Home Image Defogging Algorithm Based on Sky Region Segmentation and Dark Channel Prior
Article
Licensed
Unlicensed Requires Authentication

Image Defogging Algorithm Based on Sky Region Segmentation and Dark Channel Prior

  • Zuyun Jiang , Xiangdong Sun and Xiaochun Wang EMAIL logo
Published/Copyright: November 17, 2020
Become an author with De Gruyter Brill

Abstract

Based on image segmentation and the dark channel prior, this paper proposes a fog removal algorithm in the HSI color space. Usually, the dark channel prior based defogging methods easily produce color distortion and halo effect when applied on images with a large sky area, because the sky region does not meet the prior assumption. For this reason, our method presents a new threshold sky region segmentation algorithm using the initial transmission map of the intensity component I. Based on the segmentation result, the initial transmission map is modified in turn, and finally refined by the guided filter. The saturation components S is reconstructed using the low frequencies of the V-transform to reduce noise, and stretched by multiplying a constant related to the initial transmission map. Experimental results show that the proposed algorithm has low time complexity and compelling fog removal result in both visual effect and quantitative measurement.


Supported by the National Natural Science Foundation of China (61571046) and the National Key Research and Development Program of China (2017YFF0209806)


References

[1] Fan T H, Li C L, Ma X, et al. An improved single image defogging method based on Retinex. International Conference on Image, Vision and Computing, 2017: 410–413.Search in Google Scholar

[2] Jiang B, Zhong M. Improved histogram equalization algorithm for image enhancement. Laser and Infrared, 2014(6): 702–706.Search in Google Scholar

[3] Narasimhan S G, Nayar S K. Removing weather effects from monochrome images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, 2001, 2: 186–193.10.1109/CVPR.2001.990956Search in Google Scholar

[4] Narasimhan S G, Nayar S K. Interactive (de) weathering of an image using physical models. IEEE International Conference on Computer Vision Workshop on Color and Photometric Methods in Computer Vision (CPMCV), 2003: 1–8.Search in Google Scholar

[5] Cai B L, Xu X M, Jia K, et al. DehazeNet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187–5198.10.1109/TIP.2016.2598681Search in Google Scholar PubMed

[6] Ren W Q, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks. Computer vision — ECCV 2016. Springer International Publishing, 2016: 154–169.10.1007/978-3-319-46475-6_10Search in Google Scholar

[7] Zhang H, Patel V M. Densely connected pyramid dehazing network. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 3194–3203.10.1109/CVPR.2018.00337Search in Google Scholar

[8] Ren W Q, Ma L, Zhang J W, et al. Gated fusion network for single image dehazing. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 3253–3261.10.1109/CVPR.2018.00343Search in Google Scholar

[9] Qu Y Y, Chen Y Z, Huang J Y, et al. Enhanced Pix2pix dehazing network. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 8160–8168.10.1109/CVPR.2019.00835Search in Google Scholar

[10] Fattal R. Single image dehazing. ACM Transactions on Graphics, 2008, 27(3): 1–9.10.1145/1399504.1360671Search in Google Scholar

[11] Tarel J P, Hautiere N. Fast visibility restoration from a single color or gray level image. IEEE Conference on Computer Vision, 2009: 1701–1708.10.1109/ICCV.2009.5459251Search in Google Scholar

[12] Meng G F, Wang Y, Duan J R, et al. Efficient image dehazing with boundary constraint and contextual regularization. ICCV 2013, IEEE International Conference on Computer Vision, 2013: 617–624.10.1109/ICCV.2013.82Search in Google Scholar

[13] Berman B, Treibitz T, Avidan S. Non-local image dehazing. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, 2016: 1674–1682.10.1109/CVPR.2016.185Search in Google Scholar

[14] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341–2353.10.1109/TPAMI.2010.168Search in Google Scholar PubMed

[15] He K M, Sun J, Tang X O. Guided image filtering. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2013, 35(6): 386–392.10.1007/978-3-642-15549-9_1Search in Google Scholar

[16] Mao X Y, Li W X, Ding X M. Single image dehazing algorithm based on sky region segmentation. Journal of Computer Applications, 2017, 37(10): 2916–2920.Search in Google Scholar

[17] Wang W C, Yuan X H, Wu X J, et al. Dehazing for images with large sky region. Neurocomputing, 2017, 238: 365–376.10.1016/j.neucom.2017.01.075Search in Google Scholar

[18] Wang G Y, Ren G H, Jiang L H, et al. single image dehazing algorithm based on sky region segmentation. Information Technology Journal, 2013, 12(6): 1168–1175.10.3923/itj.2013.1168.1175Search in Google Scholar

[19] Xiao J H, Zhu L, Zhang Y Q, et al. Scene-aware image dehazing based on sky-segmented dark channel prior. IET Image Processing, 2017, 11(12): 1163–1171.10.1049/iet-ipr.2017.0058Search in Google Scholar

[20] Song R X,Wang T J, Qi D X, et al. The Complete orthogonal V-system and its applications. Communication on Pure and Applied Analysis, 2007, 6(3): 853–871.10.3934/cpaa.2007.6.853Search in Google Scholar

[21] Huang C, Yang L H, Qi D X. A New class of multi-wavelet bases: V-system. Act Mathematical Sonica, 2012, 28(1): 105–120.10.1007/s10114-012-9424-8Search in Google Scholar

[22] Wang S H, Cho W, et al. Contrast-dependent saturation adjustment for outdoor image enhancement. Journal of the Optical Society of America A, 2017, 34(1): 7–17.10.1364/JOSAA.34.000007Search in Google Scholar PubMed

[23] Javier V C, Adrian G, Praveen C, et al. A fast image dehazing method that does not introduce color artifacts. Journal of Real-Time Image Processing, 2018(8): 1–16.Search in Google Scholar

[24] Kim J H, Jang W D, Sim J Y, et al. Optimized contrast enhancement for real-time image and video dehazing. Journal of Visual Communication and Image Representation, 2013, 24(3): 410–425.10.1016/j.jvcir.2013.02.004Search in Google Scholar

[25] Song R X, Sun X D, Wang X C. Haze removal algorithm based on HSI color space and dark channel prior. Journal of Systems Science and Mathematical Sciences, 2017, 37(10): 2111–2120.Search in Google Scholar

Received: 2020-02-15
Accepted: 2020-06-15
Published Online: 2020-11-17
Published in Print: 2020-11-25

© 2020 Walter De Gruyter GmbH, Berlin/Boston

Downloaded on 23.9.2025 from https://www.degruyterbrill.com/document/doi/10.21078/JSSI-2020-476-11/html
Scroll to top button