改进的暗通道先验快速图像去雾算法

doi:10.11772/j.issn.1001-9081.2017.08.2324

计算机应用 ›› 2017, Vol. 37 ›› Issue (8): 2324-2328.DOI: 10.11772/j.issn.1001-9081.2017.08.2324

• 计算机视觉与虚拟现实 • 上一篇下一篇

改进的暗通道先验快速图像去雾算法

张江鑫, 周佳波, 孟利民

浙江工业大学信息工程学院, 杭州 310023

收稿日期:2016-12-23 修回日期:2017-02-03 出版日期:2017-08-10 发布日期:2017-08-12
通讯作者: 周佳波
作者简介:张江鑫(1964-),男,浙江嘉兴人,副教授,硕士,主要研究方向:数字图像处理、多媒体数字通信;周佳波(1990-),男,浙江杭州人,硕士研究生,主要研究方向:数字图像处理;孟利民(1963-),女,浙江金华人,教授,博士,主要研究方向:数字图像处理、无线通信。
基金资助:
国家自然科学基金资助项目（61372087）。

Improved fast image defogging algorithm based on dark channel prior

ZHANG Jiangxin, ZHOU Jiabo, MENG Limin

College of Information Engineering, Zhejiang University of Technology, Hangzhou Zhejiang 310023, China

Received:2016-12-23 Revised:2017-02-03 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61372087).

摘要/Abstract

摘要： 针对暗通道去雾算法复杂度过高的问题，提出一种基于暗通道的快速去雾算法。首先对图像分块处理，提高求取暗通道值的速度；接着采用线性插值算法平滑处理，消除块状效应；然后根据暗通道先验求得透射率；最终利用大气散射模型得到清晰无雾图像。实验结果证明，在保证良好去雾效果的前提下，相比原暗通道算法，所提算法复杂度被有效降低，去雾所需时间也降为原来的1/10左右，达到准实时。

关键词: 去雾算法, 暗通道, 导向滤波, 分块, 线性插值

Abstract: Due to high complexity of dark channel prior defogging algorithm, a fast defogging algorithm based on dark channel prior was proposed. Firstly, the computing of the dark channel map was accelerated by blocking the image. Secondly, the block effect was eliminated by using the linear interpolation algorithm to smoothing. Then, the transmission map was acquired by dark channel prior. Finally, a clear and haze-free image would be gotten from the atmospheric scattering model. The experimental results show that the defogging effect of the proposed algorithm can be as good as the original defogging algorithm but the complexity can be reduced effectively. The proposed algorithm needs time about one-tenth of the original algorithm and reaches the requirement of near real-time.

Key words: defogging algorithm, dark channel, guided filtering, blocking, linear interpolation

中图分类号:

TP391.413

张江鑫, 周佳波, 孟利民. 改进的暗通道先验快速图像去雾算法[J]. 计算机应用, 2017, 37(8): 2324-2328.

ZHANG Jiangxin, ZHOU Jiabo, MENG Limin. Improved fast image defogging algorithm based on dark channel prior[J]. Journal of Computer Applications, 2017, 37(8): 2324-2328.

