基于目标场景颜色恢复的偏振图像去雾算法

doi:10.19678/j.issn.1000-3428.0069450

摘要/Abstract

摘要：

尽管现有图像去雾方法在处理浓雾场景时可基本去除图像中的雾气, 但在复原过程中容易导致图像的颜色分布发生明显偏移。针对传统偏振去雾算法色彩失真的问题, 提出一种基于目标场景颜色恢复的偏振图像去雾算法。根据大气光饱和度低与亮度高的特征, 结合总光强图和偏振差分图估计无穷远处大气光值, 以降低白色高亮物体的影响。充分利用无穷远处大气光的估计位置来提取大气光偏振角, 并通过Stokes矢量自动估算出随深度变化的大气光偏振度矩阵。基于大气散射光边缘跳变处的空间相关性, 利用大气光偏振度与图像色度构建正则化约束来校正大气散射光。此外, 为提升目标场景的色彩保真度, 提出自适应色彩均衡方法来改善复原结果的颜色分布。实验结果表明, 相比DCP、BCCR、GPLPF、PLF、POBS等经典去雾算法, 所提算法的NIQE、BRISQUE和偏色因子K分别提升了9.62%、13.49%、40.13%, 并且对于不同雾霾浓度场景均具有良好的复原效果, 有效提高了不同深度下目标的能见度, 避免出现颜色失真现象, 尤其是对浓雾场景同样适用。

关键词: 偏振去雾, 大气光校正, 颜色失真, Stokes矢量, 正则化约束

Abstract:

When processing fog scenes, current image dehazing methods can remove fogs from an image but they tend to cause the color distribution of the image to shift significantly during the restoration process. This study proposes a polarization image dehazing algorithm based on target scene color restoration to address the problem of color distortion in traditional polarization dehazing algorithms. By leveraging the characteristics of low saturation and high brightness of atmospheric light and combining them with the total light intensity and polarization difference diagrams, atmospheric light value at infinity is estimated to reduce the influence of white-highlighted objects. The estimated position of atmospheric light at infinity is used to extract the polarization angle of atmospheric light, and the polarization matrix of atmospheric light varying with depth is automatically estimated using the Stokes vector. Based on the spatial correlation at the edge jumps of atmospheric scattered light, regularization constraints are constructed using atmospheric polarization and image chromaticity to correct the atmospheric scattered light. In addition, to improve the color fidelity of the target scene, this study proposes an adaptive color equalization method to improve the color distribution of the restored results. Compared with classical dehazing algorithms such as DCP, BCCR, GPLPF, PLF, and POBS, the proposed algorithm improves the NIQE, BRISQUE, and color deviation factor K by 9.62%, 13.49%, and 40.13%, respectively. Moreover, it has good restoration effects for scenes with different haze concentrations, effectively improving the visibility of targets at different depths and avoiding color distortion, particularly for dense fog scenes.

Key words: polarization dehazing, atmospheric light correction, color restoration, Stokes vector, regularization constraint

孙超, 范之国, 罗茂文, 胡泉. 基于目标场景颜色恢复的偏振图像去雾算法[J]. 计算机工程, 2025, 51(9): 268-279.

SUN Chao, FAN Zhiguo, LUO Maowen, HU Quan. Polarization Image Dehazing Algorithm Based on Target Scene Color Restoration[J]. Computer Engineering, 2025, 51(9): 268-279.

https://www.ecice06.com/CN/Y2025/V51/I9/268

图/表 15

图1 频域低通滤波偏振去雾方法在不同p_A和

$A_{\infty}$

条件下的复原实验结果

Fig.1 Restoration experimental results of the frequency domain low-pass filtering polarization dehazing method under differentp_Aand

$A_{\infty}$

conditions

图2 无穷远处大气光

$A_{\infty}$

估计分布图

Fig.2 Estimated distribution maps of atmospheric light

$A_{\infty}$

at infinity

图3 两组雾天场景下预处理的大气光图像与复原结果及其局部放大结果分析

Fig.3 Analysis of preprocessed atmospheric light images and restoration results, as well as local magnification results, in two sets of foggy scenes

图4 浓雾场景下所提算法的去雾结果及其色彩均衡方法校正结果

Fig.4 The dehazing results of the proposed algorithm and color balance correction results in dense fog scenes

图5 所提算法流程图

Fig.5 Flowchart of the proposed algorithm

图6 大气偏振信息观测平台

Fig.6 Atmospheric polarization information observation platform

图7 所提算法在不同雾霾浓度下目标场景的复原结果

Fig.7 The restoration results of the proposed algorithm in target scenes under different haze concentrations

