基于变异鸡群优化透射率估计的去雾算法

doi:10.16180/j.cnki.issn1007-7820.2024.11.004

电子科技 ›› 2024, Vol. 37 ›› Issue (11): 22-30.doi: 10.16180/j.cnki.issn1007-7820.2024.11.004

基于变异鸡群优化透射率估计的去雾算法

吴龙¹, 陈杰¹, 陈淑玉², 杨旭¹, 徐璐¹

1.浙江理工大学计算机科学与技术学院,浙江杭州 310018
2.浙江理工大学科技与艺术学院,浙江绍兴 312369

收稿日期:2023-02-23 出版日期:2024-11-15 发布日期:2024-11-21
作者简介:吴龙(1978-),男,博士,讲师。研究方向:光电信号检测和微波光子学。
陈杰(1997-),男,硕士研究生。研究方向:数字图像处理。
基金资助:
国家自然科学基金(61801429);浙江省自然科学基金(LY20F010001);浙江省自然科学基金(LQ20F050010);浙江理工大学基本科研业务费专项资金(2021Q030)

Image Dehazing Based on Transmittance Estimation by Variant Chicken Swarm Optimization Algorithm

WU Long¹, CHEN Jie¹, CHEN Shuyu², YANG Xu¹, XU Lu¹

1. School of Computer Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China
2. Keyi College,Zhejiang Sci-Tech University,Shaoxing 312369,China

Received:2023-02-23 Online:2024-11-15 Published:2024-11-21
Supported by:
National Natural Science Foundation of China(61801429);Natural Science Foundation of Zhejiang(LY20F010001);Natural Science Foundation of Zhejiang(LQ20F050010);Fundamental Research Funds of Zhejiang Sci-Tech University(2021Q030)

摘要/Abstract

摘要：

在大雾天气下,收集的图片存在清晰度降低和颜色畸变等问题。为获得高质量的去雾图像,文中提出了一种混合暗通道去雾算法。该算法使用Retinex算法去除照射分量的干扰,采用变异鸡群优化算法获得引导滤波所需的导向图片来优化大气透射率,并应用改进的暗通道先验算法来获得去雾图像。相较于其他暗通道先验去雾算法,该方法的平均标准差降低了28.3%,平均峰值信噪比增长了10.3%,平均熵增加了8.0%。测试了同一个场景中不同雾霾程度下的图片,结果显示图片清晰,细节信息保留完整,且评价标准数值基本保持稳定。测试结果表明,所提算法具有较高的鲁棒性和良好的色彩保真能力。

关键词: 图像去雾, 混合暗通道先验算法, 变异鸡群优化算法, 透射率, 大气光强, Retinex, 大气散射模型, 引导滤波

Abstract:

In foggy weather, the collected pictures have the problems of reduced clarity and color distortion. In order to obtain haze-free images with high quality, a hybrid dark channel prior algorithm is proposed in this study. The proposed algorithm employs Retinex algorithm to remove the interference of the illumination component. The variant chicken swarm optimization algorithm is used to obtain the guidance image required by the guided filter to optimize the atmospheric transmittance. The improved dark channel prior algorithm is used to obtain the fog removal image. Compared with other dark channel prior defogging algorithms, the mean standard deviation of the proposed method is reduced by 28.3%, the mean peak signal-to-noise ratio is increased by 10.3% and the mean entropy is increased by 8.0%. In this study, the pictures of different haze levels under the same scene are tested. The results show that the pictures are clear, the details are intact, and the evaluation standard values are basically stable. The above test results indicate that the proposed algorithm has high robustness and color fidelity capabilities.

Key words: image defogging, hybrid dark channel prior algorithm, variant chicken swarm optimization algorithm, transmissivity, atmospheric light intensity, Retinex, atmospheric scattering model, guided filtering

中图分类号:

TP751.1

吴龙, 陈杰, 陈淑玉, 杨旭, 徐璐. 基于变异鸡群优化透射率估计的去雾算法[J]. 电子科技, 2024, 37(11): 22-30.

WU Long, CHEN Jie, CHEN Shuyu, YANG Xu, XU Lu. Image Dehazing Based on Transmittance Estimation by Variant Chicken Swarm Optimization Algorithm[J]. Electronic Science and Technology, 2024, 37(11): 22-30.

