Pixel-labeling-based parameter-adaptive dehazing algorithm for aerial image

doi:10.3785/j.issn.1008-973X.2026.03.011

Journal of ZheJiang University (Engineering Science)

2026, Vol. 60

Issue (3): 556-564 DOI: 10.3785/j.issn.1008-973X.2026.03.011

Pixel-labeling-based parameter-adaptive dehazing algorithm for aerial image

Yinqing HUANG(

),Li ZENG*(

)

School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, China

Download:

HTML

PDF(3894KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A pixel-labeling-based parameter-adaptive dehazing algorithm was proposed to address color distortion, detail blurring and low contrast commonly observed in aerial images captured under foggy conditions. The causes of image degradation were analyzed, and the dehazing task was transformed into pixel-label estimation of atmospheric light and transmission. A pixel-level label assignment model was constructed. A weighted graph optimization method was employed to adaptively adjust the labels and improve the estimation accuracy of atmospheric light value based on image brightness distribution and pixel similarity. A multi-label classification approach was applied to optimize the transmission, eliminating halo effect and edge blurring. The recovered clear images were obtained by using a foggy image restoration model. The experimental results showed that the proposed algorithm effectively suppressed noise, enhanced fine details, and improved image contrast and clarity in various aerial scenes. Significant improvements in information entropy (IE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were observed compared with existing methods, which validated its robustness and generalization capability across diverse foggy environment.

Key words： image dehazing dark channel prior pixel labeling atmospheric light value transmission

Received: 28 February 2025 Published: 04 February 2026

CLC:

TP 391

Fund: 重庆市自然科学基金创新发展联合基金资助项目（CSTB2023NSCQ-LZX0127）；重庆交通大学研究生科研创新项目（2025S0057）.

Corresponding Authors: Li ZENG E-mail: 622230040036@mails.cqjtu.edu.cn;zengli_sichuan@163.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yinqing HUANG
	Li ZENG

Cite this article:

Yinqing HUANG,Li ZENG. Pixel-labeling-based parameter-adaptive dehazing algorithm for aerial image. Journal of ZheJiang University (Engineering Science), 2026, 60(3): 556-564.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2026.03.011 OR https://www.zjujournals.com/eng/Y2026/V60/I3/556

像素标签化参数自适应航拍去雾算法

针对雾天航拍图像中常见的色偏、细节模糊和对比度低等问题，提出像素标签化参数自适应去雾算法. 分析图像降质的成因，将去雾问题转化为大气光值和透射率的像素标签估计任务，构建像素级标签分配模型. 基于图像亮度分布和像素相似性，利用加权图优化方法自适应调整标签，提升大气光值的估计精度. 通过多标签分类方法优化透射率，消除光晕效应和边缘模糊，结合雾天图像复原模型恢复清晰图像. 实验表明，该算法在多种航拍图像中均能够有效地抑制噪声、增强细节，提升图像对比度和清晰度. 与现有的方法相比，所提算法在信息熵（IE）、结构相似度（SSIM）和峰值信噪比（PSNR）等指标上均取得显著的提升，验证了该方法在不同雾天环境下的鲁棒性和泛化能力.

关键词： 图像去雾, 暗通道先验, 像素标签, 大气光值, 透射率

Fig.1 Flowchart of proposed method

Fig.2 Flowchart of atmospheric light estimation

Fig.3 Comparison of dehazing effect between traditional DCP and proposed adaptive atmospheric light value estimation method

Fig.4 Comparison of transmission map performance between DCP method and proposed method

Fig.5 Comparison of dehazing effect before and after applying different methods in mountainous and urban dense fog environment

Fig.6 Comparison of dehazing result of nighttime hazy images 1-3 (from top to bottom) among He method^[14], Meng method^[15] and proposed method

Fig.7 Comparison of dehazing result of daytime hazy images 4-6 (from top to bottom) among He method^[14], Meng method^[15] and proposed method

Tab.1 Objective evaluation result of dehazing performance in fig.6 and fig.7


[1]	王丹. 基于暗通道先验的图像和视频去雾模型及算法研究[D]. 长沙: 国防科学技术大学, 2016. WANG Dan. Mathematical modeling and algorithm on single image and video dehazing [D]. Changsha: National University of Defense Technology, 2016.

