基于颜色衰减先验和视觉显著性的水下图像增强算法

Underwater image enhancement algorithm based on color attenuation prior and visual saliency

针对水下拍摄的图片存在颜色失真、细节和边缘模糊等特点,提出了一种基于颜色衰减先验的水下图像增强算法。首先在计算暗通道函数时,用最小值滤波去噪。然后,对图片进行显著图处理,利用颜色先验法则完成深度估计。此滤波方法不仅能降噪,还可以防止颜色失真。最后,基于模型简化获得复原的图片,将其进行伽马变换进行校正,实现柔性去雾。实验结果表明,本文算法与几种典型的水下图像去雾算法相比,能够较好提高图像的清晰度和对比度,同时获得较好的图像颜色。

Imaging in the atmosphere presents the phenomenons of low contrast,low saturation and hue offset due to atmospheric particles such as haze and fog.The dehaze image based on dark channel prior presents the phenomena of halo effect and color distortion in sky region.In view of the characteristics of color distortion,detail and edge blur of pictures taken underwater,an underwater image enhancement algorithm based on color attenuation prior was proposed.First,when calculated the dark channel function,the minimum value filter was used to denoise.Minimum value filtering is a relatively conservative image processing method,which can be simply filtered.Then,the image was processed for saliency map,and the depth estimation was completed using the color prior rule.This filtering method could not only reduce noise,but also prevented color distortion.Finally,the simplified atmospheric scattering model and tone mapping are used to get the restored image.It corrected by gamma transformation to achieve flexible defogging.Experimental results show that compared with several typical underwater image defogging algorithms,the algorithm in this paper can improve the clarity and contrast of the image,and at the same time obtain better image color.