基于深度学习的图像去雾算法

针对有雾天气会使图像质量降低，影响对图像信息的提取，导致图像的应用价值减少的问题，提出一种基于深度学习的图像去雾算法。首先，对原有雾图像进行单尺度和多尺度的卷积来特征提取，其次再用多尺度卷积核实现图像细节的重建得到粗略的透射率传播图，同时利用原有雾图像中像素点的位置和亮度值得到大气光值，利用导向滤波得到精细透射率传播图和之前得到的大气光值进而反演出无雾图像，最终对无雾图像进行直方图颜色校正。实验结果表明，相比传统去雾算法，该算法对图像细节的处理更加自然并具有很好的视觉效果。

Image Dehazing Algorithm Based on Deep Learning

Aiming at the problem that the foggy weather will reduce the image quality, affect the extraction of image information, and reduce the application value of the image, an image defogging algorithm based on deep learning is proposed. Firstly, the original fog image is subjected to single-scale and multi-scale convolution for feature extraction, and then the multi-scale convolution kernel is used to reconstruct the image detail to obtain a rough transmittance propagation map. The atmospheric light value is obtained by using the position and brightness value of the pixel in the original fog image. The guided transmission is used to obtain the fine transmittance propagation map and the previously obtained atmospheric light values to invert the fog-free image. The histogram color correction is finally performed on the fog-free image. The experimental results show that compared with the traditional dehazing algorithm, the algorithm is more natural and has a good visual effect.