基于逆通道与改进引导滤波的暗通道去雾算法

为解决暗通道先验去雾算法存在的透射率计算不精确和图像去雾后偏暗等问题，提出一种利用逆通道与改进滤波的暗通道去雾算法。根据雾天可见光的衰减特性，基于蓝色通道的逆通道得到修正的雾天图像暗通道图，通过在引导滤波中设置自适应平滑因子，滤波处理时检测图像边缘并利用局部方差自适应调整滤波强度，以获得更准确的透射率，同时选取图像中天空部分亮度最大区域的像素平均值作为大气光值，最终得到修复的去雾图像。实验结果表明，与基于边界限制的去雾算法和多尺度小波去雾算法相比，该算法的峰值信噪比和结构相似性值更高且均方误差更小，图像去雾效果更好，能较好保持图像原有信息。

Dark Channel Defogging Algorithm Based on Inverse Channel and Improved Guided Filtering

To solve the problems of the existing prior defogging algorithms based on dark channel, such as inaccurate calculation of transmittance and dark defogged images and other problems, this paper proposes a dark channel defogging algorithm using inverse channel and improved filtering.According to the attenuation characteristics of visible light in foggy weather, the inverse channel of the blue channel is used to obtain the modified dark channel map of the foggy image.By setting an adaptive smoothing factor in the guided filtering, the edge of the image is detected in the filtering process, and the filtering intensity is adaptively adjusted by using local variance for more accurate transmittance.The average value of the pixels in the area with the maximum brightness of the sky part in the image is taken as the atmospheric light value, and finally the repaired defogged image is obtained.Experimental results show that compared with the defogging algorithm based on boundary restriction and multi-scale wavelet defogging algorithm, the proposed algorithm has higher Peak Signal to Noise Ratio(PSNR) and Structual Similarity(SSIM)value, smaller Mean Square Error(MSE) and better image defogging effects.It can keep the original image information better.