Open Access Open Access  Restricted Access Subscription or Fee Access

Single Image Dehazing using Dark Channel Prior with Adaptive Window Size and Shape

Ujjwal Mann, Priyanka .

Abstract


Single image dehazing has been widely researched in recent years with some major breakthroughs. Dark Channel Prior (DCP) is among the most prominent dehazing techniques in literature. Although DCP based algorithms provide satisfactory results when accompanied by a refinement technique, like soft matting, to remove the halo effect; it still cannot guarantee accurate estimation of transmission map. There are two main assumptions associated with DCP, firstly it is assumed to be zero to recover the scene radiance and secondly this is also assumed that transmission characteristics do not vary within chosen window. Thus the selection of window size should be made in such a way that both these conditions are satisfied. The proposed dehazing algorithm focuses mainly on selection of the window size and shape that alleviates the drawbacks of the original DCP. Further the original DCP becomes unreliable in the sky region, hence introducing artifacts in that region. This paper proposes a simple method to identify the sky region and to adjust the transmission map of that region. Simulation results using both real images and synthetic foggy images are given which shows better results and hence validating the proposed technique.


Full Text:

PDF

References


K. He, J. Sun, X. Tang. “Single image haze removal using dark channel prior”, IEEE Transactions on Pattern Analysis and Machine Intelligence. December 2011; 33(12): 2341–2353.

S.G. Narasimhan and S.K. Nayar, “Vision and the Atmosphere”, Int. Jour. on Computer Vision, vol. 48, (2002), pp. 233–254.

R. Fattal, “Single Image Dehazing”, Proc. of ACM SIGGRAPH, (2008), pp. 1–9.

R. Tan, “Visibility in Bad Weather from a Single Image”, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, (2008) June, pp. 1–8.

J.P. Tarel and N. Hautiere, “Fast visibility restoration from a single color or gray level image”, IEEE Int. Conf. on Computer Vision, (2009), pp. 2201–2208.

E.B. Goldstein, “Sensation and Perception”, Cengage Learning 1980.

A.J. Preetham, P. Shirley, and B. Smits, “A Practical Analytic Model for Daylight,” Proc. ACM SIGGRAPH ’99, 1999.

A. Levin, D. Lischinski, and Y. Weiss, “A Closed Form Solution to Natural Image Matting,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 61–68, 2006.

K. He, J. Sun, X. Tang, “Guided Image Filtering”, IEEE Trans. on Pattern Analysis And Machine Intelligence, Vol. 35, No. X, 2013

Y. Wang and B. Wu, “Improved Single Image Dehazing using Dark Channel Prior”, Proc. IEEE Conf. Intelligent Computing and Intelligent Systems (ICIS), vol. 2, (2010), pp. 789–792.

J. Chen and L. Chau, “An enhanced window-variant dark channel prior for depth estimation using single foggy image,” IEEE Int Conf. on Image Processing, Melbourne, VIC, 2013, pp. 3508–3512, doi: 10.1109/ICIP.2013.6738724.

S. Yang, Q. Zhu, J. Wang, D. Wu, and Y. Xie, “An Improved Single Image Haze Removal Algorithm Based on Dark Channel Prior and Histogram Specification”, Proc. 3rd Int. Conf. on Multimedia Technology, Atlantis Press, http://www.springer.com/lncs, (2013), pp. 279–292.

Bo Li, S. Wang, J. Zheng, L. Zheng, “Single image haze removal using content-adaptive dark channel and post enhancement” , IET Computer Vision, 2014, Vol. 8, No. 2, pp. 131–140.

J. Liu, J. Zheng, Z. Cui, G. Tang, F. Liu, “An Improved Image Dehazing Algorithm Based on Dark Channel Prior”, IEEE Works. on Advanced Research and Technology in Industry Applications (WARTIA), 2014.

