access icon free Single image dehazing with bright object handling

© The Institution of Engineering and Technology
Received 28/11/2015, Accepted 14/05/2016, Revised 23/03/2016, Published 19/05/2016

This study addresses the shortcomings of the dark channel prior (DCP). The authors propose a new and efficient method for transmission estimation with bright-object handling capability. Based on the intensity value of a bright surface, they categorise DCP failures into two types: (i) obvious failure: occurs on surfaces that are brighter than ambient light. They show that, for these surfaces, altering the transmission value proportional to the brightness is better than the thresholding strategy; (ii) non-obvious failure: occurs on surfaces that are brighter than the neighbourhood average haziness value. Based on the observation that the transmission of a surface is loosely connected to its neighbours, the local average haziness value is used to recompute the transmission of such surfaces. This twofold strategy produces a better estimate of block and pixel-level haze thickness than DCP. To reduce haloes, a reliability map of block-level haze is generated. Then, via reliability-guided fusion of block- and pixel-level haze values, a high-quality refined transmission is obtained. Experimental results show that the authors’ method competes well with state-of-the-art methods in typical benchmark images while outperforming these methods in more challenging scenarios. The authors’ proposed reliability-guided fusion technique is about 60 times faster than other well-known DCP-based approaches.

Inspec keywords: image restoration; image fusion; image resolution

Other keywords: block-level haze thickness estimation; obvious failure; DCP; nonobvious failure; reliability-guided fusion; pixel-level haze thickness estimation; dark channel prior; transmission estimation; transmission value; single image dehazing; bright-object handling capability; bright surface intensity value; reliability map; haloes reduction; local average haziness value; DCP failure categorisation

Subjects: Computer vision and image processing techniques; Sensor fusion; Optical, image and video signal processing