图/表 11

图1

图2

图3

图4

表1

表2

表3

表4

表5

图5

表6

参考文献 21

[1]	Ngo D, Lee S, Kang B. Nonlinear unsharp masking algorithm[C]. Barcelona:The International Conference on Electronics,Information,and Communication, 2020:1-6.
[2]	Guo J H, Yang J Y, Yue H J, et al. Landsat-8 OLI multispectral image dehazing based on optimized atmospheric scattering model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(12):10255-10265.
[3]	Ju M Y, Ding C, Ren W Q, et al. IDE:Image dehazing and exposure using an enhanced atmospheric scattering model[J]. IEEE Transactions on Image Processing, 2021, 30(1):2180-2192.
[4]	Qian J M, Li J X, Wang Y B, et al. Underwater image recovery method based on hyperspectral polarization imaging[J]. Optics Communications, 2021, 484(126691):1-8.
[5]	He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353. doi: 10.1109/TPAMI.2010.168 pmid: 20820075
[6]	陆欢. 基于暗原色优化算法的去雾研究[J]. 电子科技, 2020, 33(4):61-64,70.
	Lu Huan. Research on fog removal based on dark primary color optimization algorithms[J]. Electronic Science and Technology, 2020, 33(4):61-64,70.
[7]	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 pmid: 23599054
[8]	Pang C Y, Ji X Q, Sun L N, et al. An improved method of image fast defogging[J]. Acta Photonica Sinica, 2013, 42(7):872-877.
[9]	Zhang D Y, Ju M Y, Wang X M. A fast image haze removal algorithm using dark channel prior[J]. Acta Electronica Sinica, 2015, 43(7):1437-1443.
[10]	何宜鸿, 李彦锋, 黄树恺, 等. 基于深度卷积神经网络的自适应图像去雾算法[J]. 电子科技, 2020, 33(8):70-73.
	He Yihong, Li Yanfeng, Huang Shukai, et al. Adaptive image dehazing algorithm based on deep convolutional neural network[J]. Electronic Science and Technology, 2020, 33(8):70-73.
[11]	Salazar-Colores S, Moya-Sánchez M S, Ramos-Arreguín J M, et al. Fast single image defogging with robust sky detection[J]. IEEE Access, 2020, 8(8):149176-149189.
[12]	Peng Y T, Cao K, Cosman P C. Generalization of the dark channel prior for single image restoration[J]. IEEE Transactions on Image Processing, 2018, 27(6):2856-2868.
[13]	Yan S Y, Zhu J W, Yun K, et al. An infrared image dehazing method based on modified dark channel prior[C]. Guangzhou:International Conference on Biometrics, Microelectronic Sensors, and Artificial Intelligence,the International Society for Optical Engineering, 2022:1-7.
[14]	Ancuti C O, Ancuti C, Timofte R, et al. O-HAZE:A dehazing benchmark with real hazy and haze-free outdoor images[C]. Salt Lake City:IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2018:867-875.
[15]	Silberman N, Hoiem D, Kohli P, et al. Indoor segmentation and support inference from RGBD images[C]. Florence:The Twelfth European Conference on Computer Vision, 2012:746-760.
[16]	郭梦琰, 张娟, 刘巧红, 等. 基于循环生成对抗网络的图像去雾算法[J]. 计算机工程, 2022, 48(3):280-287. doi: 10.19678/j.issn.1000-3428.0059926
	Guo Mengyan, Zhang Juan, Liu Qiaohong, et al. Image dehazing algorithm based on recurrent generative adversarial network[J]. Computer Engineering, 2022, 48(3):280-287. doi: 10.19678/j.issn.1000-3428.0059926
[17]	孟宇飞, 王晓玲, 刘畅, 等. 四分暗通道均值比较法的双角度偏振图像去雾[J]. 激光与光电子学进展, 2022, 59(4):240-248.
	Meng Yufei, Wang Xiaoling, Liu Chang, et al. Dehazing of dual angle polarization image based on mean comparison of quartering dark channels[J]. Laser & Optoelectronics Progress, 2022, 59(4):240-248.
[18]	Yang Y, Wang Z W. Haze removal:Push DCP at the edge[J]. IEEE Signal Processing Letters, 2020, 27(7):1405-1409.
[19]	Cosgun T, Sari M. A novel approach regarding the fixed points of repelling nature[J]. Chaos,Solitons & Fractals, 2021, 153(3):1-7.
[20]	Meng X B, Liu Y, Gao X Z, et al. A new bio-inspired algorithm:Chicken swarm optimization[J]. Current Opinion in Nephrology & Hypertension, 2014, 8794(10):86-94.
[21]	Sun W, Zhang W, Wang J T. Fusion algorithm for foggy image enhancement based on transmittance weight factor[C]. Chengdu:The Fourth International Conference on Artificial Intelligence and Big Data, 2021:419-422.