参考文献

[1] 徐同莹,彭定明,王卫星.改进的直方图均衡化算法[J].兵工自动化,2006,25(7):58-59.(XU T Y, PENG D M, WANG W X. Improved histogram equalization algorithm[J]. Ordnance Industry Automation, 2006, 25(7):58-59.)
[2] 张新明,沈兰荪.基于小波的同态滤波器用于图像对比度增强[J].电子学报,2001,29(4):531-533.(ZHANG X M, SHEN L S. Image contrast enhanchment by wavelet based homomorphic filtering[J]. Acta Electronica Sinica, 2001, 29(4):531-533.)
[3] RAHMAN Z U, JOBSON D J, WOODELL G A. Retinex processing for automatic image enhancement[J]. Journal of Electronic Imaging, 2004, 13(1):100-110.
[4] TAN R T. Visibility in bad weather from a single image[C]//CVPR 2008:Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2008:1-8.
[5] TAREL J P, HAUTIERE N. Fast visibility restoration from a single color or gray level image[C]//Proceedings of the 2009 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2009:2201-2208.
[6] FATTAL R. Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27(3):Article No. 72.
[7] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2011:1956-1963.
[8] 马江峰,杨忠斌,毕笃彦,等.快速图像去雾新方法[J].计算机应用,2012,32(6):1567-1569.(MA J F, YANG Z B, BI D Y, et al. New method for fast image dehazing[J]. Journal of Computer Applications, 2012, 32(6):1567-1569.)
[9] 杨燕,王帆,白海平.基于相对透射率估计的快速图像去雾算法[J].计算机应用,2016,36(3):806-810.(YANG Y, WANG F, BAI H P. Fast image dehazing algorithm based on relative transmittance estimation[J]. Journal of Computer Applications, 2016, 36(3):806-810.)
[10] 王雅婷,冯子亮.基于暗原色先验的单幅图像快速去雾算法[J].计算机应用,2016,36(12):3406-3410.(WANG Y T, FENG Z L. Single image fast dehazing method based on dark channel prior[J]. Journal of Computer Applications, 2016, 36(12):3406-3410.)
[11] 孙抗,汪渤,周志强,等.基于双边滤波的实时图像去雾技术研究[J].北京理工大学学报,2011,31(7):810-813.(SUN K, WANG B, ZHOU Z Q, et al. Realtime image haze removal using bilateral filter[J]. Transactions of Beijing Institute of Technology, 2011, 31(7):810-813.)
[12] HE K, SUN J, TANG X. Guided image filtering[J]. IEEE Trans-actions on Software Engineering, 2013, 35(6):1397-1409.
[13] 孙小明,孙俊喜,赵立荣,等.暗原色先验单幅图像去雾改进算法[J].中国图象图形学报,2014,19(3):381-385.(SUN X M, SUN J X, ZHAO L R, et al. Improved algorithm for single iamge haze removing using dark channel prior[J]. Journal of Image and Graphics, 2014, 19(3):381-385.)
[14] NARASIMHAN S G, NAYAR S K. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3):233-254.
[15] NARASIMHAN S G, NAYAR S K. Chromatic framework for vision in bad weather[C]//Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2000:598-605.
[16] HORE A, ZIOU D. Image quality metrics:PSNR vs. SSIM[C]//Proceedings of the 2010 International Conference on Pattern Recognition. Piscataway, NJ:IEEE, 2010:2366-2369.
[17] HAUTIERE N, TAREL J P, AUBERT D, et al. Blind contrast enhancement assessment by gradient rationing at visible edges[J]. Image Analysis and Stereology, 2008, 27(2):87-95.

改进的暗通道先验快速图像去雾算法

Improved fast image defogging algorithm based on dark channel prior

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王云飞, 王园宇. 基于Msmall-Patch训练的夜晚单幅图像去雾算法——MP-CGAN[J]. 计算机应用, 2020, 40(3): 865-871.
[2]	李南云, 王旭光, 吴华强, 何青林. 基于灰度塔评分的匹配模型构建在无人机网络视频拼接中的应用[J]. 计算机应用, 2019, 39(5): 1480-1484.
[3]	娄梦莹, 袁丽莎, 刘娅琴, 万雪梅, 杨丰. 基于自适应融合的手掌静脉增强方法[J]. 计算机应用, 2019, 39(4): 1176-1182.
[4]	汪汉新, 洪思琴. 基于环分块的能耗均衡分簇路由算法[J]. 计算机应用, 2019, 39(1): 251-255.
[5]	王青松, 葛慧. Winnowing指纹串匹配的重复数据删除算法[J]. 计算机应用, 2018, 38(3): 677-681.
[6]	张浩, 窦奇伟, 栾桂凯, 姚绍文, 周维. 基于空洞卷积的快速背景自动更换[J]. 计算机应用, 2018, 38(2): 405-409.
[7]	周锋, 林楠, 陈小平. 基于六维线性插值的六自由度机械臂逆运动学方程求解方法[J]. 计算机应用, 2018, 38(2): 563-567.
[8]	杜秀丽, 张薇, 陈波. 基于波浪式矩阵置换的稀疏度均衡分块压缩感知算法[J]. 计算机应用, 2018, 38(12): 3541-3546.
[9]	韩李涛, 刘海龙, 孔巧丽, 阳凡林. 基于多核计算环境的地貌晕渲并行算法[J]. 计算机应用, 2017, 37(7): 1911-1915.
[10]	鲍振华, 康宝生, 张雷, 张婧. 基于草图局部几何不变矩的图像检索方法[J]. 计算机应用, 2017, 37(6): 1753-1758.
[11]	张洁玉. 基于图像分块的局部阈值二值化方法[J]. 计算机应用, 2017, 37(3): 827-831.
[12]	盛婷婷, 陈强, 孙权森. 基于暗通道原理从单幅遥感影像估计山脉高程的方法[J]. 计算机应用, 2017, 37(3): 839-843.
[13]	毛祥宇, 李为相, 丁雪梅. 基于天空分割的单幅图像去雾算法[J]. 计算机应用, 2017, 37(10): 2916-2920.
[14]	董宇飞, 杨燕, 曹碧婷. 基于导向图优化的单幅图像深度去雾算法[J]. 计算机应用, 2017, 37(1): 268-272.
[15]	张文达, 许悦雷, 倪嘉成, 马时平, 史鹤欢. 基于多尺度分块卷积神经网络的图像目标识别算法[J]. 计算机应用, 2016, 36(4): 1033-1038.