融合改进暗通道和Retinex的遥感影像去雾增强算法

Remote Sensing Image Defogging and Enhancement Algorithm Based on Improved Dark Channel and Retinex

针对云、雾、霾条件导致的遥感影像饱和度低,色彩失真,细节模糊等问题。提出一种融合改进暗通道和Retinex的遥感影像去雾增强算法。首先,采用改进的暗通道先验方法对雾度分布不均的有雾影像进行复原;其次,将复原处理后的影像作为单尺度Retinex算法的原始输入图像,使影像更加清晰,细节更加明显,更加符合人类视觉特性。通过主观评价和平均梯度、均方误差和信息熵等影像质量评价指标验证了文章算法的有效性。

Aimed at the problems of low saturation,color distortion,and blurred details of remote sensing images caused by cloud,fog,and haze conditions,a remote sensing image defogging and enhancement algorithm combining improved dark channel and Retinex is proposed.First,the improved dark channel prior method is used to restore the foggy image with uneven haze distribution;secondly,the restored image is used as the original input image of the SSR algorithm to make the image clearer,more obvious in detail,and more in line with human visual characteristics.Through subjective evaluation and image quality evaluation indicators such as average gradient,mean square error,and information entropy,the effectiveness of this algorithm is verified.