结合颜色线和暗通道的遥感图像去雾

张峥; 李奇; 徐之海; 冯华君; 陈跃庭

doi:10.3788/OPE.20192701.0181

您当前的位置：

首页 >

文章列表页 >

结合颜色线和暗通道的遥感图像去雾

信息科学 | 更新时间：2020-08-13

- 结合颜色线和暗通道的遥感图像去雾
- Color-line and dark channel based dehazing for remote sensing images
- 光学精密工程 2019年27卷第1期页码：181-190
- 作者机构：
  
  浙江大学现代光学仪器国家重点实验室，浙江杭州 310027
- 作者简介：
  
  [ "张峥(1992-)，男，浙江台州人，博士研究生，2014年于浙江大学获得学士学位，主要从事图像质量评价、图像增强等方面的研究。Email:11430016@zju.edu.cn" ]
  [ "李奇(1973-)，男，江苏沛县人，教授，博士生导师，2004年于浙江大学获得博士学位，现为浙江大学光学成像工程研究所副所长，主要从事成像系统、遥感等方面的研究。Email: liqi@zju.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(61475135);民用航天预研项目
- DOI：10.3788/OPE.20192701.0181
  中图分类号： TN911.73
- 收稿日期：2018-06-08，
  
  录用日期：2018-8-16，
  
  纸质出版日期：2019-01-15
- 稿件说明：
移动端阅览
张峥, 李奇, 徐之海, 等. 结合颜色线和暗通道的遥感图像去雾[J]. 光学精密工程, 2019,27(1):181-190.

Zheng ZHANG, Qi LI, Zhi-hai XU, et al. Color-line and dark channel based dehazing for remote sensing images[J]. Optics and precision engineering, 2019, 27(1): 181-190.
张峥, 李奇, 徐之海, 等. 结合颜色线和暗通道的遥感图像去雾[J]. 光学精密工程, 2019,27(1):181-190. DOI： 10.3788/OPE.20192701.0181.

Zheng ZHANG, Qi LI, Zhi-hai XU, et al. Color-line and dark channel based dehazing for remote sensing images[J]. Optics and precision engineering, 2019, 27(1): 181-190. DOI： 10.3788/OPE.20192701.0181.

摘要

为了解决遥感图像中存在雾气引起图像可见度下降的问题，提出一种基于颜色线先验和暗通道先验的遥感图像去雾算法。针对颜色线先验对部分场景不适用的情况，提出一种基于最小二乘的透过率优化方法，通过计算先验可信度权重来加权融合颜色线先验和暗通道先验估计的透过率图，以获得更为准确的透过率分布。为了避免halo效应，在优化方程中加入梯度正则化约束。实验结果表明，本方法对透过率估计准确，重建结果清晰度提升明显。另外，该方法改善了客观评价指标，其灰度平均梯度(GMG)和信息熵(IE)平均值最高，取得了最佳的重建效果。

Abstract

A color-line and dark channel based dehazing algorithm was proposed to solve the problem of image contrast decreasing caused by haze in remote sensing images. In view of the deficiencies in the color-line a priori

a least squares based transmittance optimization method was proposed. In order to obtain a more accurate transmittance distribution

the transmissivity maps estimated by the color-line prior and the dark channel prior are fused by weight which is calculated by their credibility. A gradient regularization constraint was added to the optimization equation to avoid the halo effect. The experimental results show that the proposed method is accurate in estimating transmittance and the clarity of the reconstruction results is significantly improved. In addition

the objoctive evaluation index is improved as its Gray Mean Grads(GMG) and Information Entropy(IE) show the highest average value

which indicates that the proposed method has achieve the best reconstruction result among the state-of -art methods.

关键词

Keywords

references

陶叔银.基于大气物理特征的光学图像退化及补偿技术研究[D].杭州: 浙江大学, 2014. http://cdmd.cnki.com.cn/Article/CDMD-10335-1014269147.htm

TAO SH Y. Research on image degradation and recovery based on physical properties of atmosphere [D]. Hangzhou: Zhejiang University, 2004. (in Chinese)

NARASIMHAN S G, NAYAR S K. Vision and the atmosphere[J]. International Journal of Computer Vision , 2002, 48(3): 233-254.

