论文部分内容阅读
雾霾天气下采集到的退化含噪图像模糊不清、对比度较低;而使用传统基于双边滤波的去雾方法得到的图像偏暗,效果有限。针对这些问题,提出了一种新的基于二次滤波的算法,实现雾霾天气下交通图像去雾处理;利用双边滤波对含雾图像的暗通道图像进行第一次滤波,用引导滤波对图像的透射率粗估计进行二次滤波优化。根据降质模型对含雾图像进行复原,进而得到去雾后的图像。实验效果证明,与传统方法相比,得到的去雾图像与真实场景亮度更加相似,色彩饱和度较好,图像质量较高。
The degraded and noisy images collected in haze weather are blurred and the contrast is low. However, the images obtained by the traditional de-fogging method based on bilateral filtering are dimmed with limited effect. Aiming at these problems, a new algorithm based on quadratic filtering is proposed to realize the traffic image de-fogging in foggy haze. The bilateral filtering is used to filter the dark channel image with foggy image for the first time, The rough estimate of the transmittance for the second pass filter optimization. According to the degraded model, the fog-containing image is restored, and the defogged image is obtained. Experimental results show that, compared with the traditional method, the obtained fog-removing image is more similar to the real scene brightness, the color saturation is better and the image quality is higher.