基于多子块协同单尺度Retinex的浓雾图像增强

高原原; 胡海苗

doi:10.13700/j.bh.1001-5965.2018.0528

基于多子块协同单尺度Retinex的浓雾图像增强

doi: 10.13700/j.bh.1001-5965.2018.0528

高原原^1, ,,
胡海苗²

1.
中国电子科技集团公司信息科学研究院, 北京 100086
2.
北京航空航天大学计算机学院, 北京 100083

基金项目:

国家自然科学基金 61801448

详细信息

作者简介:
高原原女, 博士研究生, 工程师。主要研究方向:图像处理

胡海苗男, 副教授。主要研究方向:图像处理

通讯作者:
高原原. E-mail:gyy002005@163.com

中图分类号: TP391
计量
- 文章访问数: 599
- HTML全文浏览量: 73
- PDF下载量: 344
- 被引次数: 0
出版历程
- 收稿日期: 2018-09-06
- 录用日期: 2018-10-17
- 网络出版日期: 2019-05-20

Foggy image enhancement based on multi-block coordinated single-scale Retinex

GAO Yuanyuan^{1
, ,},
HU Haimiao²

1.
Information Sciences Academe, China Electronic Technology Group Corporation, Beijing 100086, China
2.
School of Computer Science and Engineering, Beihang University, Beijing 100083, China

Funds:

National Natural Science Foundation of China 61801448

More Information

Corresponding author: GAO Yuanyuan. E-mail: gyy002005@163.com

摘要

摘要:
针对现有算法增强雾气分布不均匀的浓雾图像效果不理想的问题，提出了一种基于多子块协同单尺度Retinex的浓雾图像增强算法。该算法不同于传统的利用全局统计量获取动态截断值的Retinex算法，首先将图像划分为多个子块，计算出适合不同浓度雾气的动态截断值；然后，利用动态截断值对高频细节信息进行动态范围调整，得到多幅局部最优的图像；最后，融合多幅局部最优图像生成高质量的结果，从而实现浓雾图像每个区域细节的增强。实验结果表明，所提算法能够有效去除不均匀浓雾，并保证去雾后图像的亮度保持在适合人眼观察的范围。
- 图像去雾 /
- 图像增强 /
- 图像分解 /
- 多子块增强 /
- 浓雾图像
Abstract:
Aimed at the problem that the existing algorithms are not ideal to enhance foggy images with non-uniform fog distribution, this paper proposes a foggy image enhancement algorithm based on multi-block coordinated single-scale Retinex. Different from traditional Retinex algorithms that use the global statistic to obtain dynamic truncation values, the proposed algorithm first divides the image into several sub-blocks to calculate dynamic truncation values suitable for different areas with different concentrations of fog. Then, the dynamic range of detail information is adjusted with these dynamic truncation values to obtain multiple locally optimal images. Finally, the final enhancement image is calculated by fusing multiple optimal local images. This strategy enables the enhancement of detail in each area of a foggy image. The experimental results show that the proposed algorithm can effectively remove the non-uniform fog and ensure that the brightness of defogged image is kept within a range suitable for human eyes.
- image defogging /
- image enhancement /
- image decomposition /
- multi-block enhancement /
- foggy image

HTML全文

图 1 单尺度Retinex处理结果

Figure 1. Processed result of single-scale Retinex

下载: 全尺寸图片幻灯片

图 2 利用不同局部均值统计拉伸量化后结果

Figure 2. Stretched quantization result using different local mean statistics

下载: 全尺寸图片幻灯片

图 3 基于多子块协同的单尺度Retinex算法流程

Figure 3. Flowchart of multi-block coordinated single-scale Retinex algorithm

下载: 全尺寸图片幻灯片

图 4 去雾效果对比示例1

Figure 4. Example 1 of defogged result comparison

下载: 全尺寸图片幻灯片

图 5 去雾效果对比示例2

Figure 5. Example 2 of defogged result comparison

下载: 全尺寸图片幻灯片

图 6 去雾效果对比示例3

Figure 6. Example 3 of defogged result comparison

下载: 全尺寸图片幻灯片

表 1 图 4去雾后客观指标评价结果

Table 1. Objective indicator evaluation results of defogged images in Fig. 4

图像编号	h	e	γ
图 4(b)	6.57	284.20	8.42
图 4(c)	6.92	56.96	3.82
图 4(d)	7.38	247.70	7.07
图 4(e)	5.43	8.87	2.21
图 4(f)	7.24	286.73	9.47

下载: 导出CSV

表 2 图 5去雾后客观指标评价结果

Table 2. Objective indicator evaluation results of defogged images in Fig. 5

图像编号	h	e	γ
图 5(b)	6.23	2.38	4.60
图 5(c)	6.94	1.36	1.89
图 5(d)	7.11	0.10	3.03
图 5(e)	7.46	0.51	1.67
图 5(f)	6.38	4.35	6.18

