崔倩男,田小平,吴成茂.基于引导滤波改进的暗原色去雾算法[J].计算机科学,2018,45(5):285-290
基于引导滤波改进的暗原色去雾算法
Improved Algorithm of Haze Removal Based on Guided Filtering and Dark Channel Prior
投稿时间:2017-04-21  修订日期:2017-07-09
DOI:10.11896/j.issn.1002-137X.2018.05.049
中文关键词:  图像去雾,引导滤波,暗原色先验,透射率
英文关键词:Image dehazing,Guided filtering,Dark channel prior,Transmittance
基金项目:本文受国家自然科学基金重点项目(61136002),陕西省自然科学基金资助
作者单位E-mail
崔倩男 西安邮电大学电子工程学院 西安710121 cuiqiannan93@163.com 
田小平 西安邮电大学电子工程学院 西安710121  
吴成茂 西安邮电大学电子工程学院 西安710121  
摘要点击次数: 324
全文下载次数: 214
中文摘要:
      针对雾天条件下户外图像存在清晰度降低和色彩偏移的现象,提出一种基于引导滤波改进的暗原色去雾算法。首先,采用暗原色先验理论估计出粗透射率,通过灰度的引导图像对粗透射率进行引导滤波的细化处理;然后,对图像中暗原色失效的区域进行判定,利用调整因子对该区域的透射率进行修正;最后,通过大气散射模型获得复原图像,并对HSI颜色空间进行亮度均衡化,使复原图像得到增强。实验结果表明,该算法能复原出细节突出、色彩自然的图像,具有较高的运算效率。
英文摘要:
      Aiming at the bad influence on outdoor images in fog weather such as decrease of definition and color deviation problem,an improved algorithm of haze removal based on guided filtering and dark channel prior was proposed.Firstly,the rough transmittance is estimated through the dark channel prior,and then the guided filter is adopted to refine the transmission by using the grayscale image as the guidance images.Next,the failure areas of dark channel prior are detected and adjustment factor is used to modify the transmittance.At last,the restored image is obtained from atmospheric scattering model,and the HSI color space intensity equalization method is used to enhance the restored ima-ge.Experimental results show that the proposed algorithm can provide more detailed restored image with natural color effect and improve operational efficiency.
查看全文  查看/发表评论  下载PDF阅读器