T.M. Bui, H.N. Tran, W. Kim and S. Kim, “Segmenting dark channel prior in single image dehazing”, Electronics Letters, 27th March 2014 Vol. 50 No. 7 pp. 516–518

C. Hsieh, C. Chen and Y. Lin, "Adaptive fast image dehazing algorithm", IEEE Int. Symp. on Independent Computing (ISIC), Orlando, FL, 2014, pp. 1–6, doi: 10.1109/INDCOMP.2014.7011755.

D.K. Naik and D.K. Rout, “Outdoor image enhancement: Increasing visibility under extreme Haze and lighting condition, “IEEE Int. Advance Computing Conference (IACC), Gurgaon, 2014, pp. 1081–1086, doi: 10.1109/IAdCC.2014.6779476.

Y. Zhu, J. Liu and Y. Hao, “An single image dehazing algorithm using sky detection and segmentation,” 7th Int. Congress on Image and Signal Processing, Dalian, 2014, pp. 248–252, doi: 10.1109/CISP.2014.7003786.

C. Hsieh, Y. Lin and C. Chang, “Haze removal without transmission map refinement based on dual dark channels,” Int.Conf. on Machine Learning and Cybernetics, Lanzhou, 2014, pp. 512–516, doi: 10.1109/ICMLC.2014.7009660.

A. Golts, D. Freedman, and M. Elad, “Unsupervised Single Image Dehazing Using Dark Channel Prior Loss”, IEEE Trans. on Image Processing, Vol. X, No. Y, October 2018, pp. 1–8.

L. Guo, J. Song, X. Li, H. Huang, J. Du, G. Sheng, “Single Image Haze Removal Using Dark Channel Prior and Adaptive Transmission Rate”, 2nd Int. Conf. on Computer Science and Intelligent Communication (CSIC 2018), pp.135–141.

M. KokilaDas, P. Dinulal, G. Koshy, P. Simon, “Image Dehazing using Improved Dark Channel Prior and Relativity of Gaussian”, Int conf. on recent trends in advanced computing 2019, icrtac 2019, procedia computer science, science direct, elsevier. pp. 442–448.

D. Zhen, H.A. Jalab, and L. Shirui, “Haze Removal Algorithm Using Improved Restoration Model Based on Dark Channel Prior” Advances in Visual Informatics, 6th Int. Visual Informatics Conf, IVIC November 19–21, 2019, Proc. Springer Nature, pp. 157–169, 2019.

J. Yu, Y. Wang, S. Zhou, R. Zhai, and S. Huang, “Unmanned aerial vehicle (UAV) image haze removal using dark channel prior”, The Sec. Int. Conf. on Physics, Mathematics and Statistics, Journal of Physics: Conf. Series 1324 (2019) 012036. Pp. 1–8.

W. Cheng, H. Hsiao, W. Huang, C. Hsieh, “Image Haze Removal Using Dark Channel Prior Technology with Adaptive Mask Size”, Sensors and Materials, Vol. 32, No. 1, MYU Tokyo, https://doi.org/10.18494/SAM.2020.2593, 2020, pp.317–335.

S. Lee, S. Yun, J. Nam, C. Won, S. Jung, “A review on dark channel prior based image dehazing algorithms”, EURASIP Journal on Image and Video Processing, 2016 doi: 10.1186/s13640-016-0104-y., pp. 1–23.

Z. Li and J. Zheng, “Edge-Preserving Decomposition-Based Single Image Haze Removal,” in IEEE Trans. on Image Processing, vol. 24, no. 12, pp. 5432-5441, Dec. 2015, doi: 10.1109/TIP.2015.2482903.

F. Guo, J. Tang, & Z. Cai, “Objective measurement for image defogging algorithms”. J. Cent. South Univ. 21, 272–286 (2014). https://doi.org/10.1007/s11771-014–1938-z, Springer.

R. C. Gonzalez, R. E. Woods, “Image Compression” in Digital Image Processing, Third ed., Dorling Kindersley (India), Pearson Education, 2008, ch. 8, sec. 8.3, pp 636.


Refbacks

  • There are currently no refbacks.