Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 5, pp 5701–5713 | Cite as

Non-local Dehazing enhanced by color gradient

  • Jun Chu
  • Jia Luo
  • Lu LengEmail author
Article
  • 118 Downloads

Abstract

Ubiquitous visual surveillance is critical to public security. Unfortunately, adverse weathers, especially haze, degrade visual surveillance quality evidently, so dehazing is commonly used to limit the interference of haze. Unlike traditional dehazing methods that use various patch-based priors, non-local dehazing employs color index and regularization to estimate and refine initial transmission, respectively. However, currently non-local dehazing has not made the most of pixel neighborhood relation, so the edge details cannot be preserved powerfully. Since the gradient represents the difference between the adjacent pixels, the non-local dehazing algorithm is enhanced by color gradient in this paper. The color index and color gradient are jointly clustered to improve the accuracy of initial transmission. Finally the haze is removed according to the transmission refined by guided filter. The experimental results show that the proposed non-local dehazed algorithm enhanced by color gradient can effectively maintain the edge details and improve the performance of dehazing.

Keywords

Non-local dehazing Color gradient Guided filter 

Notes

Acknowledgements

This work was supported by National Natural Science Foundation of China (61663031, 61741312, 61772255, 61763033), Key Research & Development Project of Jiangxi Province (20161BBE50085, 20171ACE50024), Construction Project of Advantage Scientific & Technological Innovation Team in Jiangxi Province (20165BCB19007), Construction Project of Advantage Scientific & Technological Innovation Team in Nanchang City, Application Innovation Program of Public Security Ministry (2017YYCXJXST048), Science and Technology Research Project of Education Department of Jiangxi Province (GJJ150715), Open Foundation of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition (ET201680245, TX201604002), Ph.D Starting Foundation of Nanchang Hangkong University (EA201620045), Post-graduate Innovation Foundation of Jiangxi Province (YC2016021, YC2017095).

References

  1. 1.
    Berman D, Avidan S (2016) Non-local image dehazing. IEEE Conference on Computer Vision and Pattern Recognition, 1674–1682Google Scholar
  2. 2.
    Chen C, Do MN, Wang J (2016) Robust image and video dehazing with visual artifact suppression via gradient residual minimization. European Conference on Computer Vision, p. 576–591Google Scholar
  3. 3.
    Choudhury SK, Sa PK, Bakshi S et al (2016) An evaluation of background subtraction for object detection vis-a-vis mitigating challenging scenarios. IEEE Access 4(99):6133–6150CrossRefGoogle Scholar
  4. 4.
    Choudhury SK, Sa PK, Padhy RP et al (2017) Improved pedestrian detection using motion segmentation and silhouette orientation. Multimedia Tools Appl 6:1–40Google Scholar
  5. 5.
    Fang S, Wang F, Zhan Q et al (2012) Simultaneous dehazing and denoising of single hazing image. Pattern Recognit Artif Intell 25(1):136–142Google Scholar
  6. 6.
    Gonzalez CI, Melin P, Castro JR, et al (2015) Color image edge detection method based on interval type-2 fuzzy systems. Design of Intelligent Systems Based on Fuzzy Logic, Neural Networks and Nature-Inspired Optimization. Springer International Publishing, p. 3–11Google Scholar
  7. 7.
    Gonzalez CI, Melin P, Castro JR, et al (2017) Edge detection methods and filters used on digital image processing. Edge Detection Methods Based on Generalized Type-2 Fuzzy Logic. Springer International Publishing, p. 11–16Google Scholar
  8. 8.
    He KM, Sun J (2009) Single image haze removal using dark channel prior. IEEE Conf Comput Vis Pattern Recognit, p. 1956–1963Google Scholar
  9. 9.
    He K, Sun J (2015) Fast guided filter. Comput Sci 1–2Google Scholar
  10. 10.
    He K, Sun J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 35(6):1397–1409CrossRefGoogle Scholar
  11. 11.
    Israni S, Jain S (2016) Edge detection of license plate using Sobel operator. International Conference on Electrical, Electronics, and Optimization Techniques, 3561–3563Google Scholar
  12. 12.
    Jiang B, Woodell GA, Jobson DJ (2015) Novel multi-scale Retinex with color restoration on graphics processing unit. J Real-Time Image Proc 10(2):239–253CrossRefGoogle Scholar
  13. 13.
    Lim SH, Isa NAM, Ooi CH et al (2015) A new histogram equalization method for digital image enhancement and brightness preservation. SIViP 9(3):675–689CrossRefGoogle Scholar
  14. 14.
    Meng G, Wang Y, Duan J, et al (2013) Efficient image dehazing with boundary constraint and contextual regularization. IEEE Int Conf Comput Vision, p. 617-624Google Scholar
  15. 15.
    Nanda A, Chauhan DS, Sa PK et al (2017) Illumination and scale invariant relevant visual features with hypergraph-based learning for multi-shot person re-identification. Multimedia Tools Appl 6:1–26Google Scholar
  16. 16.
    Narasimhan SG, Nayar SK (2001) Removing weather effects from monochrome images. IEEE Conf Comput Vis Pattern Recognit, p. 186–193Google Scholar
  17. 17.
    Narasimhan SG, Nayar SK (2002) Vision and the atmosphere. Int J Comput Vis 48(3):233–254CrossRefGoogle Scholar
  18. 18.
    Narasimhan SG, Nayar SK (2003) Contrast restoration of weather degraded images. IEEE Trans Pattern Anal Mach Intell 25(6):713–724CrossRefGoogle Scholar
  19. 19.
    Putra O V, Prianto B, Yuniarno E M, et al (2016) Visibility restoration of lake crater hazy image based on dark channel prior. International Computer Science and Engineering Conference, p. 1–6Google Scholar
  20. 20.
    Raman R, Choudhury SK, Bakshi S (2018) Spatiotemporal optical blob reconstruction for object detection in grayscale videos. Multimedia Tools & Applications 77(1):741-762Google Scholar
  21. 21.
    Ren W, Liu S, Zhang H, et al (2016) Single image dehazing via multi-scale convolutional neural networks. European Conference on Computer Vision, p. 154–169Google Scholar
  22. 22.
    Sun Y, Xiao L, Wei Z et al (2007) Method of defogging image of outdoor scenes based on PDE. J Syst Simulation 19(16):3739–3744Google Scholar
  23. 23.
    Wang YK, Fan CT (2014) Single image defogging by multiscale depth fusion. IEEE Trans Image Process 23(11):4826–4837MathSciNetCrossRefGoogle Scholar
  24. 24.
    Yadav G, Maheshwari S, Agarwal A (2016) Multi-domain image enhancement of foggy images using contrast limited adaptive histogram equalization method. International Conference on Recent Cognizance in Wireless Communication Image Processing, p. 31–38Google Scholar
  25. 25.
    Zeng JX, Yu YL (2017) Image defogging and edge preserving algorithm based on dark channel prior bilateral filtering. J Image Graph 22(2):147–153Google Scholar
  26. 26.
    Zhang S, Qing C, Xu X, et al (2016) Dehazing with improved heterogeneous atmosphere light estimation and a nonlinear color attenuation prior model. 10th International Symposium on Communication Systems, Networks and Digital Signal Processing, p. 1–6Google Scholar
  27. 27.
    Zhu Q, Mai J, Shao L (2015) A fast single image haze removal algorithm using color attenuation prior. IEEE Trans Image Process 24(11):3522–3533MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of SoftwareNanchang Hangkong UniversityNanchangPeople’s Republic of China
  2. 2.Key Laboratory of Jiangxi Province for Image Processing and Pattern RecognitionNanchang Hangkong UniversityNanchangPeople’s Republic of China
  3. 3.School of Information EngineeringNanchang Hangkong UniversityNanchangPeople’s Republic of China

Personalised recommendations