基于暗原色先验的区域自适应图像去雾方法  

Regional adaptive image haze removal method based on dark channel prior

作　　者：刘冬冬[1] 陈莹[1] 

机构地区：[1]江南大学轻工过程先进控制教育部重点实验室,江苏无锡214000

出　　处：《计算机工程与应用》2016年第7期166-170,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61104213);江苏省自然科学基金(No.BK2011146)

摘　　要：在雾霾天气条件下,由于大气粒子的散射作用导致拍摄的图像严重退化。针对这一问题,提出一种简单有效的单幅图像去雾算法。设计晕光估计算子检测出晕光区域,在暗原色先验条件下,根据晕光估计值获取区域自适应融合权值,进而在不同区域采用不同的加权方式融合基于单像素估算的透射率与基于块状区域的透射率以获取精确透射率,有效地消除了晕光效应;最后增加参数限制透射率过低,保护了天空区域。实验表明该算法复原的图像清晰自然,尤其是在前景与背景的边缘处及天空区域能够达到很好的去雾效果。Images taken in foggy weather are seriously degraded due to the scattering of atmospheric particles. A simple and effective haze removal algorithm from a single image is proposed. Firstly, a halo evaluator is designed to detect halo zone. Then, precise transmission rat is obtained by weight fusion of single pixel based rate and block area based one, both taking the prior of dark channel. The weight is determined according to the halo evaluator. Finally, a parameter is added for image recovery to limit the low transmission and to protect the sky area. Experiments show that compared with other methods, more vivid and natural images can be recovered by the proposed method, especially at the edges of the foreground and the background and in the sky area.

关 键 词：去雾 暗原色先验 加权 透射率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]