An Effective and Efficient Dehazing Method of Single Input Image

The quality of an image may be degraded seriously when it is captured in a foggy weather condition. In this paper, an effective and efficient dehazing method is proposed for a single input image by combining the dark channel prior information and a low-light image enhancement model. First, the dark channel is derived via two minimum operations. After estimating the atmospheric light, the transmission is initialized according to the property of aerial perspective. In terms of the atmospheric light, a bound constraint is computed further to refine the transmission. Finally, a high-quality image is obtained via the haze image model. Experimental results demonstrate the effectiveness and efficiency of the proposed method.

[1]  David Zhang,et al.  FSIM: A Feature Similarity Index for Image Quality Assessment , 2011, IEEE Transactions on Image Processing.

[2]  Yu Li,et al.  LIME: Low-Light Image Enhancement via Illumination Map Estimation , 2017, IEEE Transactions on Image Processing.

[3]  Hongguang Li,et al.  Haze removal for unmanned aerial vehicle aerial video based on spatial-temporal coherence optimisation , 2018, IET Image Process..

[4]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[5]  Jian Sun,et al.  Single image haze removal using dark channel prior , 2009, CVPR.

[6]  Wei Liu,et al.  Haze removal for a single inland waterway image using sky segmentation and dark channel prior , 2016, IET Image Process..

[7]  Nanning Zheng,et al.  Haze Removal Using the Difference- Structure-Preservation Prior , 2017, IEEE Transactions on Image Processing.

[8]  Hao Wang,et al.  Fast single image haze removal via local atmospheric light veil estimation , 2015, Comput. Electr. Eng..

[9]  Shih-Chia Huang,et al.  A High-Efficiency and High-Speed Gain Intervention Refinement Filter for Haze Removal , 2016, Journal of Display Technology.

[10]  Dong Yang,et al.  Improved algorithm for image haze removal based on dark channel priority , 2017, Comput. Electr. Eng..

[11]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[12]  Gaofeng Meng,et al.  Efficient Image Dehazing with Boundary Constraint and Contextual Regularization , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Apurva Kumari,et al.  Real Time Visibility Enhancement for Single Image Haze Removal , 2015 .