Bright-Dark Channel Defogging Algorithm Based on SLIC Super-pixel Segmentation
Tingping Yang, Baojuan Li, Yuncheng Zhang, Di Fan, Aying Wei · 2023
In order to solve the problem of block effect and distortion in the distant view after using dark channel prior algorithm to remove fog, this paper presents a bright and dark channel defogging algorithm based on SLIC super-pixel segmentation. Firstly, the irregular region obtained by SLIC super-pixel segmentation is used to replace the fixed window to obtain the bright and dark channel map; Secondly, the weighted atmospheric light is obtained by weighting global atmospheric light and pixel-level atmospheric light; Then the transmittance of the bright area is corrected; Finally, the defogging image is obtained based on the atmospheric scattering model. The outcomes demonstrated that the block effect at the edge of the image and the distortion at the perspective of the image can be basically solved after using the proposed algorithm, which is superior to other contrast algorithms in subjective evaluation and objective analysis.