Real-time smoke removal for the surveillance images under fire scenario

  • Sen Li
  • Shuyan Wang
  • Dan ZhangEmail author
  • Chunyong Feng
  • Long Shi
Original Paper


When a fire happens in a building, internal closed-circuit television system becomes less effective under the influences of hot smoke. The fire scenario is very similar to the environments with bad weather conditions such as haze, rain, and snow. Comparing those bad weather conditions, the fire scenarios are much complicated with difficulties in processing the images. This can be reflected by two important aspects: The lighting condition changes frequently inside the building, and the smoke is always in black while the particles under bad weather conditions are generally white. So a fast image restoration method (GL-MSR method) based on the multi-scale Retinex (MSR) was developed in this study to improve the detection accuracy under complicated fire or the similar situations. For the proposed GL-MSR method, the Gaussian pyramid was used to replace the Gaussian convolution where a lookup table was built to reduce the calculation time of the logarithmic algorithm. Compared with the traditional methods such as histogram equalization, the GL-MSR method shows a better result than the others and its operation time was found only 198 ms, almost 1/26 of the traditional processing time.


CCTV Smoke Smoky image Multi-scale Retinex 



The authors thank Xiaoge Liang for preparing the experimental installation. This work was supported by the National Science Foundation for Young Scientists of China (51504219), Science and Technology Research Project of Henan Province (152102210349), and Ph.D. Research Fund of Zhengzhou University of Light Industry (2014BSJJ020). The authors appreciate the supports.


  1. 1.
    Hasikin, K., Mat Isa, N.A.: Adaptive fuzzy intensity measure enhancement technique for non-uniform illumination and low contrast images. Signal Image Video Process. 9(6), 1419–1442 (2015)CrossRefGoogle Scholar
  2. 2.
    Wang, X., Chen, L.: Contrast enhancement using feature-preserving bi-histogram equalization. Signal Image Video Process. 12(4), 685–692 (2018)CrossRefGoogle Scholar
  3. 3.
    Jin, W., Gong, F., Zeng, X., Fu, R.: Illumination robust face recognition using random projection and sparse representation. Signal Image Video Process. 12(4), 721–729 (2018)CrossRefGoogle Scholar
  4. 4.
    Jha, R.K., Biswas, P.K., Chatterji, B.N.: Contrast enhancement of dark images using stochastic resonance. IET Image Process. 6(3), 230–237 (2012)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Land, E.H.: The Retinex theory of color vision. Sci. Am. 237(6), 108–128 (1997)CrossRefGoogle Scholar
  6. 6.
    He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. 33(12), 2341–2353 (2011)CrossRefGoogle Scholar
  7. 7.
    Kiss, Á., Szirányi, T.: Reconstructing static scene viewed through smoke using video. In: 18th IEEE International Conference on Image Processing, Brussels, Belgium, pp. 3461-3464 (2011)Google Scholar
  8. 8.
    Lv, X., Chen, W., Shen, I.: Real-time dehazing for image and video. In: 18th Pacific Conference on Computer Graphics and Applications, Hangzhou, China, pp. 62–69 (2010)Google Scholar
  9. 9.
    Wang, W., Li, B., Zheng, J., et al.: A fast multi-scale Retinex algorithm for color image enhancement. In: International Conference on Wavelet Analysis and Pattern Recognition, Hong Kong, China, pp. 80–85 (2008)Google Scholar
  10. 10.
    Jang, C., Lim, J.H., Kim, Y.H.: A fast multi-scale Retinex algorithm using dominant SSR in weights selection. In: International SoC Design Conference, Jeju Island, Korea, pp. 37–40 (2012)Google Scholar
  11. 11.
    Wang, L., Horiuchi, T., Kotera, H.: High dynamic range image compression by fast integrated surround Retinex model. J. Imaging Sci. Technol. 51(1), 34–43 (2007)CrossRefGoogle Scholar
  12. 12.
    Keller, A., Loepfe, M., Nebiker, P., et al.: On-line determination of the optical properties of particles produced by test fires. Fire Saf. J. 41(4), 266–273 (2006)CrossRefGoogle Scholar
  13. 13.
    Jobson, D.J., Rahman, Z., Woodell, G.A.: Properties and performance of a center/surround retinex. IEEE Trans. Image Process. 6(3), 451–462 (1997)CrossRefGoogle Scholar
  14. 14.
    Jobson, D.J., Rahman, Z., Woodell, G.A.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997)CrossRefGoogle Scholar
  15. 15.
    Rahman, Z., Jobson, D.J., Woodell, G.A.: Multiscale Retinex for color rendition and dynamic range compression. In: Applications of Digital Image Processing XIX, SPIE 2847, pp. 183–191 (1996)Google Scholar
  16. 16.
    Suplata, M., Ravas, R.: Gaussian pyramid based acceleration of optical flow reconstruction. In: 19th International Conference Radioelektronika, Bratislava, Slovakia Republic, pp. 169–171 (2009)Google Scholar
  17. 17.
    Nayar, S.K., Narasimhan, S.G.: Vision in bad weather. In: The Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, pp. 820–827 (1999)Google Scholar
  18. 18.
    Parthasarathy, S., Sankaran, P.: A RETINEX based haze removal method. In: International Conference on Industrial and Information Systems, Chennai, India, pp. 1–6 (2012)Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Sen Li
    • 1
  • Shuyan Wang
    • 2
  • Dan Zhang
    • 1
    Email author
  • Chunyong Feng
    • 1
  • Long Shi
    • 3
  1. 1.School of Building Environment EngineeringZhengzhou University of Light IndustryZhengzhouPeople’s Republic of China
  2. 2.School of Information and Mechatronics EngineeringZhengzhou Chenggong University of Finance and EconomicsGongyiPeople’s Republic of China
  3. 3.Civil and Infrastructure Engineering Discipline, School of EngineeringRMIT UniversityMelbourneAustralia

Personalised recommendations