基于物理模型的雾天图像复原新方法

由于雾天场景的能见度很低,因此为了保证视频监控系统的正常工作,需要对视频图像进行去雾处理。根据光学原理,雾天条件下场景的能见度下降是与场景深度呈指数关系的,鉴于现有的基于物理模型方法的去雾效果不够理想,因此提出了一种新的基于物理模型的图像复原方法,该方法首先对雾天场景的光学成像建模;然后借助于一张晴天和一张雾天场景的参考图像,计算出场景各点的深度比关系,最后利用深度关系复原雾天图像或雾天视频。实验结果证明,该方法是有效的和实用的。

A Novel Physics based Method for Restoration of Foggy Day Images

Scene visibility is very low in foggy days. We need to defog the surveillance video to make sure the intelligent visual surveillance system work normally. According to optics theory, the reduction of scene visibility is exponential to the scene depth. The defog effect of existing model-based methods are not good enough. In this paper, a new physics-based method of image restoration is presented. This method models scene points in foggy day firstly. Then the scene depth is calculated for two images which are captured in clear day and foggy day respectively. Image or video taken in foggy day is restored using depth information finally. The experiments demonstrate the effectiveness and practicality of this method.