图8 浓雾场景下所提算法的复原结果、晴天无雾图像的颜色通道直方图分布以及对应的颜色特征指标值

Fig.8 The restoration results of the algorithm proposed in dense fog scenes, the color channel histogram distribution of clear and foggy images, and the corresponding color feature index values

图9 有天空区域的目标场景下不同方法的去雾结果比较

Fig.9 Comparison of dehazing results using different methods in target scenes with sky regions

图10 无天空区域的目标场景下不同方法的去雾结果比较

Fig.10 Comparison of dehazing results of different methods in target scenes without sky regions

图11 消融实验的去雾结果比较

Fig.11 Comparison of dehazing results of ablation experiments

参考文献 32

1	AKERLIND C, HALLBERG T, ERIKSSON J, et al. Optical polarization: background and camouflage[C]//Proceedings of Society of Photo-optical Instrumentation Engineers. [S. l. ]: Society of Photo-Optical Instrumentation Engineers, 2017: 1043204.
2	NEVEN D, DE BRABANDERE B, GEORGOULIS S, et al. Towards end-to-end lane detection: an instance segmentation approach[C]//Proceedings of 2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Washington D. C., USA: IEEE Press, 2018: 286-291.
3	PARNET F, FADE J, ORTEGA QUIJANO N, et al. Free-space active polarimetric imager operating at 1.55 μm by orthogonality breaking sensing. Optics Letters, 2017, 42(4): 723- 726. doi: 10.1364/OL.42.000723
4	JOBSON D J, RAHMAN Z, WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image Processing, 2002, 6(7): 965- 976.
5	JOHN J, WILSCY M. Enhancement of weather degraded color images and video sequences using wavelet fusion[C]//Proceedings of the 7th IEEE International Conference on Cybernetic Intelligent Systems. Washington D. C., USA: IEEE Press, 2009: 99-109.
6	王斌, 白永强, 朱仲杰, 等. 联合空角信息的无参考光场图像质量评价. 光电工程, 2024, 51(9): 240139.
	WANG B, BAI Y Q, ZHU Z J, et al. No-reference light field image quality assessment based on joint spatial-angular information. Opto-Electronic Engineering, 2024, 51(9): 240139.
7	卞鹏程, 郑忠龙, 李明禄, 等. 基于注意力融合网络的视频超分辨率重建. 计算机应用, 2021, 41(4): 1012- 1019.
	BIAN P C, ZHENG Z L, LI M L, et al. Attention fusion network based on video super-resolution reconstruction. Journal of Computer Applications, 2021, 41(4): 1012- 1019.
8	KHODJA A, ZHENG Z L, MO J S Z, et al. Rain to rain: learning real rain removal without ground truth. IEEE Access, 2021, 9, 57325- 57337. doi: 10.1109/ACCESS.2021.3072687
9	DONG Y, LIU Y H, ZHANG H, et al. FD-GAN: generative adversarial networks with fusion-discriminator for single image dehazing[EB/OL]. [2024-01-20]. https://arxiv.org/pdf/2001.06968.
10	黄山, 贾俊. 基于改进循环生成式对抗网络的图像去雾方法. 计算机工程, 2022, 48(12): 218-223, 231. doi: 10.19678/j.issn.1000-3428.0064162
	HUANG S, JIA J. Image defogging method based on improved cycle-consistent adversarial network. Computer Engineering, 2022, 48(12): 218-223, 231. doi: 10.19678/j.issn.1000-3428.0064162
11	卢昂, 储珺, 冷璐. 基于高低频特征增强的图像去雾. 计算机工程, 2023, 49(8): 174- 181. doi: 10.19678/j.issn.1000-3428.0064826
	LU A, CHU J, LENG L. Image dehazing based on high-frequency and low-frequency feature enhancement. Computer Engineering, 2023, 49(8): 174- 181. doi: 10.19678/j.issn.1000-3428.0064826
12	HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341- 2353. doi: 10.1109/TPAMI.2010.168
13	ZHU Q S, MAI J M, SHAO L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 2015, 24(11): 3522- 3533. doi: 10.1109/TIP.2015.2446191
14	BERMAN D, AVIDAN S. Non-local image dehazing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2016: 1674-1682.
15	SCHECHNER Y Y, NARASIMHAN S G, NAYAR S K. Instant dehazing of images using polarization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2001: 1-8.
16	LIANG J, REN L Y, JU H J, et al. Visibility enhancement of hazy images based on a universal polarimetric imaging method. Journal of Applied Physics, 2014, 116(17): 820- 827.
17	SHEN L H, ZHAO Y Q, PENG Q N, et al. An iterative image dehazing method with polarization. IEEE Transactions on Multimedia, 2019, 21(5): 1093- 1107. doi: 10.1109/TMM.2018.2871955
18	邵子奇, 金海红, 钱立进, 等. 基于大气光偏振层析的雾天图像重构方法. 激光与光电子学进展, 2020, 7(22): 121- 131.
	SHAO Z Q, JIN H H, QIAN L J, et al. Method of haze image reconstruction based on polarization layering and analysis of airlight. Laser & Optoelectronics Progress, 2020, 7(22): 121- 131.
19	张文飞, 满忠胜, 葛筱璐, 等. 一种快速实现的偏振光学去雾方法. 激光与光电子学进展, 2019, 56(14): 157- 162.
	ZHANG W F, MAN Z S, GE Y L, et al. Fast dehazing method based on polarizition opticals. Laser & Optoelectronics Progress, 2019, 56(14): 157- 162.
20	ZHANG X D, SONG M Y, FAN Z G, et al. Reconstruction algorithm of haze image based on blind separation model of polarized orthogonal airlight. Optics Express, 2022, 30(23): 42097- 42113. doi: 10.1364/OE.472886
21	COX L J. Optics of the atmosphere-scattering by molecules and particles. Optica Acta: International Journal of Optics, 1977, 24(7): 779.
22	LIANG J, JU H J, REN L Y, et al. Generalized polarimetric dehazing method based on low-pass filtering in frequency domain. Sensors, 2020, 20(6): 1- 12. doi: 10.1109/JSEN.2020.2973103
23	SUN R, LIAO T B, FAN Z G, et al. Polarization dehazing method based on separating and iterative optimizing airlight from the frequency domain for different concentrations of haze. Applied Optics, 2022, 61(35): 10362- 10373. doi: 10.1364/AO.475021
24	王楚宁, 赵开春. 基于暗通道先验原理的偏振图像去雾. 光学精密工程, 2023, 31(23): 3474- 3481.
	WANG C N, ZAHO K C. Polarization image defogging based on dark channel prior principle. Optics and Precision Engineering, 2023, 31(23): 3474- 3481.
25	倪萍, 赖惠成, 高古学, 等. 基于形态学与梯度域导向滤波的图像去雾算法. 计算机工程, 2022, 48(10): 252- 261. doi: 10.19678/j.issn.1000-3428.0062874
	NI P, LAI H C, GAO G X, et al. Image dehazing algorithm based on morphological and gradient domain guided filtering. Computer Engineering, 2022, 48(10): 252- 261. doi: 10.19678/j.issn.1000-3428.0062874
26	徐晓昭, 蔡轶珩, 刘长江, 等. 基于图像分析的偏色检测及颜色校正方法. 测控技术, 2008, 27(5): 10-12, 21.
	XU X Z, CAI Y H, LIU C J, et al. Color cast detection and color correction methods based on image analysis. Measurement & Control Technology, 2008, 27(5): 10-12, 21.
27	CHOI L K, YOU J, BOVIK A C. Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Transactions on Image Processing, 2015, 24(11): 3888- 3901. doi: 10.1109/TIP.2015.2456502
28	PENG J, YU H Y, WANG Z. Underwater image color analysis and indicators based on statistical characteristics[C]//Proceedings of the 4th International Conference on Computer Vision, Image and Deep Learning (CVIDL). Washington D.C., USA: IEEE Press, 2023: 1-7.
29	MENG G F, WANG Y, DUAN J Y, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2013: 617-624.
30	LIANG J, REN L, LIANG R. Low-pass filtering based polarimetric dehazing method for dense haze removal. Optics Express, 2021, 29(18): 28178- 28189. doi: 10.1364/OE.427629
31	MITTAL A, SOUNDARARAJAN R, BOVIK A C. Making a "completely blind" image quality analyzer. IEEE Signal Processing Letters, 2013, 20(3): 209- 212. doi: 10.1109/LSP.2012.2227726
32	MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing, 2012, 21(12): 4695- 4708. doi: 10.1109/TIP.2012.2214050

[1]	杨斌,林志贤,郭太良. 基于改进容差机制的图像去雾算法[J]. 计算机工程, 2019, 45(1): 226-232.
[2]	康牧, 王子须. 一种基于移植理论的图像旋转算法[J]. 计算机工程, 2012, 38(23): 227-230.

选择文件类型/文献管理软件名称

选择包含的内容