基于多子块协同单尺度Retinex的浓雾图像增强

针对现有算法增强雾气分布不均匀的浓雾图像效果不理想的问题，提出了一种基于多子块协同单尺度Retinex的浓雾图像增强算法。该算法不同于传统的利用全局统计量获取动态截断值的Retinex算法，首先将图像划分为多个子块，计算出适合不同浓度雾气的动态截断值；然后，利用动态截断值对高频细节信息进行动态范围调整，得到多幅局部最优的图像；最后，融合多幅局部最优图像生成高质量的结果，从而实现浓雾图像每个区域细节的增强。实验结果表明，所提算法能够有效去除不均匀浓雾，并保证去雾后图像的亮度保持在适合人眼观察的范围。 

Foggy image enhancement based on multi-block coordinated single-scale Retinex

Aimed at the problem that the existing algorithms are not ideal to enhance foggy images with non-uniform fog distribution, this paper proposes a foggy image enhancement algorithm based on multi-block coordinated single-scale Retinex. Different from traditional Retinex algorithms that use the global statistic to obtain dynamic truncation values, the proposed algorithm first divides the image into several sub-blocks to calculate dynamic truncation values suitable for different areas with different concentrations of fog. Then, the dynamic range of detail information is adjusted with these dynamic truncation values to obtain multiple locally optimal images. Finally, the final enhancement image is calculated by fusing multiple optimal local images. This strategy enables the enhancement of detail in each area of a foggy image. The experimental results show that the proposed algorithm can effectively remove the non-uniform fog and ensure that the brightness of defogged image is kept within a range suitable for human eyes.