改进大气散射模型实现的图像去雾算法

传统大气散射模型在图像去雾的求解过程中通常假设场景入射光为全局常量,然而这种假设并不合理,为此提出一种基于改进大气散射模型的图像去雾算法.首先基于亮通道先验和模糊聚类对雾图进行场景分类,并估计出各个场景的入射光照;然后根据光学辐射特性估计出场景结构,并利用雾气浓度估计模型进一步获得透射率的表达式;最后通过改进大气散射模型恢复出无雾图像.大量对比实验结果表明,该算法能够恢复出细节丰富、清晰自然的无雾图像,计算速度相对较快,能满足一般工程的实时性要求.

An Image Dehazing Algorithm Based on Improved Atmospheric Scattering Model

The scene incident light is always assumed to be a global constant when the traditional atmos- pheric scattering model is used in the image dehazing. However, the assumption is unreasonable. Thus, an image dehazing method based on an improved atmospheric scattering model is put forward. Firstly, a hazy image was classified into different scenes by the brightness channel prior and the fuzzy clustering. Secondly, the incident light of each scene was estimated. Then, the scene structure was estimated by the optical radia- tion characteristic. After that, the transmission can be calculated by the haze concentration estimation model. Finally, the hazy image is recovered with the improved atmospheric scattering model. A large number of comparative experimental results show that the proposed algorithm can recover a more detailed, clear and natural haze-free images. Besides, the calculation speed is relatively fast which can meet the real-time re- quirements of general engineering.