References

    1. 1)
      • 31. Wang, Z., Bovik, A.C., Sheikh, H.R., et al: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process., 2004, 13, pp. 600–612.
    2. 2)
      • 30. ‘Evaluation over images with known transmission’. Available at http://www.cs.huji.ac.il/~raananf/projects/dehaze_cl/results/index_comp.html, accessed 05 September 2015.
    3. 3)
      • 28. Zhu, Q., Mai, J., Shao, L.: ‘A fast single image haze removal algorithm using color attenuation prior’, IEEE Trans. Image Process., Nov 2015, 24, pp. 3522–3533.
    4. 4)
      • 6. Tarel, J.P., Hautiere, N.: ‘Fast visibility restoration from a single color or gray level image’. ICCV, 2009, pp. 2201–2208.
    5. 5)
      • 24. Sulami, M., Glatzer, I., Fattal, R., et al: ‘Automatic recovery of the atmospheric light in hazy images’. IEEE Int. Conf. on Computational Photography (ICCP), 2014, 2014, pp. 1–11.
    6. 6)
      • 20. Carr, P., Hartley, R.: ‘Improved single image dehazing using geometry’. DICTA, 2009, pp. 103–110.
    7. 7)
      • 10. Narasimhan, S.G., Nayar, S.K.: ‘Vision and the atmosphere’, Int. J. Comput. Vis., 2002, 48, pp. 233–254.
    8. 8)
      • 21. Gibson, K.B., Nguyen, T.Q.: ‘An analysis of single image defogging methods using a color ellipsoid framework’, EURASIP J. Image Video Process., 2013, 2013, pp. 1–14.
    9. 9)
      • 23. Wang, Y.K., Fan, C.T.: ‘Single image defogging by multiscale depth fusion’, IEEE Trans. Image Process., 2014, 23, pp. 4826–4837.
    10. 10)
      • 5. Li, B., Wang, S., Zheng, J., et al: ‘Single image haze removal using content-adaptive dark channel and post enhancement’, IET Comput. Vis., 2014, 8, pp. 131–140.
    11. 11)
      • 22. Li, Z., Zheng, J.: ‘Edge-preserving decomposition-based single image haze removal’, IEEE Trans. Image Process., 2015, 24, pp. 5432–5441.
    12. 12)
      • 12. Schechner, Y.Y., Narasimhan, S.G., Nayar, S.K.: ‘Instant dehazing of images using polarization’. CVPR, 2001, pp. 325–332.
    13. 13)
      • 17. Tan, R.T.: ‘Visibility in bad weather from a single image’. CVPR, 2008, pp. 1–8.
    14. 14)
      • 32. Levin, A., Lischinski, D., Weiss, Y.: ‘A closed-form solution to natural image matting’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, pp. 228–242.
    15. 15)
      • 27. Porter, T., Duff, T.: ‘Compositing digital images’, SIGGRAPH Comput. Graph., 1984, 18, pp. 253–259.
    16. 16)
      • 19. ‘A fast single image haze removal algorithm using color attenuation prior’. Available at http://web.siat.ac.cn/∼qingsong/projects/single_image_dehazing/project.html, accessed 05 March 2016.
    17. 17)
      • 18. Narasimhan, S.G., Nayar, S.K.: ‘Chromatic framework for vision in bad weather’. CVPR, 2000, pp. 598–605.
    18. 18)
      • 9. Narasimhan, S.G., Nayar, S.K.: ‘Contrast restoration of weather degraded images’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, pp. 713–724.
    19. 19)
      • 13. Schaul, L., Fredembach, C., Süsstrunk, S.: ‘Color image dehazing using the near-infrared’. ICIP, 2009.
    20. 20)
      • 7. Kopf, J., Neubert, B., Chen, B., et al: ‘Deep photo: model-based photograph enhancement and viewing’, ACM Trans. Graph., 2008, 27, pp. 1–10.
    21. 21)
      • 2. Yu, T., Riaz, I., Piao, J., et al: ‘Real-time single image dehazing using block-to-pixel interpolation and adaptive dark channel prior’, IET Image Process., 2015, 9, pp. 725–734.
    22. 22)
      • 8. Fattal, R.: ‘Single image dehazing’, ACM Trans. Graph., 2008, 27, pp. 1–9.
    23. 23)
      • 29. ‘Guided image filtering’. Available at http://research.microsoft.com/en-us/um/people/kahe/eccv10/, accessed 05 March 2015.
    24. 24)
      • 16. Nishino, K., Kratz, L., Lombardi, S.: ‘Bayesian defogging’, Int. J. Comput. Vis., 2012, 98, pp. 263–278.
    25. 25)
      • 4. Fattal, R.: ‘Dehazing using color-lines’, ACM Trans. Graph., 2014, 34, pp. 1–14.
    26. 26)
      • 34. Dollar, P., Appel, R., Belongie, S., et al: ‘Fast feature pyramids for object detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, pp. 1532–1545.
    27. 27)
      • 15. Tan, K., Oakley, J.P.: ‘Enhancement of color images in poor visibility conditions’. ICIP, 2000, pp. 788–791.
    28. 28)
      • 26. ‘Constrained optimization’. Available at http://www.mathworks.com/help/optim/constrained-optimization.html, accessed 05 September 2015.
    29. 29)
      • 3. Tang, K., Yang, J., Wang, J.: ‘Investigating haze-relevant features in a learning framework for image dehazing’. CVPR, 2014, pp. 2995–3002.
    30. 30)
      • 1. He, K., Sun, J., Tang, X.: ‘Single image haze removal using dark channel prior’. CVPR, 2009, pp. 1956–1963.
    31. 31)
      • 14. Narasimhan, S.G., Nayar, S.K.: ‘Interactive (de) weathering of an image using physical models’. CPMCV, 2003, p. 1.
    32. 32)
      • 11. He, K., Sun, J., Tang, X.: ‘Guided image filtering’. ECCV, 2010, pp. 1–14.
    33. 33)
      • 25. Scharstein, D., Szeliski, R.: ‘A taxonomy and evaluation of dense two-frame stereo correspondence algorithms’, Int. J. Comput. Vis., 2002, 47, pp. 7–42.
    34. 34)
      • 33. Lemire, D.: ‘Streaming maximum-minimum filter using no more than three comparisons per element’, Nord. J. Comput., 2006, 13, pp. 328–339.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2015.0451
Loading

Related content

content/journals/10.1049/iet-cvi.2015.0451
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading