雾霾退化图像场景再现新算法

doi:10.3969/j.issn.1001-2400.2013.05.016

J4 ›› 2013, Vol. 40 ›› Issue (5): 99-106.doi: 10.3969/j.issn.1001-2400.2013.05.016

雾霾退化图像场景再现新算法

李权合;查宇飞;熊磊;毕笃彦

(空军工程大学航空航天工程学院，陕西西安 710038)

收稿日期:2012-06-26 出版日期:2013-10-20 发布日期:2013-11-27
通讯作者: 李权合
作者简介:李权合(1987-)，男，空军工程大学博士研究生，E-mail: liquanhe.ning666@163.com．
基金资助:
国家自然科学基金资助项目(61175029, 61203268, 61202339)

Novel method for haze degraded image scene rendition

LI Quanhe;ZHA Yufei;XIONG Lei;BI Duyan

(Inst. of Aeronautics and Astronautics, Air Force Eng. Univ., Xi'an 710038， China)

Received:2012-06-26 Online:2013-10-20 Published:2013-11-27
Contact: LI Quanhe

摘要/Abstract

摘要：

为了快速有效地去雾，分析了单色大气散射模型和Retinex模型的对等关系，并从变分Retinex的角度提出了单色大气散射模型的求解新方法．求解过程首先构造了大气传递图的变分模型，将其估计问题转换为二次规划问题; 其次，在3个颜色通道分别求解大气传递图，并反解单色大气散射模型得到反射图像; 最后，依据颜色恒常性理论对去雾结果进行色彩复原．实验结果表明，新算法能够快速有效地去除浓雾．

关键词: 图像去雾, 图像复原, 图像增强, 大气散射模型, Retinex模型, 二次规划

Abstract:

To remove haze rapidly and effectively, equivalence between Retinex model and Monochrome Atmospheric Scattering model is explored, and then a novel solution for the Monochrome Atmospheric Scattering model is proposed based on the variational Retinex. Firstly, a variational model for the atmosphere transmission map is constructed, so the transmission map estimation problem can be formulated as a Quadratic Programming optimization problem. Secondly, we calculate the transmission map and resolve the Monochrome Atmospheric Scattering model in each channel to get the Reflectance image; Finally, the Color Constancy is adopted to restore the color of the dehazed image. Experimental results show that the proposed method could remove haze rapidly and effectively, and has some advantages over other algorithms.

Key words: image defog, image restoration, image enhancement, atmosphere scattering model, retinex model, quadratic programming

李权合;查宇飞;熊磊;毕笃彦. 雾霾退化图像场景再现新算法[J]. J4, 2013, 40(5): 99-106.

LI Quanhe;ZHA Yufei;XIONG Lei;BI Duyan. Novel method for haze degraded image scene rendition[J]. J4, 2013, 40(5): 99-106.

参考文献

［1］ Tan R T. Visibility in Bad Weather from a Single Image［C］//Proceedings of 26th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2008: 1-8.
［2］ Fattal R. Single Image Dehazing ［J］. ACM Transcations on Graph, 2008: 27(3): 1-9.
［3］ He Kaiming, Sun Jian, Tang Xiaoou. Single Image Haze Removal Using Dark Channel Prior ［C］//Proceedings of 27th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2009: 1956-1963.
［4］方帅, 王勇, 曹洋, 等. 单幅雾天图像复原［J］. 电子学报, 2010, 38(10): 2279-2284.
Fang Shuai, Wang Yong, Cao Yang, et al. Restoration of Image Degraded by Haze ［J］. Acta Electronic Sinica, 2010, 38(10): 2279-2284.
［5］ Jobson D J, Rahman Z, Woodell G A. A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes ［J］. IEEE Transcations on Image Processing, 1997, 6(7): 965-976.
［6］ Kimmel R, Elad M, Shaked D, et al. A Variational Framework for Retinex ［J］. International Journal of Computer Vision, 2003, 52(1): 7-23.
［7］马时平, 张明, 毕笃彦, 等. 一种细节保持的Retinex图像增强算法［J］. 西安电子科技大学学报, 2010, 37(3): 541-546.
Ma Shiping, Zhang Ming, Bi Duyan, et al. Novel Detail Preserving Retinex Algorithm for Image Enhancement［J］. Journal of Xidian University, 2010, 37(3): 541-546.
［8］ Narasimhan S G, Nayar S K. Contrast Restoration of Weather Degraded Images ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6): 713-724.
［9］ Li Cheng, Gao Shan, Bi Duyan. A Modified Image Enhancement Algorithm Based on Color Constancy ［J］. Chinese Optical Letter, 2009, 7(9): 783-788.
［10］ Tarel J P, Hauti`ere N. Fast Visibility Restoration from a Single Color or Gray Level Image ［C］//Proceedings of International Conference on Computer Vision(ICCV'09). Piscataway: IEEE, 2009: 193-201.
［11］李权合, 毕笃彦, 何林远. 退化过程模拟模型及其在图像增强中的应用［J］. 西安电子科技大学学报, 2011, 38(6): 185-192.
Li Quanhe, Bi Duyan, He Linyuan. Degradation Process Simulation Model and Its Application in Image Enhancement ［J］. Journal of Xidian University, 2011, 38(6): 185-192.
［12］高雪妮, 玉振明, 张军, 等. 基于多级分块迭代法的不同聚焦图像融合［J］. 电子学报, 2011, 39(3): 690-694.
Gao Xueni, Yu Zhenming, Zhang Jun, et al. Multi-Focus Image Fusion Based on Multi-Level and Iterative Method ［J］. Acta Electronic Sinica, 2011, 39(3): 690-694.

[1]	孙彦景,魏力,张年龙,云霄,董锴文,葛敏,程小舟,侯晓峰. 联合DD-GAN和全局特征的井下人员重识别方法[J]. 西安电子科技大学学报, 2021, 48(5): 201-211.
[2]	王俊祥,黄霖,张影,倪江群,林朗. 低复杂度的增强图像来源检测算法[J]. 西安电子科技大学学报, 2021, 48(1): 96-106.
[3]	刘志强,张铭津,池源,李云松. 一种深度学习的硬件木马检测算法[J]. 西安电子科技大学学报, 2019, 46(6): 37-45.
[4]	暴婉婷,王俊平,魏书蕾,李艳波,周勇. 天空区域分割修正的图像去雾新算法[J]. 西安电子科技大学学报, 2019, 46(2): 164-169.
[5]	胡妍;王柯俨;许宁;李云松;张闪闪. 利用分割中值滤波和透射率补偿的图像去雾[J]. 西安电子科技大学学报, 2018, 45(4): 99-105.
[6]	冯玉颖;王俊平;马塾亮;李超;伍尧. COPLIP新模型及其图像增强新算法[J]. 西安电子科技大学学报, 2018, 45(1): 66-71.
[7]	汪云飞;刘华伟;赵搏欣. 融合超像素的黄金暗通道单幅图像去雾方法[J]. 西安电子科技大学学报, 2017, 44(5): 147-152.
[8]	虞泓波;冯大政;解虎. 采用序列二次规划求解的稳健波束形成新算法[J]. 西安电子科技大学学报, 2016, 43(2): 41-45+204.
[9]	刘巧红;李斌;林敏. 非凸混合总变分图像盲复原[J]. 西安电子科技大学学报, 2016, 43(2): 120-125.
[10]	虞泓波;冯大政;解虎. MIMO雷达迭代降维稳健波束形成方法[J]. J4, 2016, 43(1): 30-35.
[11]	张明;白松浩. 利用上下边界估计的图像增强方法[J]. J4, 2015, 42(1): 149-154.
[12]	崔华;周婷洁;郭璐;袁超;宋焕生. 改进的偏微分扩散方程图像增强方法[J]. J4, 2014, 41(6): 195-198.
[13]	吴炜;郑成林;张莹莹;周寿桓. 广义非局部均值和自相似性的超分辨率算法[J]. J4, 2014, 41(4): 100-107.
[14]	李锦;王俊平;万国挺;李紫阳;许丹;曹洪花;张广燕. 一种结合直方图均衡化和MSRCR的图像增强新算法[J]. J4, 2014, 41(3): 103-109.
[15]	张广燕;王俊平;汪松;曹洪花;许丹;李锦;李长江. 一种SLIP模型的图像增强新算法[J]. J4, 2014, 41(1): 105-109+169.

雾霾退化图像场景再现新算法

Novel method for haze degraded image scene rendition

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0