基于大气散射模型的去雾算法

Image Dehazing Algorithm Based on Atmospheric Scattering Model

提出一种基于大气散射模型的去雾算法。基于大气散射模型,利用四细分法求取光度值;结合均方误差对比模型,构建像素信息丢失与对比度联合代价函数;优化代价函数获得最优透射估计,保留更多像素信息;增设约束条件恢复去雾图像。实验结果表明,所提算法能够保留更多像素信息,消除"黑影"现象,去雾效果良好。

Image dehazing is a hot research topic in the field of computer vision. The traditional algorithm uses contrastenhanced processing method to make image with low contrast of image dehazing clear. In order to achieve enhanced contrast,the compensation of truncation effect of pixel values often causes a lot of pixel information loss,and leads to the fog image ＂ shadow ＂ phenomenon,image dehazing effect is not ideal. Aiming at solving this problem,this paper proposes an image dehazing algorithm based on the atmospheric scattering model. First of all,based on the atmospheric scattering model,a method with four subdivisions is used to calculate the photometric values. Secondly,based on MSE compared model,a function for pixel information loss associated with contrast cost is built. Optimizing the cost function the optimal transmission estimation can be obtained,and more information of pixels can be kept. Finally,constraints are designed to restore dehazed image. The experimental results show that the proposed algorithm can retain more information of pixels,and eliminate the phenomenon of ＂ shadow＂,and has a good effect of dehazing image.