[2]	PANDEY P, GUPTA R, GOEL N Comprehensive review of single image defogging techniques: enhancement, prior, and learning based approaches[J]. Artificial Intelligence Review, 2025, 58 (4): 116 doi: 10.1007/s10462-024-11034-4

[3]	LIU R, HE G. A novel dehazing algorithm based on Retinex principle [C]//Proceedings of the International Conference on Machine Learning and Intelligent Systems Engineering. Chongqing: IEEE, 2021: 349–356.

[4]	ACHARYA U K, KUMAR S Image sub-division and quadruple clipped adaptive histogram equalization (ISQCAHE) for low exposure image enhancement[J]. Multidimensional Systems and Signal Processing, 2023, 34 (1): 25- 45 doi: 10.1007/s11045-022-00853-9

[5]	SURYA KAVITA T, VAMSIDHAR A, SUNIL KUMAR G, et al Cascaded combination of total variation regularization and contrast limited adaptive histogram equalization based image dehazing[J]. The Imaging Science Journal, 2025, 73 (2): 213- 226 doi: 10.1080/13682199.2024.2345030

[6]	崔莹. 基于直方图的图像去雾方法[D]. 长春: 吉林大学, 2018. CUI Ying. Histogram based image dehaze algorithm [D]. Changchun: Jilin University, 2018.

[7]	CHEN G, JIA Y, YIN Y, et al. Remote sensing image dehazing using a wavelet-based generative adversarial networks [J]. Scientific Reports, 2025, 15(1): 1–13.

[8]	YANG P, WU H, WANG T, et al Multi-scale underwater image enhancement with optimized homomorphic filter and RGB color correction[J]. Optical Review, 2022, 29 (6): 457- 468 doi: 10.1007/s10043-022-00762-z

[9]	ZAMIR S W, ARORA A, KHAN S, et al Learning enriched features for fast image restoration and enhancement[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (2): 1934- 1948 doi: 10.1109/TPAMI.2022.3167175

[10]	NAYAR S K, NARASIMHAN S G. Vision in bad weather [C]//Proceedings of the 7th IEEE International Conference on Computer Vision. Kerkyra: IEEE, 2002: 820–827.

[11]	TAN K K, OAKLEY J P Physics-based approach to color image enhancement in poor visibility conditions[J]. Journal of the Optical Society of America A, Optics, Image Science, and Vision, 2001, 18 (10): 2460- 2467 doi: 10.1364/JOSAA.18.002460

[12]	TAN R T. Visibility in bad weather from a single image [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1–8.

[13]	FATTAL R. Single image dehazing [C]//ACM Transactions on Graphics. [S. l. ]: ACM, 2008.

[14]	HE K, SUN J, TANG X Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33 (12): 2341- 2353

[15]	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. Sydney: IEEE, 2013: 617–624.

[16]	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

[17]	HASSAN H, BASHIR A K, AHMAD M, et al. Real-time image dehazing by superpixels segmentation and guidance filter [J]. Journal of Real-Time Image Processing, 2020, 18(5): 1–21.

[18]	金天虎, 陶砚蕴, 李佐勇基于超像素图像分割的暗通道先验去雾改进算法[J]. 电子学报, 2023, 51 (1): 146- 159 JIN Tianhu, TAO Yanyun, LI Zuoyong An improved dark channel prior dehazing algorithm based on superpixel image segmentation[J]. Acta Electronica Sinica, 2023, 51 (1): 146- 159

[19]	KUMARI A, SAHOO S K A new fast and efficient dehazing and defogging algorithm for single remote sensing images[J]. Signal Processing, 2024, 215: 109289 doi: 10.1016/j.sigpro.2023.109289

[20]	邱啟蒙, 张亚加, 高智强, 等基于四叉树分级搜索和透射率优化的水下图像复原[J]. 光学学报, 2023, 43 (12): 1201002 QIU Qimeng, ZHANG Yajia, GAO Zhiqiang, et al Underwater image restoration based on quadtree hierarchical search and transmittance optimization[J]. Acta Optica Sinica, 2023, 43 (12): 1201002 doi: 10.3788/AOS221598