下载: 导出CSV

表 3 图 6去雾后客观指标评价结果

Table 3. Objective indicator evaluation results of defogged images in Fig. 6

图像编号	h	e	γ
图 6(b)	6.59	248.67	7.48
图 6(c)	6.46	283.46	3.47
图 6(d)	7.53	281.39	6.78
图 6(e)	5.43	9.39	1.37
图 6(f)	7.37	358.36	13.13

下载: 导出CSV

参考文献(39)

[1]	代书博, 徐伟, 朴永杰, 等.基于暗原色先验的遥感图像去雾方法[J].光学学报, 2017, 37(3):341-347. http://d.old.wanfangdata.com.cn/Thesis/Y3168183 DAI S B, XU W, PIAO Y J, et al. Remote sensing image defogging based on dark channel prior[J].Acta Optica Sinica, 2017, 37(3):341-347(in Chinese). http://d.old.wanfangdata.com.cn/Thesis/Y3168183
[2]	崔运前.图像去雾技术研究与实现[D].南京: 南京理工大学, 2017: 1-8. http://cdmd.cnki.com.cn/Article/CDMD-10288-1017053387.htm CUI Y Q.Research and implementation of image dehazing technology[D].Nanjing: Nanjing University of Science and Technology, 2017: 1-8(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-10288-1017053387.htm
[3]	王圣江, 童冬生, 王海平, 等.视频监控取证系统在海警舰艇上的应用[J].中国公共安全(学术版), 2014(1):105-108. doi: 10.3969/j.issn.1672-2396.2014.01.027 WANG S J, TONG D S, WANG H P, et al.Application of video monitoring evidence system on the coast guard ship[J].China Public Security(Academy Edition), 2014(1):105-108(in Chinese). doi: 10.3969/j.issn.1672-2396.2014.01.027
[4]	MCCARTNEY E J.Optics of the atmosphere:Scattering bymolecules and particles[M].New York:John Wiley and Sons, 1976:13-51.
[5]	NARASIMHAN S G, NAYAR S K.Interactive (de)weathering of an image using physical models[C]//IEEE Workshop on Color and Photometric Methods in Computer Vision.Piscataway, NJ: IEEE Press, 2003: 1-8.
[6]	SCHECHNER Y Y, NARASIMHAN S G, NAYAR S K.Instant dehazing of images using polarization[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2001: 325-332.
[7]	SCHECHNER Y Y, NARASIMHAN S G, NAYAR S K.Polarization-based vision through haze[J].Applied Optics, 2003, 42(3):511-525. doi: 10.1364/AO.42.000511
[8]	SHWARTZ S, NAMER E, SCHECHNER Y Y.Blind haze separation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2006: 1984-1991.
[9]	孙玉宝, 肖亮, 韦志辉, 等.基于偏微分方程的户外图像去雾方法[J].系统仿真学报, 2007, 33(3):55-58. http://d.old.wanfangdata.com.cn/Periodical/xtfzxb200716030 SUN Y B, XIAO L, WEI Z H, et al.Method of defogging image of outdoor scenes based on PDE[J].Journal of System Simulation, 2007, 33(3):55-58(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/xtfzxb200716030
[10]	翟艺书, 柳晓鸣, 涂雅媛.基于模糊逻辑的雾天降质图像对比度增强算法[J].计算机应用, 2008, 28(3):662-664. http://d.old.wanfangdata.com.cn/Periodical/jsjyy200803034 ZHAI Y S, LIU X M, TU Y Y.Contrast enhancement algorithm for fog-degraded image based on fuzzy logic[J].Computer Applications, 2008, 28(3):662-664(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/jsjyy200803034
[11]	NARASIMHAN S G, NAYAR S K.Chromatic framework for vision in bad weather[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2000: 598-605.
[12]	NARASIMHAN S G, NAYAR S K.Vision and the atmosphere[J].International Journal of Computer Vision, 2002, 48(3):233-254. doi: 10.1023/A:1016328200723
[13]	KOPF J, NEUBERT B, CHEN B, et al.Deep photo:Model-based photograph enhancement and viewing[J].ACM Transactions on Graphics, 2008, 27(5):1-10. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0210187593/
[14]	NARASIMHAN S G, NAYAR S K.Removing weather effects from monochrome images[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2001: 186-193.
[15]	TAN R T.Visibility in bad weather from a single image[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2008: 1-8.
[16]	FATTAL R.Single image de-hazing[J].ACM Transactions on Graphics, 2008, 27(3):72. http://d.old.wanfangdata.com.cn/Periodical/dzcljs201603011
[17]	HE K M, SUN J, TANG X O.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2009: 1956-1963.
[18]	FATTAL R.De-hazing using color-lines[J].ACM Transactions on Graphics, 2014, 34(1):13.
[19]	ZHU Q, MAI J, SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing, 2015, 24(11):3522-3533. doi: 10.1109/TIP.2015.2446191
