摘要
针对He的暗原色去雾算法对明亮区域失效,以及去雾后图像存在的块状效应以及Halo现象,提出了一种基于暗原色先验的改进去雾方法。算法通过引进容差参数和调整透射率因子来对透射率估计低的部分进行透射率增强以避免去雾后图像出现色彩失真,并采用四叉树方法求大气光值,提高了大气光值的准确率。实验结果表明,文章去雾算法切实可行,去雾结果消除了He的暗原色去雾的颜色失真问题,并通过图像客观评价指标定量分析证明文章算法去雾效果优于暗原色先验算法。
In the light of the dark channel fogging algorithm for He is invalid for bright area,and the bulk effect and Halo phenomenon in the image after fog removal.An improved fogging method based on dark original color prior is proposed in the paper.By introducing the tolerance parameter and adjusting the transmittance factor,the algorithm enhances the transmittance of the low estimated transmittance fraction to avoid the color distortion of the image after fog removal,The four forked tree method is used to calculate the atmospheric light value,and the accuracy of atmospheric light is improved.The experimental results show that the fogging algorithm is feasible,and the fog elimination results from the color distortion of the dark original color removal of He.Through the quantitative analysis of the objective evaluation index of the image,it is proved that the effect of the algorithm is better than the dark original color prior algorithm.
作者
王鹏
郭中华
Wang Peng;Guo Zhonghua(School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750000, China;Ningxia Key Laboratory of Intelligent Sensing for Desert Information Chengdu Kaitian Electronic Co. , Ltd. , 750000, China)
出处
《国外电子测量技术》
2018年第8期44-47,共4页
Foreign Electronic Measurement Technology
关键词
暗原色先验
图像去雾
容差
haze removal
dark channel prior
tolerance