组别	DCP	FDCP	GDCP	MDCP	HDCP
a	253.793	251.860	254.895	211.887	95.901
b	254.996	254.944	254.999	202.090	140.893
c	254.923	254.738	254.979	204.359	143.147
d	254.496	254.536	229.281	196.636	195.495

组别	DCP/dB	FDCP/dB	GDCP/dB	MDCP/dB	HDCP/dB
a	24.086	24.119	24.067	24.869	28.313
b	24.065	24.066	24.065	25.075	26.642
c	24.067	24.070	24.066	25.027	26.573
d	24.074	24.073	24.527	25.194	25.219

组别	DCP	FDCP	GDCP	MDCP	HDCP
a	0.620 8	0.653 4	0.495 7	0.671 9	0.674 7
b	0.463 0	0.587 6	0.335 4	0.544 7	0.545 9
c	0.533 1	0.581 3	0.544 2	0.534 4	0.589 1
d	0.566 2	0.571 0	0.439 9	0.507 5	0.472 2

组别	DCP	FDCP	GDCP	MDCP	HDCP
a	6.748 1	6.853 9	7.619 6	7.470 7	7.670 1
b	7.324 6	7.272 5	6.857 6	7.614 2	7.848 6
c	6.861 1	6.852 3	7.075 1	7.467 8	7.495 1
d	7.137 6	7.491 8	6.849 5	7.718 1	7.775 3

组别	MSE	PSNR/dB	SSIM	E
DCP	254.807 3	24.069	0.350 8	7.190 9
FDCP	252.954 4	24.101	0.417 9	7.064 6
GDCP	253.294 4	24.095	0.492 0	7.214 2
MDCP	187.339 1	25.405	0.464 8	7.211 0
HDCP	169.886 3	25.829	0.475 9	7.743 5

基于变异鸡群优化透射率估计的去雾算法

Image Dehazing Based on Transmittance Estimation by Variant Chicken Swarm Optimization Algorithm

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 21

相关文章 7

Metrics

本文评价

推荐阅读 0

组别	MSE	PSNR/dB	SSIM	E
DCP	232.756 1	24.462	0.702 6	7.456 1
FDCP	230.576 9	24.503	0.850 3	7.422 2
GDCP	152.222 6	26.306	0.664 9	7.281 2
MDCP	179.088 5	25.600	0.725 1	7.516 1
HDCP	95.361 1	28.337	0.770 4	7.635 7

[1]	孙曦,于莲芝. 基于残差注意力和半监督学习的图像去雾算法[J]. 电子科技, 2023, 36(9): 50-57.
[2]	查俊伟,张洪艳. 动态感受野特征选择去雾网络[J]. 电子科技, 2023, 36(7): 56-63.
[3]	胡晨,胡德敏,胡钰媛,褚成伟. 一种改进的图像阴影去除方法[J]. 电子科技, 2021, 34(4): 41-46.
[4]	何宜鸿,李彦锋,黄树恺,谭万钏. 基于深度卷积神经网络的自适应图像去雾算法[J]. 电子科技, 2020, 33(8): 70-73.
[5]	陆欢. 基于暗原色优化算法的去雾研究[J]. 电子科技, 2020, 33(4): 61-65.
[6]	那彦，任梦乔. 基于引导滤波的遥感图像融合算法[J]. , 2016, 29(8): 121-.
[7]	尹红然, 俞浩, 秦清锋. 一种基于Retinex理论的彩色图像增强算法[J]. , 2012, 25(3): 21-.