As the inaccurate estimation of atmospheric light curtain and atmospheric light result in the halo effect, color distortion, and low contrast in the process of haze image restoration, a dehazing algorithm based on weighted least square (WLS) filtering and restorative controlling factor is proposed. Firstly, this study analyzes the principle and performance of the WLS filter, which can be utilized to effectively estimate the atmospheric light curtain. Secondly, with the assistance of the Sobel operator, the binary image edges are detected. The number of edges and the mean value of pixels are taken as the bases of the quad-tree space index, which improves the estimation accuracy of the atmospheric light. Finally, according to the causes of color distortion in the sky area, a restorative controlling factor is introduced to improve visual effects. Experimental results show that the mean gradient obtained by this method increases by 58.03%, and the information entropy increases by 2.88%. In particular, the running time relatively decreases by more than 50%. The proposed method achieves better restoration in terms of contrast, visibility, and color fidelity of the haze image containing complicated near and distant scenes that mixed dense haze, mist, and sky area.
1)根据浓雾区域或天空区域具有灰度值相对较高的特征, 在通道最小值的基础上, 首先求取四叉树等分后子图像的归一化均值
\begin{document}$ m $\end{document},
\begin{document}$ m $\end{document}越大表明该区域是雾最浓区域的可能性越高.
2)鉴于浓雾区域的边缘信息较弱、细节纹理不明显, 此处采用简单高效的Sobel算子检测子图像的可见边缘数目, 并统计其在整幅图像中所占的比例
\begin{document}$ n $\end{document},
\begin{document}$ n $\end{document}越大意味着该区域是雾最浓区域的可能性越低.
3)计算
\begin{document}$ m $\end{document}与
\begin{document}$ n $\end{document}的差值:
ReferencesHe KM, Sun J, Tang XOSingle image haze removal using dark channel prior201133122341235310.1109/TPAMI.2010.168
He KM, Sun J, Tang XO. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341–2353.
He KM, Sun J, Tang XOGuided image filtering20133561397140910.1109/TPAMI.2012.213
He KM, Sun J, Tang XO. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397–1409.
Nishino K, Kratz L, Lombardi S. Bayesian defogging. International Journal of Computer Vision, 2012, 98(3): 263–278.
et al. Efficient image dehazing with boundary constraint and contextual regularization. Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney: IEEE, 2013. 617–624.]]>
Fattal RDehazing using color-lines201434113
Fattal R. Dehazing using color-lines. ACM Transactions on Graphics, 2014, 34(1): 13.
Gayathri S, Ameena Bibi NEnhancement of dehaze images using multiscale Retinex2021553948
Gayathri S, Ameena Bibi N. Enhancement of Dehaze images using multiscale Retinex. International Journal of Advanced Engineering Science and Information Technology, 2021, 5(5): 39–48.
Cai BL, Xu XM, Jia K, et alDehazeNet: An end-to-end system for single image haze removal201625115187519810.1109/TIP.2016.2598681
Cai BL, Xu XM, 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.
et al. Single image dehazing via multi-scale convolutional neural networks. Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer, 2016. 154–169.]]>
Farbman Z, Fattal R, Lischinski D, et alEdge-preserving decompositions for multi-scale tone and detail manipulation2008273110
Farbman Z, Fattal R, Lischinski D, et al. Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Transactions on Graphics, 2008, 27(3): 1–10.