Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 23, pp 33401–33414 | Cite as

Estimation of atmospheric light based on gaussian distribution

  • Wenbo Zhang
  • Jinbo Lu
  • Xiaobo Xu
  • Xiaorong HouEmail author
Article
  • 48 Downloads

Abstract

Existing defogging algorithms use a small number of sample points to estimate the atmospheric light, which leads to poor defogging effect. To solve this problem, a novel Gaussian distribution based algorithm for atmospheric light estimation is proposed. The algorithm has the following features: it uses a brightness threshold to select the candidate points to increase the number of initial samples; it uses clustering algorithms to merge the point clusters for increasing the samples included in the candidate point cluster; it uses a proportional threshold to filter out unreasonable point clusters; it regards each candidate point cluster as a single light source and calculates their influence on surrounding pixels with a Gaussian-distribution-based model; and it uses an atmospheric light map (instead of a constant value) to restore the image. The experimental results suggest that the defogging results produced by the proposed algorithm look more natural than the original algorithm under subjective vision and the objective image quality evaluation indicators are also excellent.

Keywords

Image defog Estimation of atmospheric light Statistical clustering Gaussian distribution Image quality evaluation 

Notes

References

  1. 1.
    Agaian SS, Panetta K, Grigoryan AM (2000) A new measure of image enhancement. In: IASTED international conference on signal processing & communication, Citeseer, pp 19–22Google Scholar
  2. 2.
    Choi L K, You J, Bovik A C (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–3901MathSciNetCrossRefGoogle Scholar
  3. 3.
    Cozman F, Krotkov E (1997) Depth from scattering. In: 1997 IEEE computer society conference on computer vision and pattern recognition, 1997. Proceedings, IEEE, pp 801–806Google Scholar
  4. 4.
    Hautière N, Tarel JP, Aubert D, Dumont E (2011) Blind contrast enhancement assessment by gradient ratioing at visible edges. Image Analysis & Stereology 27(2):87–95MathSciNetCrossRefGoogle Scholar
  5. 5.
    He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353CrossRefGoogle Scholar
  6. 6.
    He K, Sun J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 6:1397–1409CrossRefGoogle Scholar
  7. 7.
    Hu R, Zhu X, Cheng D, He W, Yan Y, Song J, Zhang S (2017) Graph self-representation method for unsupervised feature selection. Neurocomputing 220:130–137CrossRefGoogle Scholar
  8. 8.
    Levin A, Lischinski D, Weiss Y (2008) A closed-form solution to natural image matting. IEEE Trans Pattern Anal Mach Intell 30(2):228–242CrossRefGoogle Scholar
  9. 9.
    Lu H, Li Y, Nakashima S, Serikawa S (2016) Single image dehazing through improved atmospheric light estimation. Multimed Tools Appl 75(24):17081–17096CrossRefGoogle Scholar
  10. 10.
    Narasimhan SG, Nayar SK (2002) Vision and the atmosphere. Int J Comput Vis 48(3):233–254CrossRefGoogle Scholar
  11. 11.
    Narasimhan SG, Nayar SK (2003) Contrast restoration of weather degraded images. IEEE Trans Pattern Anal Mach Intell 25(6):713–724CrossRefGoogle Scholar
  12. 12.
    Narasimhan SG, Nayar SK (2003) Interactive (de) weathering of an image using physical models. In: IEEE workshop on color and photometric methods in computer vision, France, vol 6, pp 1Google Scholar
  13. 13.
    Nayar SK, Narasimhan SG (1999) Vision in bad weather. In: The proceedings of the 17th IEEE international conference on computer vision, 1999, IEEE, vol 2Google Scholar
  14. 14.
    Oakley JP, Satherley BL (1998) Improving image quality in poor visibility conditions using a physical model for contrast degradation. IEEE Trans Image Process 7(2):167–179CrossRefGoogle Scholar
  15. 15.
    Park H, Park D, Han DK, Ko H (2014) Single image haze removal using novel estimation of atmospheric light and transmission. In: 2014 IEEE international conference on image processing (ICIP). IEEE, pp 4502–4506Google Scholar
  16. 16.
    Sulami M, Glatzer I, Fattal R, Werman M (2014) Automatic recovery of the atmospheric light in hazy images. In: 2014 IEEE international conference on computational photography (ICCP). IEEE, pp 1–11Google Scholar
  17. 17.
    Sun W, Wang H, Sun C, Guo B, Jia W, Sun M (2015) Fast single image haze removal via local atmospheric light veil estimation. Comput Electr Eng 46:371–383CrossRefGoogle Scholar
  18. 18.
    Wang YK, Fan CT (2014) Single image defogging by multiscale depth fusion. IEEE Trans Image Process 23(11):4826–4837MathSciNetCrossRefGoogle Scholar
  19. 19.
    Wu D, Qs Zhu (2015) The latest research progress of image dehazing. Acta Automatica Sinica 41(2):221–239Google Scholar
  20. 20.
    Zhang L, Li X, Hu B, Ren X (2015) Research on fast smog free algorithm on single image. In: 2015 1st international conference on computational intelligence theory, systems and applications (CCITSA), IEEE, pp 177–182Google Scholar
  21. 21.
    Zhang S, Li X, Zong M, Zhu X, Cheng D (2017) Learning k for knn classification. ACM Trans Intell Syst Technol (TIST) 8(3):43Google Scholar
  22. 22.
    Zhang S, Li X, Zong M, Zhu X, Wang R (2018) Efficient knn classification with different numbers of nearest neighbors. IEEE Trans Neural Netw Learn Syst 29 (5):1774–1785MathSciNetCrossRefGoogle Scholar
  23. 23.
    Zhang W, Hou X (2018) Light source point cluster selection-based atmospheric light estimation. Multimed Tools Appl 77(3):2947–2958CrossRefGoogle Scholar
  24. 24.
    Zhao H, Xiao C, Yu J, Xu X (2015) Single image fog removal based on local extrema. IEEE/CAA Journal of Automatica Sinica 2(2):158–165MathSciNetCrossRefGoogle Scholar
  25. 25.
    Zhu Q, Mai J, Shao L, et al (2015) A fast single image haze removal algorithm using color attenuation prior. IEEE Trans Image Process 24(11):3522–3533MathSciNetCrossRefGoogle Scholar
  26. 26.
    Zhu X, Zhang L, Huang Z (2014) A sparse embedding and least variance encoding approach to hashing. IEEE Trans Image Process 23(9):3737–3750MathSciNetCrossRefGoogle Scholar
  27. 27.
    Zhu X, Li X, Zhang S (2016) Block-row sparse multiview multilabel learning for image classification. IEEE Trans Cybern 46(2):450–461CrossRefGoogle Scholar
  28. 28.
    Zhu X, Suk HI, Lee SW, Shen D (2016) Subspace regularized sparse multitask learning for multiclass neurodegenerative disease identification. IEEE Trans Biomed Eng 63(3):607–618CrossRefGoogle Scholar
  29. 29.
    Zhu X, Li X, Zhang S, Ju C, Wu X (2017) Robust joint graph sparse coding for unsupervised spectral feature selection. IEEE Trans Neural Netw Learn Syst 28(6):1263–1275MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Automation EngineeringUniversity of Electronic Science and Technology of ChinaChengduChina
  2. 2.China Electronics Technology Cyber Security Co., Ltd.ChengduChina

Personalised recommendations