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.
KeywordsImage dehazing Transmission estimation Dark channel prior
- 5.Meng, G.F., Wang, Y., Duan, J.Y., Xiang, S.M., Pan, C.H.: Efficient image dehazing with boundary constraint and contextual regularization. In: IEEE International Conference on Computer Vision, pp. 617–624(2014)Google Scholar
- 6.He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 33, no. 12, 1956–1963 (2009), pp. 3271–3282 (2013)Google Scholar
- 9.Huang, C.Q., Yang, D., Zhang, R.L., Wang, L., Zhou, L.H.: Improved algorithm for image haze removal based on dark channel priority. Comput. Electr. Eng. (2017, in press). https://doi.org/10.1016/j.compeleceng.2017.09.018