT R&D program of MSIT/IITP (No. 1711117093).

Author information



Corresponding author

Correspondence to Myungjoo Kang.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Choi, HS., Jeon, M., Song, K. et al. Semantic Fire Segmentation Model Based on Convolutional Neural Network for Outdoor Image. Fire Technol (2021).

Download citation


  • Deep learning
  • Convolutional neural network
  • Semantic image segmentation
  • Fully convolutional network
  • Fire segmentation