Video Smoke Removal Based on Smoke Imaging Model and Space-Time Pixel Compensation

  • Shiori Yamaguchi
  • Keita Hirai
  • Takahiko Horiuchi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10213)


This paper presents a novel video smoke removal method based on a smoke imaging model and space-time pixel compensation. First, we develop an optical imaging model for natural scenes that contain smoke. Then, we remove the smoke in a video, frame-by-frame, based on the smoke imaging model and conventional dehazing approaches. Next, we align the smoke-removed frames using corresponding pixels. To obtain the corresponding pixels, we use SIFT and color features with distance constraints. Finally, to reproduce clear video appearance, we compensate pixel values by utilizing the space-time weightings of the corresponding pixels between the smoke-removed frames. Validation experiments show our method can provide effective smoke removal resulting in dynamic scenes.


Smoke removal Dehazing Dark Channel Prior Smoke imaging model Pixel compensation 


  1. 1.
    Flyability. Introducing Gimball, the collision-tolerant drone, May 2016.
  2. 2.
  3. 3.
    Popular Science. Watch google’s humanoid robot learn the world is a harsh place, May 2016.
  4. 4.
    IEEE Spectrum. DARPA’s Rescue-Robot Showdown, May 2016.
  5. 5.
    Tan, R.T.: Visibility in bad weather from a single image. In: Computer Vision and Pattern Recognition, pp. 1–8. IEEE Press, Alaska (2008)Google Scholar
  6. 6.
    Fattal, R.: Single image dehazing. ACM. Trans. Graph. 27(3), 1–9 (2008). (Proceeding SIGGRAPH 2008)CrossRefGoogle Scholar
  7. 7.
    He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. In: Computer Vision and Pattern Recognition, pp. 1956–1963. IEEE Press, Miami (2009)Google Scholar
  8. 8.
    Gibson, K.B., Nguyen, T.Q.: On the effectiveness of the dark channel prior for single image dehazing by approximating with minimum volume ellipsoids. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1253–1256. IEEE Press, Prague (2011)Google Scholar
  9. 9.
    Yang, S., Zhu, Q., Wang, J., Wu, D., Xie, Y.: An improved single image haze removal algorithm based on dark channel prior and histogram specification. In: 6th International Conference on Model Transformation, pp. 279–292, Budapest (2013)Google Scholar
  10. 10.
    Tan, Z., Bai, X., Wang, B., Higashi, A.: Fast single-image defogging. FUJITSU Sci. Tech. J. 50(1), 60–65 (2014)Google Scholar
  11. 11.
    Fattal, R.: Dehazing using color-lines. ACM. Trans. Graph. 34(1), 1–14 (2014). (Proceeding SIGGRAPH 2015)CrossRefGoogle Scholar
  12. 12.
    Tarel, J.P., Hautiere, N.: Fast visibility restoration from a single color or gray level image. In: 20th IEEE International Conference on Computer Vision, pp. 2201–2208. IEEE Press, Kyoto (2009)Google Scholar
  13. 13.
    Zhang, J., Li, L., Zhang, Y., Yang, G., Cao, X., Sun, J.: Video dehazing with spatial and temporal coherence. Vis. Comput. 27(6), 749–757 (2011)CrossRefGoogle Scholar
  14. 14.
    Kim, J., Jang, W., Sim, J., Kim, C.: Optimized contrast enhancement for real-time image and video dehazing. J. Vis. Commun. Image R. 24(3), 410–426 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Graduate School of Advanced Integration ScienceChiba UniversityChibaJapan

Personalised recommendations