A Novel Single Image Dehazing Method

被引：0

作者：

Yang, Yanjing ^{[1
]}

Fu, Zhizhong ^{[1
]}

Li, Xinyu ^{[1
]}

Shu, Chang ^{[1
]}

Li, Xiaofeng ^{[1
]}

机构：

[1] UESTC, Sch Commun & Informat Engn, Chengdu, Sichuan, Peoples R China

来源：

2013 INTERNATIONAL CONFERENCE ON COMPUTATIONAL PROBLEM-SOLVING (ICCP) | 2013年

关键词：

image dehazing; image enhancement; image restoration; dark channel prior; guided filter; wavelet transform;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, a novel single image dehazing method based on dark channel prior is proposed. The original dark channel prior based method employs soft matting algorithm to refine the transmission map, which is time-consuming. Recently, guided filter, which is time-saving, has been introduced to perform the same function as soft matting. In our work, based on the observation that haze mainly has an effect on the low-frequency component of an image, by employing guided filter instead of soft matting algorithm to refine the transmission map of the low-frequency component of haze image extracted by Haar wavelet transform, the runtime cost is dramatically decreased. Experimental results show that the proposed algorithm restores the image faster while maintaining relatively excellent performance compared with the Dark Channel Prior with Guided Filter based method, which allows this algorithm to be applied to the real-time applications such as obstacle detection and surveillance.

引用

页码：275 / 278

页数：4

共 12 条

[1] [Anonymous], CVPR
[2] [Anonymous], 2010, ECCV
[3] [Anonymous], 1976, OPTICS ATMOSPHERE SC
[4] [Anonymous], 2003, IEEE WORKSH COL PHOT
[5] [Anonymous], 2006, P IEEE COMP SOC C CO
[6] Single image dehazing
Fattal, Raanan
[J]. ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (03):
[7] He KM, 2009, PROC CVPR IEEE, P1956, DOI [10.1109/CVPR.2009.5206515, 10.1109/CVPRW.2009.5206515]
[8] Narasimhan S. G., 2002, P ECCV
[9] Narasimhan S. G., 2003, IEEE T PAMI, V25, P731
[10] Nayar S. K., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P820, DOI 10.1109/ICCV.1999.790306

← 1 2 →