Smoke Detection on Video Sequences Using Convolutional and Recurrent Neural Networks

  • Alexander Filonenko
  • Laksono Kurnianggoro
  • Kang-Hyun Jo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10449)


The combination of a convolutional neural network (CNN) and recurrent neural network (RNN) is proposed to detect the smoke in space and time domains. CNN part automatically builds the low-level features, and RNN part finds the relation between the features in different frames of the same event. For this work, the new dataset was constructed with at least 64 sequential frames for each set giving the network ability to analyze the behavior of the smoke for at least 2 s. While being not too deep thus allowing fast processing, the proposed network outperformed state of the art deep CNNs which do not consider the change of the object in time.


Smoke detection Convolutional neural network Recurrent neural network 



This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korean Government (2016R1D1A1A02937579).


  1. 1.
    Lee, C.-Y., Lin, C.-T., Hong, C.-T., Su, M.-T.: Smoke detection using spatial and temporal analyses. Int. J. Innov. Comput. 8(6), 1–23 (2012)Google Scholar
  2. 2.
    Torabnezhad, M., Aghagolzadeh, A., Seyedarabi, H.: Visible and IR image fusion algorithm for short range smoke detection. In: Proceedings of ICRoM, Tehran (2013)Google Scholar
  3. 3.
    Chen, J., Wang, Y., Tian, Y., Huang, T.: Wavelet based smoke detection method with RGB contrast-image and shape constrain. In: Proceedings of VCIP, Kuching (2013)Google Scholar
  4. 4.
    Maruta, H., Iida, Y., Kurokawa, F.: Anisotropic LBP descriptors for robust smoke detection. In: Proceedings of IECON, Vienna (2013)Google Scholar
  5. 5.
    Rashmi, G.P., Nirmala, L.: FPGA based FNN for accidental fire alarming system in a smart room. Int. J. Adv. Res. Comput. Commun. Eng. 3(6), 6902–6906 (2014)Google Scholar
  6. 6.
    Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors, Computing Research Repository (2012).
  7. 7.
    Xu, G., Zhang, Y., Zhang, Q., Lin, G., Wang, J.: Deep domain adaptation based video smoke detection using synthetic smoke images, fire safety journal, under review.
  8. 8.
    Frizzi, S., Kaabi, R., Bouchouicha, M., Ginoux, J.M., Moreau, E., Fnaiech, F.: Convolutional neural network for video fire and smoke detection. In: 42nd Annual Conference of the IEEE Industrial Electronics Society, IECON 2016, Florence, pp. 877–882 (2016). doi: 10.1109/IECON.2016.7793196
  9. 9.
    Tao, C., Zhang, J., Wang, P.: Smoke detection based on deep convolutional neural networks. In: 2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), pp. 150–153, (2016). doi: 10.1109/ICIICII.2016.0045
  10. 10.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions, computing research repository (2014).
  11. 11.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI 2017, pp. 4278–4284. AAAI Press (2017)Google Scholar
  12. 12.
    Chollet, F.: Xception: deep learning with depthwise separable convolutions, computing research repository (2017).
  13. 13.
    Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches, computing research repository (2014).
  14. 14.
    Chollet, F.: Keras (2015).

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Alexander Filonenko
    • 1
  • Laksono Kurnianggoro
    • 1
  • Kang-Hyun Jo
    • 1
  1. 1.Graduate School of Electrical EngineeringUniversity of UlsanUlsanRepublic of Korea

Personalised recommendations