[20]	BERMAN D, TREIBITZ T, AVIDAN S.Non-local image dehazing[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2016: 1674-1682.
[21]	CAI B, XU X, JIA K, et al.DehazeNet:An end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing, 2016, 25(11):5187-5198. doi: 10.1109/TIP.2016.2598681
[22]	REN W Q, LIU S, ZHANG H, et al.Single image dehazing via multi-scale convolutional neural networks[C]//European Conference on Computer Vision, 2016: 154-169.
[23]	LI B, PENG X, WANG Z, et al.AOD-Net: All-in-One dehazing network[C]//IEEE International Conference on Computer Vision.Piscataway, NJ: IEEE Press, 2017: 4780-4788.
[24]	ORCHARD M T, BOUMAN C A.Color quantization of images[J].IEEE Transactions on Signal Processing, 1991, 39(12):2677-2690. doi: 10.1109/78.107417
[25]	KIM T K, PAIK J K, KANG B S.Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering[J].IEEE Transactions on Consumer Electronics, 1998, 44(1):82-87. doi: 10.1109/30.663733
[26]	KIM J Y, KIM L S, HWANG S H.An advanced contrast enhancement using partially overlapped sub-block histogram equalization[J].IEEE Transactions on Circuits and Systems for Video Technology, 2002, 11(4):475-484. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0214906169/
[27]	ZUIDERVELD K.Contrast limited adaptive histogram equalization[M]//JAMES A.Graphics gems.San Diego, CA: Academic Press Professional, Inc., 1994: 474-485.
[28]	XU H, ZHAI G, WU X, et al.Generalized equalization model for image enhancement[J].IEEE Transactions on Multimedia, 2014, 16(1):68-82. doi: 10.1109/TMM.2013.2283453
[29]	WANG S H, CHO W, JANG J, et al.Contrast-dependent saturation adjustment for outdoor image enhancement[J].Journal of the Optical Society of America A-Optics Imaging Science and Vision, 2017, 34(1):2532-2542. doi: 10.1364/JOSAA.34.000007
[30]	ERIKSSON B.Automatic image de-weathering using curvelet-based vanishing point detection[J].Communications on Pure and Applied Mathematics, 2007, 3(5):219-232.
[31]	ZIA R.Properties of a center/surround Retinex: Part 1.Signal processing design: cr198194[R].Washington, D.C.: NASA, 1995.
[32]	JOBSON D J, GLENN A W.Properties of a center/surround Retinex: Part 2.Surround design: tm110188[R].Washington, D.C.: NASA, 1995.
[33]	RAHMAN Z U, JOBSON D J, WOODELL G A.Multi-scale Retinex for color image enhancement[C]//IEEE International Conference on Image Processing.Piscataway, NJ: IEEE Press, 2002: 1003-1006.
[34]	WANG W, LI B, ZHENG J, et al.A fast multi-scale Retinex algorithm for color image enhancement[C]//IEEE International Conference on Wavelet Analysis and Pattern Recognition.Piscataway, NJ: IEEE Press, 2008: 80-85.
[35]	肖胜笔, 李燕.具有颜色保真性的快速多尺度Retinex去雾算法[J].计算机工程与应用, 2015, 51(6):176-180. doi: 10.3778/j.issn.1002-8331.1410-0045 XIAO S B, LI Y.Fast multiscale Retinex algorithm of image haze removal with color fidelity[J].Computer Engineering and Applications, 2015, 51(6):176-180(in Chinese). doi: 10.3778/j.issn.1002-8331.1410-0045
[36]	WANG J, LU K, XUE J, et al.Single image dehazing based on the physical model and MSRCR algorithm[J].IEEE Transactions on Circuits and Systems for Video Technology, 2017, 28(9):2190-2199. https://www.researchgate.net/publication/318551732_Single_Image_Dehazing_Based_on_the_Physical_Model_and_MSRCR_Algorithm
[37]	HE K M, SUN J, TANG X O.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6):1397-1409. doi: 10.1109/TPAMI.2012.213
[38]	YE Z, MOHAMADIAN H, YE Y.Discrete entropy and relative entropy study on nonlinear clustering of underwater and arial images[C]//IEEE International Conference on Control Applications.Piscataway, NJ: IEEE Press, 2007: 313-318.
[39]	HAUTIERE N, TAREL J P, AUBERT D, et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology, 2008, 27(2):87-95. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_320fb103b4a9eea153bb293dd73e7f82