一种结合双区域滤波和图像融合的单幅图像去雾算法

张小刚; 唐美玲; 陈华; 汤红忠

doi:10.3724/SP.J.1004.2014.01733

一种结合双区域滤波和图像融合的单幅图像去雾算法

doi: 10.3724/SP.J.1004.2014.01733

张小刚¹,
唐美玲¹,
陈华^1,2, ,,
汤红忠^1,3

1.
湖南大学电气与信息工程学院长沙 410082;
2.
湖南大学信息科学与工程学院长沙 410082;
3.
湘潭大学信息工程学院湘潭 411105

基金项目:

国家自然科学基金（61174050，61203016）资助

详细信息

作者简介:
张小刚湖南大学电气与信息工程学院教授. 主要研究方向为工业窑炉过程控制与模式识别.E-mail：zhangxiaogang@126.com

通讯作者:
陈华湖南大学信息科学与工程学院讲师. 主要研究方向为图像处理与模式识别.E-mail：anneychen@126.com

计量
- 文章访问数: 2388
- HTML全文浏览量: 161
- PDF下载量: 1005
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-17
- 修回日期: 2013-12-09
- 刊出日期: 2014-08-20

A Dehazing Method in Single Image Based on Double-area Filter and Image Fusion

1.
College of Electrical and Information Engineering, Hunan University, Changsha 410082;
2.
School of Information Science and Engineering, Hunan University, Changsha 410082;
3.
College of Information Engineering, Xiangtan University, Xiangtan 411105

Funds:

Supported by National Natural Science Foundation of China (61174050, 61203016)

摘要

摘要: 基于大气散射物理模型和暗原色先验原理，提出一种结合双区域滤波和图像融合的单幅图像去雾算法.首先在计算暗通道函数时，定义了一类暗区域对图像边缘的低强度像素点进行描述，该区域像素点的暗原色中值取其三原色通道的最小值，以代替原来的中值滤波运算值.此滤波方法不仅能有效去除Halo效应，而且避免了黑斑效应；然后基于大气散射物理模型定义一种伪去雾图，将其与原去雾图进行像素级融合对原图进行色度校正，实现了柔性去雾，改善了现有方法易出现过去雾的缺陷.实验结果表明，该算法去雾后图像具有较好清晰度及色彩恢复度，去雾鲁棒性强.在大雾和图像色彩失真严重的情况下，仍可有效恢复图像.
- 暗原色先验 /
- 双区域滤波 /
- 图像融合 /
- 去雾
Abstract: A dehazing method based on double-regional filter and image fusion is proposed based on the atmospheric scattering model and dark channel prior principle. Firstly, a dark region is defined to describe the low intensity pixel of the image's edge area when the median filter is adopted to calculate the dark channel transmission. The minimum value of the color (RGB) channels are assigned to the dark channel in dark region pixels instead of its median. This method not only removes the halo effect but also avoids black spot. On the other hand, a pseudo-dehazed image based on the atmospheric scattering model is proposed to solve the over-defogging problem. The defect of over-defogging can be cut down by the pixels fusion between the original dehazed image and the pseudo-dehazed image. Experiments show that the dehazing images with the proposed method in this paper have better sharpness, color restore degrees and robustness, even on the dense fog and color distortion.
- Dark channel prior /
- double-regional filter /
- image fusion /
- dehazing

HTML全文

参考文献(19)

[1]	Shwartz S, Namer E, Schechner Y Y. Blind haze separation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE, 2006. 1984-1991
[2]	[2] Namer E, Schechner Y Y. Advanced visibility improvement based on polarization filtered images. In: Proceedings of IEEE Conference on Polarization Science and Remote Sensing. Washington D.C., USA: IEEE, 2005. 36-45
[3]	[3] Schechner Y Y, Narasimhan S G, Nayar S K. Instant dehazing of images using polarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE, 2001. 325-332
[4]	[4] Schechner Y Y, Narasimhan S G, Nayar S K. Polarization-based vision through haze. Applied Optics, 2003, 42(3): 511-525
[5]	[5] Oakley J P, Satherley B L. Improving image quality in poor visibility conditions using a physical model for contrast degradation. IEEE Transactions on Image Processing, 1998, 7(2): 167-179
[6]	[6] Narasimhan S G, Nayar S K. Vision and the atmosphere. International Journal of Computer Vision, 2002, 48(3): 233-254
[7]	[7] Narasimhan S G, Nayar S K. Chromatic framework for vision in bad weather. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2000. 598-605
[8]	[8] Tan R T. Visibility in bad weather from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorgae, USA: IEEE, 2008. 23-28
[9]	[9] Fattal R. Single image dehazing. ACM Transactions on Graphics, 2008, 27(3): 1-9
[10]	He Kai-Ming, Sun Jian, Tang Xiao-Ou. Single image haze removal using dark channel prior. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE, 2009. 1956-1963
[11]	He Kai-Ming, Sun Jian, Tang Xiao-Ou. Single image haze removal using dark channel prior. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353
[12]	Xu H R, Guo J M, Liu Q, Ye L L. Fast image dehazing using improved dark channel prior. In: Proceedings of the IEEE International Conference on Information Science and Technology. Hubei, China: IEEE, 2012. 663-667
[13]	Yu Jing, Li Da-Peng, Liao Qing-Min. Physics-based fast single image fog removal. Acta Automatica Sinica, 2011, 37(2): 143-149(禹晶, 李大鹏, 廖庆敏. 基于物理模型的快速单幅图像去雾方法. 自动化学报, 2011, 37(2): 143-149)
[14]	Gibson K B, Vo D T, Nguyen T Q. An investigation of dehazing effects on image and video coding. IEEE Transactions on Image Processing, 2012, 21(2): 662-673
[15]	Narasimhan S G, Nayar S K. Removing weather effects from monochrome images. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE, 2001. 186-193
[16]	Narasimhan S G, Nayar S K. Contrast restoration of weather degraded images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6): 713-724
[17]	Burt P J, Kolczynski R J. Enhanced image capture through fusion. In: Proceedings of the IEEE Computer on Computer Vision, Berlin, Germany: IEEE, 1993. 173-182
[18]	He Kai-Ming, Sun Jian, Tang Xiao-Ou. Guided image filtering. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409
[19]	Li Da-Peng, Yu Jing, Xiao Chuang-Bai. No-reference quality assessment method for defogged images. Journal of Image and Graphics, 2011, 16(9): 1753-1757(李大鹏, 禹晶, 肖创柏. 图像去雾的无参考客观质量评测方法. 中国图象图形学报, 2011, 16(9): 1753-1757)