[21]	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 doi: 10.1109/TPAMI.2003.1201821

[22]	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

[23]	HE K, SUN J, TANG X Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35 (6): 1397- 1409 doi: 10.1109/TPAMI.2012.213

[24]	ZHOU J, ZHANG D, ZOU P, et al Retinex-based Laplacian pyramid method for image defogging[J]. IEEE Access, 2019, 7: 122459- 122472 doi: 10.1109/ACCESS.2019.2934981

[25]	王健, 秦春霞, 杨珂, 等基于HSV透射率加权修正的机载视频去雾系统设计[J]. 西南交通大学学报, 2021, 56 (1): 160- 167 WANG Jian, QIN Chunxia, YANG Ke, et al Design of airborne video dehazing system for UCAV based on HSV transmission weighted correction[J]. Journal of Southwest Jiaotong University, 2021, 56 (1): 160- 167

[26]	WANG Z, BOVIK A C, SHEIKH H R, et al Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13 (4): 600- 612 doi: 10.1109/TIP.2003.819861

[1]	Yan YANG,Lipeng CHAO. A two-branch feature joint dehazing network based on multidimensional collaborative attention[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(6): 1119-1129.

[2]	Xianglei YIN,Shaopeng QU,Yongfang XIE,Ni SU. Occluded bird nest detection based on asymptotic feature fusion and multi-scale dilated attention[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(3): 535-545.

[3]	Yan YANG,Cunpeng JIA. An efficient image dehazing algorithm with Agent Attention for domain feature interaction[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(12): 2527-2538.

[4]	Mengyuan HAO,Leike ZHANG,Xiaolian LIU,Xueni WANG,Yu TIAN. Pumps and valves joint optimization control in complex water conveyance system based on artificial rabbits optimization algorithm[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(10): 2115-2124.

[5]	Qing Lü,Jiafei HU,Jian MA,Xianhong HUA,Gang XU. Shear performance of shear connectors for prefabricated foundation of transmission tower[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(6): 1153-1160.

[6]	Xiaozhe MENG,Yuxin FENG,Zhuo SU,Fan ZHOU. Real-world dehazing method with invariant learning[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(2): 268-278.

[7]	Jian-zhao ZHANG,Ji-chang GUO,Yu-dong WANG. Underwater image enhancement algorithm via fusing reverse medium transmission map[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(5): 921-929.

[8]	Yang-zhao CHEN,Wei-na YUAN. Deep learning aided multi-user detection for up-link grant-free NOMA[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 816-822.

[9]	Guo-hui SHEN,Bao-heng LI,Yong GUO,Zheng ZHAO,Feng PAN. Calculation methods of torsion response and torsion equivalent static wind loading of transmission tower[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(3): 579-589.

[10]	Zhen-hong MA,Zhen LIU,Sheng-yong YIN,Rong-wei MA,Ke-ping YAN. Experimental study on melanoma cell ablation by high-voltage nanosecond pulsed electric field[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(6): 1168-1174.

[11]	Fang-ping HUANG,Guo-fang GONG,Can-jun YANG,Hua-yong YANG. Simulation and experimental study of energy-capturing and wave-dissipating floating breakwater with S type blade[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(5): 866-874.

[12]	Xiao-hu WANG,Ni-du JIKE,Shan CHEN,Yu-xuan QI,Yu PENG,Qiang ZENG. Water imbibition in concrete in-situ traced by transmission X-ray radiography[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(4): 727-732.

[13]	Xue-yun CHEN,Jin XIA,Ke DU. Overhead transmission line detection based on multiple linear-feature enhanced detector[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(12): 2382-2389.

[14]	Guo-hui SHEN,Yu-nan BAO,Yong GUO,Gang SONG,Yi-wen WANG. Along-line wind loads and distribution patterns of transmission lines[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(9): 1658-1665.

[15]	Yang-jian LI,Wei HE,Hong-wei LIU,Wei LI,Yong-gang LIN,Ya-jing GU. Active damping control for drive train of horizontal-axis tidal current turbines[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(7): 1355-1361.

Viewed

Full text

Abstract

Cited

Shared

Discussed