Weighted variational regularization image dehazing algorithm based on non-local prior

In hazy weather conditions, the quality of images taken outdoors will be degraded, so researching image dehazing has great practical significance. Therefore, an image dehazing algorithm based on non-local prior weighted variational regularization is proposed. Since the performance of the image dehazing algorithm depends largely on the accuracy of the estimated transmission, a classical non-local prior algorithm is first adopted to make a rough initial estimate of the transmission. Then a weighted variational regularization model is proposed to further optimize the initial transmission and solve the model by the alternating direction multiplier method. Finally, a haze-free image can be recovered directly from the atmospheric scattering model by using the optimized transmission. The experimental results verify that the proposed algorithm has higher image dehazing performance than several commonly used algorithms.

[1]  Zhe Xiao,et al.  Variational Regularized Transmission Refinement for Image Dehazing , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[2]  Jean-Baptiste Thomas,et al.  Deep Learning for Dehazing: Comparison and Analysis , 2018, 2018 Colour and Visual Computing Symposium (CVCS).

[3]  Shai Avidan,et al.  Non-local Image Dehazing , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[6]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Shree K. Nayar,et al.  Instant dehazing of images using polarization , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Lee-Sup Kim,et al.  An advanced contrast enhancement using partially overlapped sub-block histogram equalization , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[9]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[10]  W. Middleton,et al.  Vision Through the Atmosphere , 1952 .