RIZZI A, GATTA C, MARINI D. A new algorithm for unsupervised global and local color correction[J]. Pattern Recognition Letters , 2003, 24(11): 1663-1677.

TAN R T. Visibility in bad weather from a single image[C]. Computer Vision and Pattern Recognition , 2008. IEEE , 2008: 1-8. https://www.researchgate.net/publication/221362812_Visibility_in_bad_weather_from_a_single_image

陈志斌, 张超, 宋岩, 等.灰度拉伸Retinex在大动态范围烟雾图像增强中的应用[J].红外与激光工程, 2014, 43(9): 3146-3150.

CHEN ZH B, ZHANG CH, SONG Y, et al .. Application of Retinex with grayscale stretching in large dynamic range smoke image enhancement[J]. Infrared and Laser Engineering , 2014, 43(9): 3146-3150. (in Chinese)

FATTAL R. Single image dehazing[J]. ACM transactions on graphics (TOG) , 2008, 27(3): 72.

TAREL J P, HAUTIERE N. Fast visibility restoration from a single color or gray level image[C]. Computer Vision, 2009 IEEE 12th International Conference on. IEEE , 2009: 2201-2208. http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=5459251

HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE transactions on pattern analysis and machine intelligence , 2011, 33(12): 2341-2353.

MENG G, WANG Y, DUAN J, et al .. Efficient image dehazing with boundary constraint and contextual regularization[C]. Proceedings of the IEEE International Conference on Computer Vision . 2013: 617-624. https://www.researchgate.net/publication/262356211_Efficient_Image_Dehazing_with_Boundary_Constraint_and_Contextual_Regularization

BERMAN D, AVIDAN S. Non-local image dehazing[C]. Proceedings of the IEEE conference on computer vision and pattern recognition , 2016: 1674-1682. https://www.researchgate.net/publication/311610242_Non-local_Image_Dehazing

武昆, 韩广良, 杨航, 等.多尺度引导滤波及其在去雾中的应用[J].光学精密工程, 2017, 25(8): 2182-2194.

WU K, HAN G L, YANG H, et al .. Multi-scale guided filter and its application in image dehazing[J]. Opt. Precision Eng ., 2017, 25(8): 2182-2194. (in Chinese)

邓莉.针对明亮区域的自适应全局暗原色先验去雾[J].光学精密工程, 2016, 24(4): 892-901.

DENG L. Adaptive image dehazing for bright areas based on global dark channel prior[J]. Opt. Precision Eng ., 2016, 24(4): 892-901. (in Chinese)

吴斌, 付辉, 张红英.大气光幂雾图像的清晰度复原[J].光学精密工程, 2016, 24(8): 2018-2026.

WU B, FU H, ZHANG H Y. De-hazing of atmosphere veil haze images[J]. Opt. Precision Eng ., 2016, 24(8): 2018-2026. (in Chinese)

ALLARD É. Mémoire sur l′intensité et la portée des phares [M]. Impr. nationale, 1876.

ORCHARD M T, BOUMAN C A. Color quantization of images[J]. IEEE transactions on signal processing , 1991, 39(12): 2677-2690.

HE K, SUN J, TANG X. Guided image filtering[C]. European conference on computer vision. Springer Berlin Heidelberg , 2010: 1-14.

MARSAGLIA G. Choosing a point from the surface of a sphere[J]. The Annals of Mathematical Statistics , 1972, 43(2): 645-646.

FARBMAN Z, FATTEL R, LISCHINSKI D, et al .. Edge-preserving decompositions for multi-scale tone and detail manipulation[C]. ACM Transactions on Graphics (TOG). ACM , 2008, 27(3): 67-77 https://www.researchgate.net/publication/220184290_Edge-preserving_decompositions_for_multi-scale_tone_and_detail_manipulation

浏览量

177

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

频域特征蒸馏的双尺度融合图像去雾网络

改进暗通道先验的大幅面倾斜影像快速去雾

轻量级重参数化的遥感图像超分辨率重建网络设计

全局和局部特征融合的图像去雾

基于偏振度优化与大气光校正的图像去雾