针对经典的暗通道先验算法对图像去雾存在出现色斑、“白边”和细节缺失的问题,本文采用导向滤波与K阈值相结合的方法进行优化,并利用图像质量评估方法对优化后的算法进行测试和综合分析。经实验结果验证,优化后的算法比原有算法去雾效果更佳。
Abstract
In view of the classic dark channel prior algorithm for image to fog will exist a splash and appear the "white",the problem of the missing details,the article adopts oriented filtering and K threshold method to optimize the combination,and use the image quality evaluation method for the optimized algorithm for testing and comprehensive analysis.The optimized algorithm are verified through the experiment to fog effect is better than the original algorithm.
关键词
暗通道先验算法 /
导向滤波 /
K阈值
Key words
dark channel prior algorithm /
guided filtering /
K threshold
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 刘一贤.面向交通安全的去雾图像清晰化技术研究[D].绵阳:西南科技大学,2018.
[2] Lai Y,Wang Q,Chen R.Improved Single Image Haze Removal for Intelligent Driving[J].Pattern Recognition Image Anal,2020,30(1):523-529.
[3] 魏然然,詹伟达,朱德鹏,等.改进多尺度的Retinex红外图像增强[J].液晶与显示,2021,36(3):465-474.
[4] CHOIL K,YOU J,BOVIK A C.Referenceless prediction of perceptual fog density and perceptual image defogging[J].IEEE Transactions on Image Processing,2015,24(11):3888-3891.
[5] Vaz Eduardo,Kyriakidis Jordan.Dark channels in resonant tunneling transport through artificial atoms[J].The Journal of Chemical Physics,2008,129(2).
[6] KHe,J Sun,X Tang.Single Image Haze Removal Using Dark Channel Prior[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[7] HE K M,SUN J,TANG X O.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[8] 高陈强,李佩.引导滤波和三维块匹配结合的红外图像去噪[J].重庆邮电大学学报(自然科学版),2016,28(2):150-155.
基金
*国家自然科学基金资助(61901347)。