摘要
为解决雾霾天气车载辅助安全系统中图像传感器所采集到的图像对比度低,颜色失真等问题,提出了基于改进的暗通道先验理论的图像增强方案。采用等间隔取样、去除亮度突变区域等方法,对图像大气光强值的估计进行改进,并通过分区域的方法优化透射率的计算。实验表明,该算法在实时性、颜色保真度、图像对比度等方面均优于其他算法。
In order to solve the problems that fog haze weather vehicle auxiliary safety system image sensor has low contrast and color distortion, an image enhancement method is proposed based on the improved dark channel prior theory. The image atmosphere intensity value estimation method is improved using interval sampling, removing brightness mutations area. And the transmittance calculating is optimized through region separating. Experimental results show that the proposed algorithm has better performance than other algorithms in real-time, color fidelity and picture contrast ratio.
出处
《激光与光电子学进展》
CSCD
北大核心
2016年第4期74-79,共6页
Laser & Optoelectronics Progress
基金
国家自然科学基金(51274118)
辽宁省科技攻关项目(2011229011)
关键词
图像处理
图像增强
雾霾
暗通道
等间隔区域
分区域
image processing
image enhancement
smog
dark channel
interval area
regional block
